Archive / 2026-08-24
August 24, 2026
News
View all news →Xiaomi: New CPU matches Apple cores single threaded, much faster multithreaded
twitter.com24 days ago1003 ptsView detailsJoin discussion
Coding expertise is going to collapse from AI reliance
larsfaye.com24 days ago549 ptsView detailsJoin discussion
RISC-V is now officially supported by CPython
blog.python.org24 days ago305 ptsView detailsJoin discussion
Show HN: A techno machine in one HTML file, with verifiable renders
ssx360.github.io24 days ago236 ptsView detailsJoin discussion
LLMs could control their host machines by exploiting inference engines
boydkane.com24 days ago194 ptsView detailsJoin discussion
FDA clears blood test to aid evaluation for Alzheimer's disease
medicine.washu.edu25 days ago187 ptsView detailsJoin discussion
OCR It – pull text out of un-copyable documents for your LLM
github.com25 days ago140 ptsView detailsJoin discussion
Headlong: A microharness for persistent agents
laude.org24 days ago125 ptsView detailsJoin discussion
lucumr.pocoo.org24 days ago127 ptsView detailsJoin discussion
- Primary source
Disrupting a new covert influence campaign from Russia
OpenAI banned Russia-origin accounts using AI to promote a fake Israel-based think tank and a “sovereignty” index praising Russia and criticizing the West.
openai.com24 days ago95 ptsView details
Hot Chips 2026: CUDA Targets RISC-V – By Chester Lam
chipsandcheese.com24 days ago97 ptsView detailsJoin discussion
dejan.ai24 days ago89 ptsView detailsJoin discussion
yegge.ai24 days ago87 ptsView detailsJoin discussion
Characterizing Agentic Flooding of Government Services
arxiv.org24 days ago82 ptsView detailsJoin discussion
corkmac.app25 days ago83 ptsView detailsJoin discussion
code.joejag.com24 days ago74 ptsView detailsJoin discussion
Show HN: Screen memory without screenshots, just text to Markdown
github.com24 days ago62 ptsView detailsJoin discussion
Your Open Source Model Could Have a Hidden Time-Release Backdoor
morgin.ai25 days ago62 ptsView detailsJoin discussion
The Government Report That Made Me Stop Trusting Our Statistical Agencies
econjared.substack.com24 days ago58 ptsView detailsJoin discussion
github.com24 days ago55 ptsView detailsJoin discussion
80% of developers find AI coding more addictive than helpful
zdnet.com24 days ago38 ptsView detailsJoin discussion
tomtunguz.com25 days ago35 ptsView detailsJoin discussion
Em Dash Is Fine – It Is AI That Sucks
blog.torh.net24 days ago27 ptsView detailsJoin discussion
NetBSD GSoC 2026 Improving RAIDframe
blog.netbsd.org24 days ago27 ptsView detailsJoin discussion
Show HN: See how much your AI knows about you
withcorpus.com24 days ago21 ptsView detailsJoin discussion
github.com24 days ago21 ptsView detailsJoin discussion
Deno team releases Dactyl, an AI app builder that runs on your ChatGPT plan
dactyl.dev24 days ago20 ptsView detailsJoin discussion
Some of Russia's A.I. Drones Are Powered by Nvidia
nytimes.com25 days ago18 ptsView detailsJoin discussion
Show HN: I built a lite LPU that can do inference on Karpathy's MicroGPT
lpulite.com24 days ago17 ptsView detailsJoin discussion
Scaling Memory Safety: AI-Assisted Rewrites of C/C++ Dependencies to Rust
bughunters.google.com24 days ago16 ptsView detailsJoin discussion
Casio's Bluetooth F-B100W-1A with step-tracker sells out again
notebookcheck.net25 days ago14 ptsView detailsJoin discussion
Nvidia customers notified about AI-related price hikes above 15%
reuters.com24 days ago13 ptsView detailsJoin discussion
A Drone Killed Three Ukrainians. It Was Guided by A.I
nytimes.com24 days ago13 ptsView detailsJoin discussion
What languages are agent skills written in?
plicara.ai24 days ago11 ptsView detailsJoin discussion
StateM: Stateful Control for Long-Horizon Agents
github.com24 days ago11 ptsView detailsJoin discussion
Qualcomm is now a leader of Linux upstreaming for their SoCs
social.kernel.org24 days ago10 ptsView detailsJoin discussion
- Primary source
Introducing the Admin plugin for ChatGPT Work and Codex
Use the Admin plugin for ChatGPT Work and Codex to analyze workspace usage, manage members and permissions, adjust limits, and act on admin requests.
openai.com24 days agoView details
- Primary source
Advancing price-performance for developers with GPT‑5.6 in Kiro
GPT‑5.6 is now available in Kiro, helping developers plan, build, review, and test software with better price-performance.
openai.com24 days agoView details
- Primary source
Wire It, Run It, Deploy It: AI Workflows in Gradio
huggingface.co24 days agoView details
Fastino released GLiNER2.5, replacing span enumeration with boundary prediction so entity width no longer costs compute. Three Apache 2.0 checkpoints ship at 74M, 194M, and 287M parameters, all CPU-runnable. The release adds joint entity-relation decoding, constrained classification, span attributes, and 4,096-word co…
marktechpost.com24 days agoView details
Generalist AI has released GEN-1.5, a robot foundation model that learns a new physical task from a single demonstration. Drop 3–12 seconds of sensorimotor data into its 30-second context window, and the robot performs the task. No gradient updates, no fine-tuning, no task-specific programming. Across 10 diverse manip…
marktechpost.com24 days agoView details
framework that folds aggregate human movement into text-based place embeddings. Language models describe what a place is; they miss how it is used. ME-POIs encodes each visit as a contextualized vector and aligns it with one learnable prototype per POI through contrastive learning, then transfers visit distributions f…
marktechpost.com24 days agoView details
The five largest GPU neoclouds now run on very different models. CoreWeave and Nebius report to the SEC; Lambda and Crusoe are private and heading toward IPOs; Groq rebuilt itself as an inference cloud after licensing its LPU technology to NVIDIA. This comparison checks each provider's live rate card, Q2 2026 financia…
marktechpost.com25 days agoView details
They Dedicated Their Lives to Teaching. Then the Deepfakes Started
The deepfake epidemic in schools is affecting more than students. Four teachers tell WIRED about becoming targets of sexualized, AI-generated content—and how difficult it was to find accountability.
wired.com25 days agoView details
arXiv:2608.22230v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for hate speech moderation, often within human--AI workflows in which reviewers provide feedback before a final decision. Such feedback introduces two manipulation directions: whitewashing hateful content as normal and s…
arxiv.org24 days agoView details
arXiv:2608.22246v1 Announce Type: new Abstract: Harmful content in German social media does real-world damage, from calls to action to criminal defamation. The GermEval 2026 shared task scores its detection in four subtasks. The technical challenge is a severe class imbalance. The harmful classes are rare and share su…
arxiv.org24 days agoView details
Length-Adaptive Decoding for Masked Diffusion Machine Translation
arXiv:2608.22274v1 Announce Type: new Abstract: Machine translation tests masked diffusion language models (dLLMs) because every source token must be rendered faithfully, while fixed canvas decoding must choose target length before denoising. Existing masked diffusion decoding work mainly studies token unmasking order…
arxiv.org24 days agoView details
arXiv:2608.22014v1 Announce Type: new Abstract: Automated prompt and skill optimization typically produces a single static instruction that is reused across inference instances until the next optimization cycle. However, this approach cannot adapt when the required context, constraints, and evidence vary from one inst…
arxiv.org24 days agoView details
arXiv:2608.22312v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that safety behavior learned in the textual space does not reliably transfer…
arxiv.org24 days agoView details
Noise Floor Audit for Agent Benchmarks
arXiv:2608.22331v1 Announce Type: new Abstract: We audit measurement variability for 3 native tool-calling endpoints across 2 providers on the official BFCL multiple and parallel categories, using matched AST grading. At temperature 0, reruns are nearly deterministic across Groq endpoints and a thinking-enabled Gemini…
arxiv.org24 days agoView details
SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality
arXiv:2608.21952v1 Announce Type: new Abstract: Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providing a viable alternative to Transformers. Building upon this, Mamba-2 introduces the Structured State Space Duality (SSD)…
arxiv.org24 days agoView details
Context as an Environment: Programmatic Context Management for Long-Horizon Agents
arXiv:2608.21690v1 Announce Type: new Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to preserve before fut…
arxiv.org24 days agoView details
VisAdj: Learning Adjacency Matrices from Node-Link Images
arXiv:2608.21825v1 Announce Type: new Abstract: Learning adjacency matrices from node-link images is a fundamental problem for recovering structured graph information from visual observations. Existing methods typically rely on fixed KNN-based heuristics for candidate edge selection and fail to capture dependencies am…
arxiv.org24 days agoView details
LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model
arXiv:2608.22295v1 Announce Type: new Abstract: Evaluation of large language models (LLMs) increasingly requires predicting how a model will perform on new questions or tasks before collecting large amounts of new annotations. This problem is challenging because question difficulty, scenario, and underlying capability…
arxiv.org24 days agoView details
Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning
arXiv:2608.21898v1 Announce Type: new Abstract: Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding broken links, inconsistent states, or infeasible tasks. We address the gap between scalable environment generation and…
arxiv.org24 days agoView details
arXiv:2608.21806v1 Announce Type: new Abstract: Computational resources are increasingly central to NLP research, but how closely reported GPU capability aligns with scholarly impact remains unclear. We analyze 13,921 ACL, EMNLP, and NAACL main-conference papers published between 2020 and 2025, using GPU resources as…
arxiv.org24 days agoView details
Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?
arXiv:2608.21827v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved significant progress across a wide range of natural language processing (NLP) tasks, yet their ability to understand literary texts, particularly modern Chinese poetry, remains largely unexplored. The unique literary characteris…
arxiv.org24 days agoView details
SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing
arXiv:2608.22018v1 Announce Type: new Abstract: Hate speech detection has recently shifted from coarse-grained classification to structured parsing, where systems must jointly identify hateful targets, arguments, and target-level labels. However, existing studies primarily emphasize benchmark evaluation while paying l…
arxiv.org24 days agoView details
arXiv:2608.22026v1 Announce Type: new Abstract: Accurate simulation of the long-time evolution of systems governed by partial differential equations (PDEs) is central to scientific computing. Among existing deep learning?based approaches for solving PDEs, neural operators typically rely on extensive trajectory data, w…
arxiv.org24 days agoView details
arXiv:2608.22048v1 Announce Type: new Abstract: Large language models are increasingly deployed on local hardware for privacy, cost, and accessibility reasons. Yet many evaluations emphasize accuracy while fewer quantify local runtime and energy, characterize failure modes, or apply paired statistical comparisons unde…
arxiv.org24 days agoView details
arXiv:2608.21714v1 Announce Type: new Abstract: Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-lingual, low-resource settings. We introduce L\"etzCross, a benchmark for cross-lingual page-level retrieval over Luxembo…
arxiv.org24 days agoView details
MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning
arXiv:2608.21808v1 Announce Type: new Abstract: Multimodal Retrieval-Augmented Generation (RAG) with visual citation is crucial for ensuring the traceability and verifiability of MLLMs. However, current RAG and SFT-based methods struggle to achieve robust cross-modal reasoning, causing imprecise visual citations or de…
arxiv.org24 days agoView details
Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems
arXiv:2608.21384v1 Announce Type: new Abstract: Modern multilingual tokenizers often fragment Ukrainian and other underrepresented Cyrillic-script languages more heavily than English, creating disparities in cost and context capacity. We quantify this overhead across nine production tokenizers and five languages with…
arxiv.org24 days agoView details
On the Role of Citations in Preference Data
arXiv:2608.21376v1 Announce Type: new Abstract: Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against model hallucination and as a means for users to verify the credibility of model outputs. Yet, it is unclear how humans and…
arxiv.org24 days agoView details
No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios
arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adversarial jailbreaks that bypass safety filters to implicit hate that evades detection, the range of risks these models pos…
arxiv.org24 days agoView details
Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review
arXiv:2608.21449v1 Announce Type: new Abstract: Time series arise in a wide range of application domains and are analyzed using machine learning in decision-critical settings. Time series classification (TSC) is one of the most widely studied and relevant tasks. In this context, ensuring the transparency and trustwort…
arxiv.org24 days agoView details
K-Bench: measuring model performance on real scientific agent requests
arXiv:2608.21601v1 Announce Type: new Abstract: Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference solutions, or simulators with a known generative structure. Real scientific requests arrive differently. They are underspecifi…
arxiv.org24 days agoView details
Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching
arXiv:2608.22332v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable problem-solving capabilities when guided by Chain-of-Thought (CoT) prompting, yet the internal mechanisms underlying these improvements remain poorly understood. In this work, we investigate where CoT-related causal eff…
arxiv.org24 days agoView details
arXiv:2608.21821v1 Announce Type: new Abstract: When Wikipedia's language editions describe the same concept, how differently do they frame it? Prior work measures coverage gaps between editions; we measure framing distance for matched concepts. We analyze 2,799 valid articles from 3,000 possible concept-language obse…
arxiv.org24 days agoView details
The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate
arXiv:2608.22152v1 Announce Type: new Abstract: Multi-agent systems built from large language models are deployed widely, yet how much performance is lost when two LLMs must coordinate rather than act alone remains unclear. We formulate the collaboration tax as the team-decentralisation loss of a two-player cooperativ…
arxiv.org24 days agoView details
The Abstention Protocol: RCA for Clos Fabrics
arXiv:2608.21412v1 Announce Type: new Abstract: Root cause analysis (RCA) in large datacenter networks is challenging because telemetry is noisy, partial, and asynchronous. Score-based approaches degrade under these conditions, often yielding unstable or incorrect attributions. We present \textsc{CoreSec}, a productio…
arxiv.org24 days agoView details
Reviewing Model Collapse and Countermeasures
arXiv:2608.21366v1 Announce Type: new Abstract: Driven by massive amounts of web-scale data, generative AI (GenAI) has achieved remarkable progress, enabling various applications in diverse sectors. The advances of GenAI have actuated practitioners to use AI-synthesized data for training next-generation AI models. Und…
arxiv.org24 days agoView details
Bulbul: A Dataset for Dialectal Arabic Speech Recognition
arXiv:2608.21950v1 Announce Type: new Abstract: Arabic automatic speech recognition (ASR) faces unique challenges due to diglossia, extensive regional dialect variation, and limited speech resources. Existing speech datasets often focus on single dialects or large-scale broadcast/web data, leading to trade-offs betwee…
arxiv.org24 days agoView details
When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents
arXiv:2608.22339v1 Announce Type: new Abstract: Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents. Prevailing agent self-evolution paradigms typically rely on a core assumption: equipping LLMs with skill memories derived from successful trajectories will…
arxiv.org24 days agoView details
Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities
arXiv:2608.21444v1 Announce Type: new Abstract: Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet, real-world adoption remains constrained not only by autonomy performance, but by the difficulty of integrating agenti…
arxiv.org24 days agoView details
arXiv:2608.21365v1 Announce Type: new Abstract: As a low-resource language, Khmer presents several retrieval challenges, including limited annotated data, ambiguous word boundaries, weak support in multilingual embedding models, and frequent mixed Khmer-English usage. This paper presents KSE-Web, an analysis of hybrid…
arxiv.org24 days agoView details
Improving Few-Step Language Flows with Untied Self-Conditioning
arXiv:2608.22244v1 Announce Type: new Abstract: Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades sharply with few sampling steps. We trace a source of this degradation to a train--inference mismatch in previous-predicti…
arxiv.org24 days agoView details
arXiv:2608.21761v1 Announce Type: new Abstract: Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information from such data remains challenging. In particular, fine-grained regional geolocalization is challenging because nearby ar…
arxiv.org24 days agoView details
Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion
arXiv:2608.22140v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong reasoning performance, but their robustness to realistic lexical corruption remains poorly understood. We evaluate four open-weight instruction-tuned models and frontier models across four reasoning benchmarks under keyboard no…
arxiv.org24 days agoView details
arXiv:2608.21501v1 Announce Type: new Abstract: Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport operator that converts this evidence into token-level advantages, and an update geometry that turns advantages into policy c…
arxiv.org24 days agoView details
arXiv:2608.22132v1 Announce Type: new Abstract: Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and phenotypes. Existing agents typically rely on static retrieval workflows or coarse-grained prompt rewriting, which can lea…
arxiv.org24 days agoView details
arXiv:2608.21417v1 Announce Type: new Abstract: Flexible manufacturing requires industrial robots to be reprogrammed rapidly as product variants change. This paper presents a language-model-based workflow that generates, validates, and iteratively corrects ABB RAPID robot programs from natural language task descriptio…
arxiv.org24 days agoView details
A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification
arXiv:2608.21570v1 Announce Type: new Abstract: Deploying a safety layer for large language models on commodity hardware is constrained by the guards available to do it: current open guard models hold between 1 and 9 billion parameters, are oriented toward the graphics processing unit, and answer in seconds per reques…
arxiv.org24 days agoView details
arXiv:2608.21605v1 Announce Type: new Abstract: Logic Tensor Network-Enhanced Generative Adversarial Networks (LTN-GANs) inject background knowledge by grounding each logical axiom as a predicate and training the generator to raise its satisfaction, a fuzzy truth value in $[0,1]$. Previous LTN-GAN work grounded every…
arxiv.org24 days agoView details
arXiv:2608.21868v1 Announce Type: new Abstract: Depression assessment from multimodal clinical interviews requires integrating dispersed evidence from multiple symptoms into a coherent PHQ-8 profile. This process is hierarchical: relevant evidence is often sparse and context-dependent within local question-answer exch…
arxiv.org24 days agoView details
Hints, Critics, and Teachers: Prior Injection for Sparse-Reward RL in Vision-Language Math Reasoning
arXiv:2608.21811v1 Announce Type: new Abstract: Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answers 3.6% of rollouts correctly, 85-97% of GRPO rollout groups are entirely wrong and contribute zero gradient. We train e…
arxiv.org24 days agoView details
Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
arXiv:2608.22034v1 Announce Type: new Abstract: Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks and architectures. We introduce Coherentist Probabilistic Compositionalism (CPC), an interpretive framework that ground…
arxiv.org24 days agoView details
arXiv:2608.21702v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity, optionally followed by reranking--often returns documents that share keywords with the query without containing the nee…
arxiv.org24 days agoView details
arXiv:2608.21871v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human-curated task collections. Zero-data self-play removes this dependency, but existing methods vet learnability only by pr…
arxiv.org24 days agoView details
arXiv:2608.21668v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training data and stress-test tutoring systems. However, common prompt-based approaches leave the answer decision to the LLM, whi…
arxiv.org24 days agoView details
TessIndex: Capability Verified Identity System for the Agent Economy
arXiv:2608.21942v1 Announce Type: new Abstract: Software systems have traditionally been organized around applications where human users act as principal decision-makers. Recent developments in agentic capabilities alter this paradigm: software agents now autonomously translate high-level goals into structured tasks,…
arxiv.org24 days agoView details
Semantics or Structure? Auditing Text Sensitivity in Multimodal Time-Series Forecasting
arXiv:2608.22321v1 Announce Type: new Abstract: Multimodal time-series forecasting has emerged as a promising paradigm in which natural-language context is expected to improve predictive performance. Recent multimodal foundation models, including Aurora, as well as early- and late-fusion approaches such as MM-TSFlib a…
arxiv.org24 days agoView details
Redteaming Leading Arabic LLMs with ASAS
arXiv:2608.21985v1 Announce Type: new Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical. However, Arabic LLM safety remains underexplored, especially in adversarial evaluation settings. We introduce the Arab…
arxiv.org24 days agoView details
arXiv:2608.21558v1 Announce Type: new Abstract: Recent advances in LLMs and the adoption of RAG systems in industry have created a need for domain-specific question-answer datasets that can assess RAG performance on proprietary data. Existing datasets, such as HotpotQA, challenge current RAG systems on Wikipedia-based…
arxiv.org24 days agoView details
arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing prefix-caching systems reduce this cost but require prompts to share a leading contiguous prefix, limiting effectiveness…
arxiv.org24 days agoView details
arXiv:2608.21418v1 Announce Type: new Abstract: Manufacturing knowledge graphs that integrate data from heterogeneous industrial systems face a trust deficit: consumers cannot determine whether queried data is valid, whether it was valid when a decision was made, where it originated, or how it was acted upon. We argue…
arxiv.org24 days agoView details
Enhanced Artificial Neural Networks Using QHAdamW in Air Quality Forecasting
arXiv:2608.21463v1 Announce Type: new Abstract: The study employed an Artificial Neural Network in combination with the optimized Adaptive Moment Estimation (Adam) algorithm, currently the only AQI forecasting model available in the Philippines. The modified QHAdamW - Quasi-Hyperbolic Momentum (QHAdam) and Adam with d…
arxiv.org24 days agoView details
AIREP: A Protocol for Per-Decision Evidence in AI Runtime Governance
arXiv:2608.21363v1 Announce Type: new Abstract: A protocol is presented for recording the governance decisions of automated AI runtimes. When a runtime releases, blocks, defers, redacts, or escalates an individual output, AIREP records that decision as a single signed object that any party can check offline, independe…
arxiv.org24 days agoView details
There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items
arXiv:2608.21382v1 Announce Type: new Abstract: Multiple-choice benchmarks fix the questions and the correct answers, but not the harness: the order of the options, the wording of the prompt, and whether a language model's answer is read from generated text or from per-option likelihoods. Work on this harness sensitiv…
arxiv.org24 days agoView details
arXiv:2608.21969v1 Announce Type: new Abstract: Humans have multiple levels of temporal abstractions on daily interaction and thinking, such as concept perception and strategic planning. Inspired by this nature, we propose a two-level hierarchical reinforcement learning (RL) framework for conversational agents, bridgi…
arxiv.org24 days agoView details
Distinguishing Revision and Delayed Elaboration in Incremental Narrative Interpretation
arXiv:2608.21364v1 Announce Type: new Abstract: Both human and AI systems that process narrative or long-form content operate incrementally: input is received over time, and internal representations must be updated accordingly. Incremental interpretation, therefore, depends not only on what is represented but also on…
arxiv.org24 days agoView details
Real-TurnTurk: A Multimodal Turkish Corpus for Turn-Taking Prediction
arXiv:2608.22071v1 Announce Type: new Abstract: Turn-taking is a basic organizational feature of human conversation and remains difficult to model in natural, synchronous dialog systems. While existing research has explored multimodal approaches and large language models for turn-ending prediction, there is a lack of…
arxiv.org24 days agoView details
Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms
arXiv:2608.22335v1 Announce Type: new Abstract: Bengali is the seventh-most-spoken language globally, yet LLM safety evaluation remains overwhelmingly English-centric. We introduce BanglaSafe, a benchmark of 879 Bengali prompts combining 309 natively authored prompts with 570 expert-reviewed prompts, spanning 17 cultu…
arxiv.org24 days agoView details
Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs
arXiv:2608.22367v1 Announce Type: new Abstract: Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally degrading as output length increases. We identify two structural deficiencies in existing decoding methods as primary…
arxiv.org24 days agoView details
Can Large Language Models "Hyper-Thread"?
arXiv:2608.22376v1 Announce Type: new Abstract: Large language models generate tokens sequentially, but can they execute multiple tasks concurrently while forming each token? Broader attention allocation may provide a mechanism for such task concurrency. Existing approaches to scaling inference primarily rely on longe…
arxiv.org24 days agoView details
arXiv:2608.21369v1 Announce Type: new Abstract: Nigerian Pidgin is one of Africa's most widely spoken languages, yet remains severely underrepresented in language model evaluation. Existing benchmarks primarily focus on translation, transcription, or generic sentiment analysis, leaving critical aspects of culturally g…
arxiv.org24 days agoView details
Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models
arXiv:2608.21377v1 Announce Type: new Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied primarily in single-turn settings. This paper investigates a critical question: does subjecting LLMs to greater interaction…
arxiv.org24 days agoView details
A Social Media Analysis of Discourse on the Israel--Palestine Conflict on Telegram
arXiv:2608.21385v1 Announce Type: new Abstract: Social media has become a central arena in which armed conflicts are contested, yet the pro-Israel and pro-Palestine communities on Telegram, whose broadcast architecture yields an unusually direct record of deliberate political communication, have not been systematicall…
arxiv.org24 days agoView details
AI Learning and Conceptual Transfer in the Game of Hidden Rules
arXiv:2608.21372v1 Announce Type: new Abstract: This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback, representation design, rule difficulty analysis, transfer learning, generalization, and ps…
arxiv.org24 days agoView details
LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platform
arXiv:2608.21374v1 Announce Type: new Abstract: Literature reviews are essential to scientific progress, but rigorously evaluating automatically generated reviews remains difficult because many aspects of research utility depend on expert judgment rather than reference-overlap metrics. We introduce LitReview Arena, a…
arxiv.org24 days agoView details
arXiv:2608.21379v1 Announce Type: new Abstract: Student burnout is highly prevalent in higher education, with reported rates ranging from 12% to over 70% and consistently exceeding those of the working population - yet it is typically identified only retrospectively, after academic decline has already occurred. A cont…
arxiv.org24 days agoView details
arXiv:2608.21393v1 Announce Type: new Abstract: Running large language models inside enterprise environments has always bumped up against a practical wall: the data lives in one place, the AI horsepower sits somewhere else, and moving sensitive records between the two creates real headaches around latency, security, a…
arxiv.org24 days agoView details
arXiv:2608.21408v1 Announce Type: new Abstract: Due to the widespread accessibility of the internet and social media, toxic and hateful con-tent has grown exponentially, causing significant distress and negative societal impacts. Ro-man Urdu, a low-resource language used in Pakistan and among Urdu-speaking communities…
arxiv.org24 days agoView details
Evaluating Multimodal Narrative Understanding of Popular Hollywood Films
arXiv:2608.21430v1 Announce Type: new Abstract: Multimodal language models increasingly show promise for enabling the large-scale computational analysis of film, opening up new avenues for learning about film history and the evolution of narrative techniques. But the creation of stable benchmarks built around Hollywoo…
arxiv.org24 days agoView details
Robust Lightweight Deep Learning Models for Oral Cancer Screening
arXiv:2608.21583v1 Announce Type: new Abstract: Oral cancer is a leading cause of mortality in low-to-middle-income countries, where a shortage of specialists delays diagnosis. While point-of-care screening via smartphones offers a scalable solution, developing robust AI for resource-constrained settings poses signifi…
arxiv.org24 days agoView details
Data-Driven Dynamic Algorithm Dispatch with Large Language Models
arXiv:2608.21584v1 Announce Type: new Abstract: We introduce a large language model (LLM)-driven approach for generating dynamic algorithmic dispatch heuristics in high-performance linear algebra. By combining prompt engineering with LLaMA 3 and a curated performance database, the model learns to synthesize selection…
arxiv.org24 days agoView details
arXiv:2608.21928v1 Announce Type: new Abstract: In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual contexts or evaluating execution-time dynamics, but the complementary axis of fixing the scene…
arxiv.org24 days agoView details
Modeling Claim Dependency Structure for Patent Litigation Prediction with Graph Attention Networks
arXiv:2608.21924v1 Announce Type: new Abstract: Patent litigation imposes substantial costs on firms and distorts R&D incentives, making early risk identification a practically important task. While prior work has applied BERT-based models to patent claim text, two fundamental limitations remain: flat sequence encodin…
arxiv.org24 days agoView details
arXiv:2608.21559v1 Announce Type: new Abstract: Multi-stage LLM pipelines can remain structurally valid even when evidence available to downstream stages becomes incomplete, compressed, or conflicting. This paper introduces and operationalizes Evidence-State Reliability (ESR), an evaluation layer concerned with whethe…
arxiv.org24 days agoView details
SchemaRouter: Field-Aware Tool Routing for Efficient Heterogeneous Agentic RAG
arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph stores. Exposing all tool descriptions to an LLM agent, or selecting tools only by vector similarity, causes two costly…
arxiv.org24 days agoView details
CyrillicQA: The Influence of Phonetically Encoded Secret Language on LLM Performance
arXiv:2608.21462v1 Announce Type: new Abstract: Due to the selection of their training data, large language models (LLMs) perform best on standard-language inputs from languages using the Latin alphabet with large speaker populations, while disadvantaging other language varieties. Nevertheless, they can also be a vers…
arxiv.org24 days agoView details
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
arXiv:2608.21415v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resulting in biased behavior when processing portraits from different social groups. Existing debia…
arxiv.org24 days agoView details
arXiv:2608.21567v1 Announce Type: new Abstract: Human mobility serves as an essential proxy for understanding social, economic, and environmental dynamics in urban systems. Geospatial transferability, which measures a model's capability in a new location or unseen region, is a critical dimension for comparing differen…
arxiv.org24 days agoView details
Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals
arXiv:2608.21610v1 Announce Type: new Abstract: Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, discarding the hierarchical structure of the source. We introduce Semantic Compression Trees (SCT), a hierarchical index in…
arxiv.org24 days agoView details
arXiv:2608.21712v1 Announce Type: new Abstract: Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures still require substantial manual tuning, and the optimal configuration may vary across tasks and hospitals. Neural architecture search (NAS) au…
arxiv.org24 days agoView details
Measuring Activation Control in Large Language Models
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especially when evaluation-aware models exhibit scheming or deception. However, if models can also control their own activations,…
arxiv.org24 days agoView details
SAEM: Stage-Aware Expert Management for Memory-Efficient MoE Inference in Chain-of-Thought Reasoning
arXiv:2608.21614v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usage. Mixture-of-Experts (MoE) models scale capacity through sparse expert activation, yet th…
arxiv.org24 days agoView details
arXiv:2608.21767v1 Announce Type: new Abstract: Accurate modeling of sea ice concentration (SIC) evolution is essential for polar climate assessment and short?range sea ice prediction. Numerical and data-driven approaches constitute major foundations for SIC modeling, but the former often require complex parameterizat…
arxiv.org24 days agoView details
arXiv:2608.21792v1 Announce Type: new Abstract: Document classification in regulated industries is constrained by data residency, limited cold-start labels, scarce review capacity, and costly model-governance procedures. We present HIRA, a training-free, on-premises retrieval-augmented cascade for document classificat…
arxiv.org24 days agoView details
Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents
arXiv:2608.21830v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diverse digital environments, where reinforcement learning (RL) has become a dominant training paradigm. However, widely used…
arxiv.org24 days agoView details
Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution
arXiv:2608.21656v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vulnerable to prompt injection attacks, which may mislead the retriever or generator to expose…
arxiv.org24 days agoView details
GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?
arXiv:2608.21833v1 Announce Type: new Abstract: Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especially demanding because program logic, visual and audio content, interfaces, interaction and playability must function toge…
arxiv.org24 days agoView details
LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization
arXiv:2608.21836v1 Announce Type: new Abstract: Large language models have become increasingly capable agents for low-level code and kernel optimization, but isolated kernel benchmarks provide only a proxy for the deployment behavior that matters in language-model inference. We identify a benchmark-to-deployment gap:…
arxiv.org24 days agoView details
arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI Watchdog, a browser-based agent interface that monitors live conversations, detects five dark-pattern categories, inclu…
arxiv.org24 days agoView details
MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance
arXiv:2608.21867v1 Announce Type: new Abstract: LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering, and web tasks. Such memory is useful only when stored experience remains reliable across hundreds of interactions, but…
arxiv.org24 days agoView details
From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning
arXiv:2608.21897v1 Announce Type: new Abstract: Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDDL annotations and may exploit solver success in semantically unfaithful ways. We study how to learn fai…
arxiv.org24 days agoView details
arXiv:2608.21914v1 Announce Type: new Abstract: We align three upper ontologies that sit under UK and NATO defence data infrastructure: the Information Exchange Standard (IES), the Higher Quality Data Model (HQDM) that underpins the National Digital Twin, and Basic Formal Ontology (BFO). No public alignment between IE…
arxiv.org24 days agoView details
ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation
arXiv:2608.21925v1 Announce Type: new Abstract: Emotional Support Conversation (ESC) systems aim to provide holistic support by balancing professional therapeutic competence with natural empathy. However, existing methods struggle to simultaneously achieve structured, stage-aware reasoning and seamless empathy-experti…
arxiv.org24 days agoView details
Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patients
arXiv:2608.21941v1 Announce Type: new Abstract: Accurate assessment of patients in intensive care units (ICUs) is essential for timely clinical intervention and improved patient outcomes. Multimodal electronic health records (EHRs), including structured physiological time series and longitudinal clinical notes, provid…
arxiv.org24 days agoView details
Repo2Skill-Evo: Repository Skills Go Stale in Silence
arXiv:2608.21964v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over evolving software repositories, where success depends on repository-specific procedural knowledge: which APIs to call, which scripts to run, and which conventions the current release expects. Agent skills extern…
arxiv.org24 days agoView details
Closed-loop AI achieves certifiable engineering design
arXiv:2608.21976v1 Announce Type: new Abstract: Agentic AI has automated parts of scientific discovery, including paper generation, expert-level coding, therapeutic proposal, and autonomous experimentation. Complex physical engineering design remains a gap, because candidates must satisfy simultaneous constraints in f…
arxiv.org24 days agoView details
arXiv:2608.21979v1 Announce Type: new Abstract: Charitable food agencies play an important role in alleviating food insecurity by distributing donated food to people in need. However, they rely on ad hoc in-kind donations and often face shortages of specific foods, so they offer substitutes. A good food substitution r…
arxiv.org24 days agoView details
arXiv:2608.21750v1 Announce Type: new Abstract: Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passage-specific LoRA adapters, reducing reliance on long in-context prompts. When multiple passages are retrieved for the same query, however, evidence-…
arxiv.org24 days agoView details
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
arXiv:2608.21946v1 Announce Type: new Abstract: Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in interaction trajectories are largely discarded after a single policy update. Existing experi…
arxiv.org24 days agoView details
arXiv:2608.21423v1 Announce Type: new Abstract: Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to deployed products, practitioners repeatedly encounter the same operational failures. We systematize these failures throug…
arxiv.org24 days agoView details
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
arXiv:2608.21544v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations rather than model parameters alone. This creates an evaluation mismatch for LLM unlearning: previous unlearning methods may…
arxiv.org24 days agoView details
Can LLMs Truly Forget? Revealing Unlearning Gaps Through Adversarial Evaluation
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whether such information has truly become inaccessible remains challenging. Existing benchmarks primarily assess unlearning…
arxiv.org24 days agoView details
Evaluation Awareness in Language Models: Representation, Verbalization, and Control
arXiv:2608.21766v1 Announce Type: new Abstract: Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their behavior in deployment. This assumption can fail, should models infer that they are being evaluated and condition their respon…
arxiv.org24 days agoView details
Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web
arXiv:2608.21794v1 Announce Type: new Abstract: GUI grounding evaluations that expose UI elements as text metadata often treat high instruction-element embedding similarity as evidence of semantic grounding. Across three mobile and web benchmarks, we show that this interpretation is frequently confounded by visible-la…
arxiv.org24 days agoView details
Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention
arXiv:2608.21721v1 Announce Type: new Abstract: Correcting health misinformation in dialogue requires more than producing a factual rebuttal: users differ in what they know, what they believe, and what they need to hear, so an effective intervention often depends on first asking the right clarifying question. Yet exis…
arxiv.org24 days agoView details
Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Stores
arXiv:2608.21829v1 Announce Type: new Abstract: Retrieval-augmented generation treats the document store as a frozen input, and the systems that instead let an agent curate one never measure what curation does to the store. We invert the framing: the knowledge base is the model. A training agent answers a supervised q…
arxiv.org24 days agoView details
GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding
arXiv:2608.21832v1 Announce Type: new Abstract: Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether models bind relational language to the correct element. We introduce GUI-Primitives, a 994-item benchmark of contrastive i…
arxiv.org24 days agoView details
PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding
arXiv:2608.21853v1 Announce Type: new Abstract: Large language models are increasingly moving beyond text processing, adding support for other modalities such as images and audio. While text understanding and generation have been extensively studied, multimodal data processing capabilities, particularly in the context…
arxiv.org24 days agoView details
arXiv:2608.21863v1 Announce Type: new Abstract: Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has become the dominant paradigm for enabling this capability. However, existing approaches typic…
arxiv.org24 days agoView details
ECHO: A Cognitively Inspired, Auditable Memory Plane for Long-Horizon Agents
arXiv:2608.21755v1 Announce Type: new Abstract: Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Context and History Orchestration), an auditable memory architecture and service prototype inspired by episodic encoding,…
arxiv.org24 days agoView details
arXiv:2608.21880v1 Announce Type: new Abstract: Bangla large language model (LLM) safety is difficult to evaluate with English-centric or standard-script benchmarks because Bangla users routinely write across scripts, spellings, code-mixed forms, and regional registers. This paper presents BanglaVeilGuard, a compact B…
arxiv.org24 days agoView details
Machine learning and digital pragmatics: Which word category influences emoji use most?
arXiv:2608.21975v1 Announce Type: new Abstract: This study examines the performance of the state-of-the-art MARBERT model in identifying the lexical/pragmatic category associated with emoji use on X within a digital pragmatics approach (DPA). A net corpus of 15856 Colloquial Arabic (CA) posts containing emojis was col…
arxiv.org24 days agoView details
Spine-Branch Coordination for Multi-agent Computer Use
arXiv:2608.22077v1 Announce Type: new Abstract: Computer use agents (CUAs) are increasingly deployed as multi-agent systems that decompose a task into multiple subtasks executed across parallel virtual machines (VMs). However, a critical physical bottleneck is that the state of two VMs cannot be merged. Previous syste…
arxiv.org24 days agoView details
Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators
arXiv:2608.22090v1 Announce Type: new Abstract: Large language models can produce fluent reasoning traces whose local semantic errors propagate to an incorrect conclusion, while unconstrained self-correction may preserve, amplify, or introduce errors. Existing diffusion language models provide iterative refinement, bu…
arxiv.org24 days agoView details
RAG Collapse: LLM Responses Collapse When Retrieved Documents Are Self-Authored
arXiv:2608.22118v1 Announce Type: new Abstract: LLM responses are based on the internet (via training or RAG), and AI is now used to generate a significant amount of content online (Paredes et al., 2026), creating the potential for a self-reinforcing feedback loop. Prior work has shown that when LLMs are recursively t…
arxiv.org24 days agoView details
LLM assisted writing deserves empirical evaluation
arXiv:2608.22124v1 Announce Type: new Abstract: LLM-assisted writing is often treated as a detection problem, as it raises questions about clarity, integrity, equity, and evaluation. An analysis of 69,209 Health Informatics papers links it to more focused presentation, broader citation practices, and more globally dis…
arxiv.org24 days agoView details
How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network
arXiv:2608.22192v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused. We study human-directed stereotypes on Moltbook, an open agent-native social platform, asking how agents construct huma…
arxiv.org24 days agoView details
Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation
arXiv:2608.22215v1 Announce Type: new Abstract: Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat external memory as a monotonically growing repository, inevitably leading to retrieval degradation and increasing computational…
arxiv.org24 days agoView details
Grounded Normative Rule Generation with Structured Search
arXiv:2608.22229v1 Announce Type: new Abstract: Normative rules like institutional charters and workplace policies must be both human-readable and operationally verifiable against actual environment records. However, current language generation and structured-output benchmarks primarily reward surface fluency or schem…
arxiv.org24 days agoView details
Models
View all models →peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF
image-text-to-text · gguf · llama.cpp · qwen35moe
huggingface.co24 days ago229 ptsView details
thomsonreuters/Thomson-1.0-Small
image-text-to-text · transformers · safetensors · qwen3_5_moe
huggingface.co24 days ago181 ptsView details
alibaba-pai/MiniMax-H3-Fun-Controlnet-Union
text-to-video · videox_fun · controlnet · video-to-video
huggingface.co25 days ago165 ptsView details
logic65/Qwen3.8-Whittle-MoE-27B-A17.8B
safetensors · qwen3_5_moe · moe
huggingface.co25 days ago103 ptsView details
joeygambino/MiniMax-H3-x-Z-Image-native
text-to-video · minimax-h3 · comfyui · comfy-native
huggingface.co25 days ago83 ptsView details
rdtand/Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm
vllm · safetensors · qwen3_5
huggingface.co25 days ago42 ptsView details
poltextlab/xlm-roberta-large-english-cap-v5
text-classification · transformers · safetensors · xlm-roberta
huggingface.co25 days ago3 ptsView details
jpsequeira/GLM-5.2-EXL3-TR3-3.40bpw-KVarN-K4V2
text-generation · vllm · safetensors · glm_moe_dsa
huggingface.co25 days ago2 ptsView details
poltextlab/xlm-roberta-large-pooled-sentiment-v3
text-classification · transformers · safetensors · xlm-roberta
huggingface.co25 days ago1 ptsView details
saishshinde15/Clyrai_Lucius-1.3B
text-generation · transformers · safetensors · llama
huggingface.co25 days agoView details
Open source
View all open source →langchain-ai/langchain langchain==1.3.17
Changes since langchain==1.3.16 release(langchain): 1.3.17 (#39893) fix(langchain): frame custom HITL rejection reasons (#39773) chore(deps): bump minor and patch dependencies (#39869)
github.com24 days agoView details
<details open> metal : per-device tuned (Q, NE) for flash-attn vec (#26570) * metal : per-device tuned (Q, NE) for flash-attn vec (#25750) * rebase Q-generic FA vec body from 01dc93607 (#23114) * add 53 f16 (Q,NE) flash-attn vec instantiations (vec 80 -> 133) * add FA vec (Q,NE)…
github.com24 days agoView details