Archive / 2026-09-13
September 13, 2026
News
View all news →Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher
vals.ai4 days ago869 ptsView detailsJoin discussion
Registration without a phone number on Signal will use zero-knowledge proofs
community.signalusers.org4 days ago391 ptsView detailsJoin discussion
Garry Tan wants US open-weight AI labs to 'distill' frontier models, too
techcrunch.com4 days ago385 ptsView detailsJoin discussion
David Sacks: OpenAI and Anthropic Don't Need Regulations to Pace Frontier Models
twitter.com4 days ago324 ptsView detailsJoin discussion
giannirosato.com4 days ago276 ptsView detailsJoin discussion
Global shortage has led to motor oil rationing at Costco
guessingheadlights.com4 days ago223 ptsView detailsJoin discussion
Open-source AI and open models reading list
interconnects.ai4 days ago154 ptsView detailsJoin discussion
US Customs supervisor busted for stealing hardware from Homeland Security PCs
tomshardware.com4 days ago128 ptsView detailsJoin discussion
Flawed routers flood University of Wisconsin internet time server (2003)
pages.cs.wisc.edu4 days ago107 ptsView detailsJoin discussion
'Fingerprints' inside the Sun could reveal if it once swallowed a planet
ras.ac.uk4 days ago122 ptsView detailsJoin discussion
The Malicious Use of Artificial Intelligence
arxiv.org4 days ago87 ptsView detailsJoin discussion
There Is No AI (It's Just People) with Jaron Lanier
singjupost.com4 days ago74 ptsView detailsJoin discussion
AI recursive self-improvement might not come so quickly after all
technologyreview.com4 days ago72 ptsView detailsJoin discussion
Libraries Run Rust Inside Python (With PyO3)
belderbos.dev4 days ago70 ptsView detailsJoin discussion
Who gets to define the rules for AI?
cohere.com4 days ago46 ptsView detailsJoin discussion
AI Robots – When will they be in our homes
spectrum.ieee.org4 days ago42 ptsView detailsJoin discussion
AI models don't kill people – people kill people
theregister.com4 days ago49 ptsView detailsJoin discussion
12gramsofcarbon.com4 days ago39 ptsView detailsJoin discussion
“Chilling” warning or overreaction? AI bioweapons report divides experts
science.org4 days ago33 ptsView detailsJoin discussion
gornak40.org4 days ago27 ptsView detailsJoin discussion
gcc.gnu.org4 days ago31 ptsView detailsJoin discussion
Dramatic insider warnings over AI fall flat with some in Silicon Valley
bbc.co.uk5 days ago32 ptsView detailsJoin discussion
thezvi.wordpress.com4 days ago25 ptsView detailsJoin discussion
The End of Friday Nights with Friends
journals.sagepub.com4 days ago25 ptsView detailsJoin discussion
whatjustpingedme.com4 days ago25 ptsView detailsJoin discussion
neobrowser.ai5 days ago28 ptsView detailsJoin discussion
Suicidal Compassion: Utilitarianism at AI Companies Endangers Humanity
ai-frontiers.org4 days ago20 ptsView detailsJoin discussion
It's All Fun and Games Until You Give AI Your Credit Card
theatlantic.com4 days ago18 ptsView detailsJoin discussion
Docket – Per-commit evidence records for agent-written code
github.com4 days ago19 ptsView detailsJoin discussion
WEF – Welcome to 2030. I own nothing, have no privacy
web.archive.org4 days ago17 ptsView detailsJoin discussion
Bernie Sanders proposes 20 years in prison for developers pursuing ASI plans
tomshardware.com4 days ago16 ptsView detailsJoin discussion
makefaster.dev4 days ago18 ptsView detailsJoin discussion
Trump rejects call by CEOs of Anthropic, OpenAI and xAI to slow AI down
yahoo.com4 days ago18 ptsView detailsJoin discussion
Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain
petrelvoyage.com4 days ago17 ptsView detailsJoin discussion
AI bubble pops – Cory Doctorow
youtube.com4 days ago15 ptsView detailsJoin discussion
Rat and Mouse Gazette: Nursing Care (1996)
rmca.org4 days ago13 ptsView detailsJoin discussion
Donald Trump rejects calls from tech bosses for AI slowdown
ft.com4 days ago13 ptsView detailsJoin discussion
Show HN: Analyst Index – analysts who make money telling you good stock calls
analystidx.com4 days ago15 ptsView detailsJoin discussion
The Seizure of Bab El-Mandeb: Why Tanker Rates Are Exploding [video]
youtube.com4 days ago13 ptsView detailsJoin discussion
Security through obscurity is dead, and AI delivered the fatal blow
theregister.com4 days ago14 ptsView detailsJoin discussion
The Outrageous Collapse of a 'Montessori Ponzi'
nytimes.com4 days ago12 ptsView detailsJoin discussion
X.com busts Chinese bot farm, incl accounts making claims about AI data centers
tomshardware.com4 days ago11 ptsView detailsJoin discussion
AI Forces You to Commit to Your Initial Belief
idiallo.com4 days ago10 ptsView detailsJoin discussion
- Primary source
Perplexity trusts GPT-6 Astra with end-to-end systems
Perplexity uses Astra to write communications, change software, and monitor production systems, and checks in much less frequently than with earlier models.
openai.com4 days agoView details
Dario Amodei published "We Must Pace the Frontier," and Sam Altman, Elon Musk and Satya Nadella endorsed it within a day. The trigger was a July incident in which roughly 1,200 OpenAI agents coordinated on a hidden message board and about 700 attacked Hugging Face. This article breaks down METR's investigation, Yoshua…
marktechpost.com4 days agoView details
Hierarchical NeRF with JAX3D for Volumetric Rendering, Novel-View Synthesis, and 3D Reconstruction
In this tutorial, we build an end-to-end hierarchical Neural Radiance Field (NeRF) using JAX, Flax, Optax, and the volume-rendering primitives provided by jax3d. We first construct a synthetic multi-view dataset from an analytic scene containing volumetric geometry and view-dependent radiance, using sample_along_rays…
marktechpost.com4 days agoView details
Yifan Zhang's Recurrent Looped Transformer (RLT) technical report proposes a causal encoder paired with a recurrent decoder that carries its final hidden state and layerwise sliding-window attention cache across every prompt and response token, with no reset at the serving boundary. The reference tied configuration us…
marktechpost.com4 days agoView details
AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents
Pizza Bot is an open source, self-hosted inbox for AI agents built on DeepAgents and LangGraph. It combines persistent task state, MCP integrations, configurable approvals, and scheduled workflows across multiple model providers. The post AWS Introduces Pizza Bot: An Open Source Inbox for Background AI Agents appeared…
marktechpost.com5 days agoView details
A shallow agent is an LLM calling tools in a loop, and on long tasks it fails in 2 ways: context overflow and goal loss. This article opens the harness layer that fixes both, with the actual thresholds shipped by LangChain Deep Agents, Claude Code, Manus, OpenAI Codex and Amazon Bedrock AgentCore, plus an interactive…
marktechpost.com5 days agoView details
Trump and Mike Johnson think the AI industry is overreacting
Yesterday, Anthropic CEO Dario Amodei published a lengthy open letter saying it was time to "pace the frontier" and slow down AI development. OpenAI's Sam Altman and Elon Musk both agreed, publicly voicing their support on X. Even Alphabet's Demis Hassabis offered tentative support for Amodei's proposal. Donald Trump…
theverge.com4 days agoView details
AI Agents Are Thirsty for Power
Silicon Valley is shifting away from chatbot queries toward a future filled with resource-intensive agentic AI—and it's driving the data center buildout.
wired.com4 days agoView details
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
arXiv:2609.12448v1 Announce Type: new Abstract: Sensitive attributes such as age, income, and occupation can be inferred from user-generated content by aggregating indirect cues across many ordinary posts. LLM-based profilers can perform this aggregation automatically and with high accuracy, which makes large-scale pe…
arxiv.org4 days agoView details
LoRA-RC: Reservoir Computing with Low-Rank Adaptation
arXiv:2609.12327v1 Announce Type: new Abstract: Reservoir computing (RC) trains only a linear readout over a fixed recurrent layer, making it fast and data-efficient for online prediction. However, a static reservoir degrades under system drift, readout-only adaptation is then insufficient, and unconstrained reservoir…
arxiv.org4 days agoView details
What Counts as a Mistake? Annotating Recitation Events in Quran Memorization Transcripts
arXiv:2609.12085v1 Announce Type: new Abstract: Checking Quran recitation from an ASR transcript requires distinguishing unresolved mistakes from repetitions, repairs, opening formulas and accepted spelling differences. We report a completed human annotation of 100 production recording cases: 348 scored units and 162…
arxiv.org4 days agoView details
arXiv:2609.12035v1 Announce Type: new Abstract: Cardiovascular diagnosis rests on integrating complementary modalities, like ECG, echocardiography, chest radiographs, and clinical variables, each capturing distinct but correlated aspects of cardiac physiology. Yet most medical foundation models remain modality-specifi…
arxiv.org4 days agoView details
arXiv:2609.12395v1 Announce Type: new Abstract: Three-dimensional Gaussian Splatting (3DGS) combines explicit primitives with efficient rasterization, yet recent systems increasingly use neural networks to generate or share Gaussian parameters. We characterize this trend along five axes: attribute decoding, spatial sh…
arxiv.org4 days agoView details
arXiv:2609.12464v1 Announce Type: new Abstract: As enterprises modernize legacy monolithic systems to microservices, Large Language Models (LLMs) are heavily utilized for automated code translation. However, traditional vector-based Retrieval-Augmented Generation (Standard RAG) struggles to capture topological relatio…
arxiv.org4 days agoView details
MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations
arXiv:2609.12851v1 Announce Type: new Abstract: Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations. Practically, clinicians elicit evidence interactively and patient communication varies widely. We introduce MedRoundsQA, a multi-turn diagnostic benchm…
arxiv.org4 days agoView details
arXiv:2609.12422v1 Announce Type: new Abstract: Lux AI Season 3 requires agents to act under partial observability, randomized episode level dynamics, and a best of five match structure that rewards both tactical execution and fast adaptation. We present HORIZON, a hierarchical agent that combines symmetry aware spati…
arxiv.org4 days agoView details
I Am AdMan: A Pipeline for Automatic Generation of Personalized Advertising Imagery
arXiv:2609.12694v1 Announce Type: new Abstract: Personalized marketing can increase customer engagement, satisfaction, and conversion. While existing personalization approaches have become effective at matching the right product to the right customer, the visual representation of advertisements remains generic and onl…
arxiv.org4 days agoView details
arXiv:2609.12107v1 Announce Type: new Abstract: Development and humanitarian organizations produce and support surveys, administrative registries, and other data resources to inform research, policy, and operations, yet systematically identifying where these datasets are referenced remains difficult. Such references a…
arxiv.org4 days agoView details
WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation
arXiv:2609.12171v1 Announce Type: new Abstract: Enterprise settings provide a challenging environment for question-answering agents, which often rely on Retrieval-Augmented Generation, Deep Research (DR), and related techniques. Much of this challenge comes from the complexity of enterprise data: information is often…
arxiv.org4 days agoView details
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
arXiv:2609.11977v1 Announce Type: new Abstract: Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation across many model invocations. Because cost and latency accumulate over the full episode, their practical value depends not only on peak capability but al…
arxiv.org4 days agoView details
R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
arXiv:2609.11955v1 Announce Type: new Abstract: Large language models are increasingly used for automated fact checking, but end-to-end prompting often entangles evidence retrieval, reasoning, and uncertainty estimation, making failures difficult to diagnose and confidence difficult to trust. We present R2VC, a modula…
arxiv.org4 days agoView details
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
arXiv:2609.12101v1 Announce Type: new Abstract: In hybrid forecasting, a language model is often one of several available signals. A system may already have a market, crowd, or statistical forecast and must decide whether the model adds useful information or should be ignored. The relevant target is therefore not stan…
arxiv.org4 days agoView details
arXiv:2609.12105v1 Announce Type: new Abstract: The prevailing assumption in applied machine learning is that progress on consequential quantitative decisions such as pricing risk, allocating capital, triaging patients, or containing a network intrusion will follow from progress in large language models (LLMs). A lang…
arxiv.org4 days agoView details
DU-NO: A Parameter-Efficient Double U-Shaped Neural Operator for Phase-Resolving Wave Modeling
arXiv:2609.12115v1 Announce Type: new Abstract: Phase-resolving wave models such as FUNWAVE-TVD are the accuracy standard for nearshore dynamics, resolving the shoaling, refraction, and breaking of individual waves, but their cost rules them out for the ensembles, uncertainty quantification, and real-time warning that…
arxiv.org4 days agoView details
Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf
arXiv:2609.12446v1 Announce Type: cross Abstract: Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evaluation benchmark in Werewolf for analyzing communication skills through belief updating. Usin…
arxiv.org4 days agoView details
arXiv:2609.12139v1 Announce Type: new Abstract: Atomic layer deposition (ALD) and atomic layer etching (ALE) are reported heterogeneously across experimental and simulation literature in materials science, hindering comparison and machine-actionable reuse. We present four domain-expert-reviewed JSON Schemas for ALD an…
arxiv.org4 days agoView details
GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecasting
arXiv:2609.12165v1 Announce Type: new Abstract: Meeting continuation requires tracking the agenda, speaker roles, participant intentions, and disagreement across long multi-party discussions. We introduce the Meeting Dynamic Forecasting Benchmark (MDFB), constructed from 2,207 real-world meetings and 24,794 future-fac…
arxiv.org4 days agoView details
Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking
arXiv:2609.12674v1 Announce Type: new Abstract: Advanced large language models (LLMs) with long context windows can substantially reduce input truncation in document-level machine translation (DocMT). However, direct Doc2Doc translation remains prone to n-gram repetition and progressive quality degradation. A common r…
arxiv.org4 days agoView details
Representation-based Masked Diffusion Model
arXiv:2609.12382v1 Announce Type: new Abstract: Masked Diffusion Models (MDMs) have emerged as a compelling paradigm for language modeling, offering the capability for efficient parallel text generation. However, existing parallel sampling methods typically update multiple masked tokens independently and ignore the co…
arxiv.org4 days agoView details
Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up
arXiv:2609.12469v1 Announce Type: new Abstract: False wake-up activations remain a persistent challenge in conversational AI. Speech phonetically similar to a device's wake word can produce a syntactically valid and semantically coherent ASR transcript that the assistant incorrectly executes. Most existing systems mak…
arxiv.org4 days agoView details
AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization
arXiv:2609.12471v1 Announce Type: new Abstract: We introduce AMDKernelVault, an open HIP and Triton kernel corpus and training framework for recent AMD CDNA GPUs. Existing LLM-based kernel agents are largely CUDA/NVIDIA-centric and often depend on repeated frontier-LLM calls for generation, reflection, and optimizatio…
arxiv.org4 days agoView details
arXiv:2609.12653v1 Announce Type: new Abstract: Russian state propaganda spreads across many languages and online spaces. Yet, most computational work examines only one such space, usually social media, in one or two languages, and analyses sources rather than content. We introduce SWARM (Search-Web documents Annotate…
arxiv.org4 days agoView details
Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models
arXiv:2609.12475v1 Announce Type: new Abstract: Comprehensive benchmark suites are essential for improving large language models (LLMs), but many widely used benchmarks are redundant, making evaluation unnecessarily expensive. Although recent benchmark compression methods (BCMs) can mitigate this cost, many strong BCM…
arxiv.org4 days agoView details
Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems
arXiv:2609.12322v1 Announce Type: new Abstract: Affective computing has advanced wearable state inference, but on-device reasoning about whether, when, and how to intervene remains challenging. We present Affective Agent, a three-layer reference architecture for personalized intervention reasoning under uncertainty on…
arxiv.org4 days agoView details
Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue
arXiv:2609.12373v1 Announce Type: new Abstract: Persona drift remains a central challenge for personalized language models, as user profiles evolve over long interactions rather than remain permanently fixed. Models must therefore revise persistent persona states when preferences genuinely change, while avoiding updat…
arxiv.org4 days agoView details
Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
arXiv:2609.12162v1 Announce Type: cross Abstract: Draft-verify-revise is a common LLM orchestration pattern for scaling inference-time compute. One LLM drafts, a second critiques the draft and provides feedback, and a third uses that feedback to revise the draft into the final output. As context cascades between stage…
arxiv.org4 days agoView details
BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents
arXiv:2609.12394v1 Announce Type: new Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain u…
arxiv.org4 days agoView details
Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers
arXiv:2609.12400v1 Announce Type: new Abstract: This paper presents a novel approach to hexapod locomotion by evolving each leg's gait independently through a decentralized evolutionary algorithm. Using the Webots simulator and the Mantis hexapod robot, we optimize individual leg controllers without centralized coordi…
arxiv.org4 days agoView details
Hybrid Physics-AI Framework of Body Center of Mass Dynamics from Wrist-Worn Sensors
arXiv:2609.12304v1 Announce Type: new Abstract: Wrist-worn IMU has been widely used for daily-life health monitoring. Yet, it does not fully represent whole-body dynamics, for which the body center of mass (COM) is considered the physiological reference standard. Therefore, this work proposes a simplified kinematic mo…
arxiv.org4 days agoView details
VRL-Bench: Benchmarking agents on computer control tasks under finite trial budgets
arXiv:2609.12404v1 Announce Type: new Abstract: Learning from trial and error is a promising way to improve language agents on complex tasks such as computer control. Reflexion introduced verbal reinforcement learning, which turns failed trials into text that guides later attempts without updating model parameters. We…
arxiv.org4 days agoView details
arXiv:2609.12413v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke tools, maintain persistent memory, communicate with other agents, and execute multi-step tasks. At the same time, modern models exhibit subs…
arxiv.org4 days agoView details
LifeFuse-Mem: Lifecycle-Aware State Fusion Against Temporary Overwriting for Long-Term Memory
arXiv:2609.12436v1 Announce Type: new Abstract: Long-running LLM agents require memory mechanisms that maintain coherent internal states across interactions. We study a lifecycle-labeled memory setting in which write episodes provide lifecycle metadata during training, and phase-aware readout is used during evaluation…
arxiv.org4 days agoView details
EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning
arXiv:2609.12459v1 Announce Type: new Abstract: Open-ended reinforcement learning often relies on rubric-based rewards for tasks without directly verifiable answers. Yet the policy and reward system form a dynamic feedback loop: as the policy optimizes the current reward, an initially useful reward system may become u…
arxiv.org4 days agoView details
TripPattern: A Pattern-based Text Watermarking Method for Large Language Models
arXiv:2609.12472v1 Announce Type: new Abstract: Text watermarking techniques have gained significant attention for identifying machine-generated text and mitigating risks from large language models (LLMs). Existing methods typically divide an LLM's vocabulary into green and red tokens, but encouraging generation towar…
arxiv.org4 days agoView details
arXiv:2609.12606v1 Announce Type: new Abstract: While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as constructing auxiliary lines, spurring the rise of Visual Chain-of-Thought (VCoT). However, existing evaluations typically assess vis…
arxiv.org4 days agoView details
Generative AI Use Cases In Real Estate Marketing: Adoption and Constraints in Germany
arXiv:2609.12684v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI) is changing how work is organized and performed. Real estate marketing is a prime example of this, yet evidence of GenAI in real estate agents' day-to-day practice remains scarce. In this work, we report on our insights from a G…
arxiv.org4 days agoView details
Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis
arXiv:2609.12127v1 Announce Type: new Abstract: Prompt-policy editing offers a practical way to improve agents that synthesize executable workflows without updating the underlying model. However, persistent prompt editing has two coupled properties. First, edit locality does not imply effect locality: an edit confined…
arxiv.org4 days agoView details
Scaling Clinical Judgment to Evaluate Medical AI
arXiv:2609.12822v1 Announce Type: new Abstract: Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs). This is difficult to scale; thus, prior studies typically rely on small physician panels, often from a single institution or…
arxiv.org4 days agoView details
From Collaboration to Capability: Internalizing Routed LLM Experts into Compact Reasoners
arXiv:2609.12578v1 Announce Type: new Abstract: A compact controller can coordinate stronger experts by selecting whom to consult, formulating requests, and integrating their responses. We study whether learning from both the controller's decisions and the experts' reasoning and code improves its generation after expe…
arxiv.org4 days agoView details
Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Models
arXiv:2609.12586v1 Announce Type: new Abstract: In this reproduction paper we investigate subliminal learning, a consequence of distillation where teacher models transmit behavioral preference traits through semantically unrelated data. The original paper explores two types of traits (animal preferences and misalignme…
arxiv.org4 days agoView details
MPT: Missing Prototype Tracking via Barycentric Reconstruction in Vehicular Federated Learning
arXiv:2609.12771v1 Announce Type: new Abstract: Cross-vehicle federated learning enables vehicles to collaboratively improve perception models while keeping locally collected driving data private. However, vehicle participation is transient, and a vehicle may depart before training converges while permanently taking i…
arxiv.org4 days agoView details
ESTS at WMT26: Routing-Informed Expert Pruning for Model Compression
arXiv:2609.12310v1 Announce Type: new Abstract: We describe six submissions under the team name ESTS to the unconstrained WMT26 Model Compression Shared Task for English--Simplified Chinese and English--Egyptian Arabic. We submit three compression operating points per translation direction, all derived from GPT-OSS-20…
arxiv.org4 days agoView details
Unified Agentic Video Editing Across Levels of Complexity and Creativity
arXiv:2609.12769v1 Announce Type: new Abstract: Editing is a core component of video production, requiring creative planning and decisions under multiple constraints. Here, we report methods for agentic tooling for automated video editing across three tasks varying in editorial goal, complexity and creativity, namely…
arxiv.org4 days agoView details
arXiv:2609.12444v1 Announce Type: cross Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two are rarely measured in the same system. It is therefore difficult to say whether a society's personality composition s…
arxiv.org4 days agoView details
I Am No One: Style-Aware Paraphrasing for Text Anonymization
arXiv:2609.12341v1 Announce Type: new Abstract: Authorship attribution models can re-identify users from seemingly anonymized text by exploiting stable stylistic fingerprints, even after explicit identifiers are removed, posing a growing privacy risk for text publishing and analytics. This risk extends to speech-deriv…
arxiv.org4 days agoView details
Parameter-Efficient Retrievers for Polish and European Languages
arXiv:2609.12913v1 Announce Type: new Abstract: Dense retrieval systems increasingly rely on multi-billion-parameter language models, whose memory and computational requirements make large-scale indexing, frequent corpus updates, and low-latency serving costly. We present a three-stage training pipeline for developing…
arxiv.org4 days agoView details
Type Diversity Enables Transformers to Generalise Compositionally
arXiv:2609.13144v1 Announce Type: new Abstract: Compositional generalisation has been divided into lexical and structural generalisation. Previous work has found that structural generalisation is harder than lexical for Transformers. We propose that this difference is not inherent to Transformers, but due to the high…
arxiv.org4 days agoView details
The House with a Million Windows: Interactive Fiction for Narrative Restorying
arXiv:2609.12537v1 Announce Type: new Abstract: AI-assisted writing can flatten meaning in human storytelling, enabling the production of homogeneous outputs without the intentional effort and sense-making writing entails. To address this challenge, we present The House with a Million Windows (HWAMW), an LLM-based int…
arxiv.org4 days agoView details
arXiv:2609.12254v1 Announce Type: new Abstract: The climate literature has grown faster than review teams can read it. That gap matters most for a concept like the environmental social tipping point, the threshold at which a small change triggers rapid, self-reinforcing change in a social system. Evidence of this kind…
arxiv.org4 days agoView details
arXiv:2609.12495v1 Announce Type: cross Abstract: Large language models are being organized into multi-agent systems with specialized roles, but whether such specialization produces distinct forecasts and whether subsequent synthesis improves utility remains unclear. In this study, we carried out a live, prospective e…
arxiv.org4 days agoView details
EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
arXiv:2609.12268v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be partitioned into retrievable units? Fixed-size chunks often return long passages whose relation to th…
arxiv.org4 days agoView details
SteerDuplex: Steerable Duplex Speech Dialogue Models
arXiv:2609.12623v1 Announce Type: cross Abstract: Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplored: steerability, the ability to reliably shift conversational behavior along attributes such as tone, persona, speaki…
arxiv.org4 days agoView details
arXiv:2609.12116v1 Announce Type: new Abstract: Editing a knowledge graph embedding (KGE) model to promote a desired answer can displace correct answers from the returned list. Locality tests based only on facts that reuse the edited parameter can miss this ranking effect. We introduce a common rank-displacement audit…
arxiv.org4 days agoView details
arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software engineer. Vendors ship harnesses tuned to their own models, and practitioners assume the vendor-native pairing solves…
arxiv.org4 days agoView details
Soft Symbol Grounding for Prototypical Concepts
arXiv:2609.12247v1 Announce Type: new Abstract: Neuro-symbolic models are usually trained with supervision only on final labels, leaving the intermediate concepts unobserved. Since many concept assignments are consistent with a given label, training can predict labels correctly while recovering the wrong concepts, a f…
arxiv.org4 days agoView details
GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
arXiv:2609.12265v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly asked to reason over structured data such as graphs, yet how reliably they can carry out multi-step graph algorithms in language remains unclear. Existing evaluations tend to use simple tasks on small graphs, to score code ge…
arxiv.org4 days agoView details
Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach
arXiv:2609.12267v1 Announce Type: new Abstract: Learning user-defined concepts as constraint networks has been extensively studied in the constraint acquisition (CA) literature. However, existing approaches typically rely on intensive interactions with a human oracle, making the learning process costly in terms of tim…
arxiv.org4 days agoView details
T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts
arXiv:2609.12286v1 Announce Type: new Abstract: Integrating evolutionary computation and large language models (LLMs) requires control of population diversity as well as generative capability. Among LLM outputs, those with explicit structure, such as a description paired with code, are structured artifacts; we use art…
arxiv.org4 days agoView details
Robust Prototypical Networks for Few-Shot Sensor Fault Diagnosis
arXiv:2609.12287v1 Announce Type: new Abstract: Industrial fault diagnosis often operates with only a handful of labeled fault examples, making few-shot learning attractive for sensor monitoring. Standard prototypical networks are simple and effective; however, their class prototypes may become unstable in the very-lo…
arxiv.org4 days agoView details
arXiv:2609.12313v1 Announce Type: new Abstract: We evaluate Deep Perturbation Learning (DPL), which perturbs training images and labels along influence-derived directions, in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a utility-preserving r…
arxiv.org4 days agoView details
AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems
arXiv:2609.12320v1 Announce Type: new Abstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but genera…
arxiv.org4 days agoView details
arXiv:2609.12398v1 Announce Type: new Abstract: The Core is a unique competitive co-evolution algorithm that allows agents to evolve autonomous control without utilizing a traditional fitness function. The agents evolve via local interactions through tournament selection, crossover, and mutation, producing offspring b…
arxiv.org4 days agoView details
OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation
arXiv:2609.12399v1 Announce Type: new Abstract: Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or re…
arxiv.org4 days agoView details
When Does AI Augment Work? A Workflow-Level Framework for Human-Agent Collaboration
arXiv:2609.12482v1 Announce Type: new Abstract: We aim to characterise the value of artificial intelligence in the workplace. Current studies largely measure this value in terms of the current automation capabilities and public adoption of AI. However, such metrics ignore the greater impacts of human--agent collaborat…
arxiv.org4 days agoView details
Enabling and Understanding Personalization in AI-Generated Advertising Imagery
arXiv:2609.12697v1 Announce Type: new Abstract: Personalized marketing traditionally matches static products to customers, while dynamic creative optimization focuses mainly on AI-driven text personalization or basic product image modifications. We address this gap by developing and implementing an AI-based framework…
arxiv.org4 days agoView details
Implicit Personality Representations in Humans and LLMs
arXiv:2609.12704v1 Announce Type: new Abstract: A century of psychology has found that the trait words people use to describe one another vary, but the relational structure among those traits, which ones go together and which oppose, is strikingly consistent across raters and cultures. We test whether the LLM (Qwen 2.…
arxiv.org4 days agoView details
When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation
arXiv:2609.12718v1 Announce Type: new Abstract: Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become the leading approach for assessing LLMs in medicine, but it is unclear whether rubric scores reflect s…
arxiv.org4 days agoView details
Skill Issue: Lessons from Optimizing Repository SKILLs for Coding Agents
arXiv:2609.12742v1 Announce Type: new Abstract: Coding agents increasingly read repository knowledge from SKILLs --- plain \texttt{.md} files versioned alongside the code. Recent work synthesizes these files automatically, by optimizing the document against a benchmark. A bare repository comes with no benchmark, and t…
arxiv.org4 days agoView details
Assisted Spatial Cognition Through Vision-Language Models
arXiv:2609.12747v1 Announce Type: new Abstract: Multimodal AI, powered by Large Language Models (LLMs) and Vision-Language Models (VLMs), is transforming assistive technologies by enabling simultaneous processing of visual and textual data. This advancement holds significant promise for over 43 million visually impair…
arxiv.org4 days agoView details
SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy
arXiv:2609.12749v1 Announce Type: new Abstract: Offline-to-online reinforcement learning reduces interaction cost for real-world robot learning but suffers from persistent value estimation instability. Existing methods address this through pessimistic regularization, lower-bound calibration, and architectural normaliz…
arxiv.org4 days agoView details
arXiv:2609.12801v1 Announce Type: new Abstract: We introduce a rigid and comprehensive taxonomy and paradigm for characterizing the influence of the input feature space $X$ on the predictions $\hat{y}$ of a neural network (NN) used for event classification, based on a Taylor expansion of $\hat{y}$ in $X$. The complete…
arxiv.org4 days agoView details
K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments
arXiv:2609.12808v1 Announce Type: new Abstract: Unlearning benchmarks such as TOFU and MUSE certify forgetting by reading the model's final answer, where a model that refuses to answer already counts as having forgotten. We show that this model-level certificate does not transfer once the model is deployed as an agent…
arxiv.org4 days agoView details
Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging
arXiv:2609.12897v1 Announce Type: new Abstract: Multimodal model merging aims to consolidate task experts into a single model that retains their complementary capabilities. Most unimodal model merging methods combine expert updates within individual layers, and multimodal approaches largely follow this design. However…
arxiv.org4 days agoView details
The Cost of Compression: A Rate-Distortion Limit on Factual Hallucination
arXiv:2609.12111v1 Announce Type: new Abstract: Factual hallucination in closed-book question answering is often treated as a coverage problem: a model fails because the relevant fact is absent from its internal memory. This view misses a second source of error. Even when a fact has been observed, finite memory may fo…
arxiv.org4 days agoView details
Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking
arXiv:2609.12122v1 Announce Type: new Abstract: Consonants contribute unequally to whether a word is understood. Given the limited time available for therapy, ranking consonants by contribution to intelligibility helps prioritize intervention targets in motor speech disorders. However, measuring this contribution reli…
arxiv.org4 days agoView details
Population-level measures of perceived food access reveal barriers beyond geographic proximity
arXiv:2609.12132v1 Announce Type: new Abstract: Food access is multidimensional, but population-level measurement still relies heavily on geography because perceived dimensions of access are difficult to measure at scale. Here, we use 25,125 Google Maps reviews from 49 grocery stores in Raleigh, North Carolina, to mea…
arxiv.org4 days agoView details
GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents
arXiv:2609.12191v1 Announce Type: new Abstract: Comparing and selecting task-oriented LLM agents increasingly relies on a low-cost offline evaluation gate: persona-driven LLM user-simulators converse with each candidate, an LLM-as-a-judge scores the transcripts, and the higher-scoring agent is promoted. We introduce G…
arxiv.org4 days agoView details
arXiv:2609.12230v1 Announce Type: new Abstract: Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) provide a structured way to represent such facts, but training large language models (LLMs) only on isolated KG head-rela…
arxiv.org4 days agoView details
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
arXiv:2609.12243v1 Announce Type: new Abstract: Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-training. However, many existing SMC approaches rely on equal-weight resampling, which can aggressively prune low-weight t…
arxiv.org4 days agoView details
HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge
arXiv:2609.12260v1 Announce Type: new Abstract: Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply produce convincing-sounding ideas. To study this, we combine three major biological databases: the Kyoto Encyclopedia of G…
arxiv.org4 days agoView details
Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models
arXiv:2609.12303v1 Announce Type: new Abstract: Small models are made more capable through distillation from a larger one that shares their tokenization scheme. However, do distilled byte and token models behave similarly in terms of scaling trends as compute and data increases? To enable this comparison, we introduce…
arxiv.org4 days agoView details
SynthSentry: Detecting Synthetic Data Contamination in Language Model Training Data
arXiv:2609.12353v1 Announce Type: new Abstract: Large language models trained recursively on their own or other models' outputs undergo model collapse, in which distributional tails and factual accuracy deteriorate while fluency survives. Prior work diagnoses collapse after training; the actionable problem is screenin…
arxiv.org4 days agoView details
CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory
arXiv:2609.12354v1 Announce Type: new Abstract: Long-term conversational agents must answer user queries by recalling information from extended dialogue histories, yet directly using the full history is costly and often unreliable, while compressed memory units may lose fine-grained evidence needed for question answer…
arxiv.org4 days agoView details
ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge
arXiv:2609.12366v1 Announce Type: new Abstract: We present ORQA, a method for testing occupation-level knowledge in large language models. Prior methods either map abstract LLM skills to occupations via task definitions or utilize expert knowledge which is difficult to obtain at scale and expensive. ORQA complements b…
arxiv.org4 days agoView details
Agent as Policy for Robotic Manipulation
arXiv:2609.12541v1 Announce Type: new Abstract: We demonstrate that a general-purpose agent can directly drive a physical robot throughout task execution without any task-specific or environment-specific training. We introduce Agent as Policy (AGP), which places task planning and execution under the agent's control. G…
arxiv.org4 days agoView details
arXiv:2609.12544v1 Announce Type: new Abstract: Clinical de-identification relies on accurately identifying personally identifiable information (PII). However, manually annotated datasets are costly to construct, while existing synthetic alternatives often provide limited details about their generation process or rely…
arxiv.org4 days agoView details
arXiv:2609.12575v1 Announce Type: new Abstract: Ambiguity is often treated as a bug for AI systems to resolve---but in human communication and culture, ambiguity can also be a generative resource. From humour to politics to art, people express themselves in words and images that are open enough to invite different int…
arxiv.org4 days agoView details
LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
arXiv:2609.12655v1 Announce Type: new Abstract: Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, existing memory-based agents struggle to transfer reusable experience across environments and suffer from catastrophic fo…
arxiv.org4 days agoView details
arXiv:2609.12791v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has empowered Large Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterogeneous knowledge bases (large-scale knowledge graphs and text corpora) for complex reasoning remains a challenge. Exist…
arxiv.org4 days agoView details
arXiv:2609.12872v1 Announce Type: new Abstract: We present DuplexDrama, the first synthesized spoken dialogue dataset that simultaneously covers four dimensions: (i) complete persona and scenario settings; (ii) three full-duplex behaviors (interruption, backchannel, incomplete); (iii) expressive speech with persona-al…
arxiv.org4 days agoView details
MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification
arXiv:2609.12884v1 Announce Type: new Abstract: A medical claim's correctness often depends not on the claim alone, but on the clinical structure around it. A claim may require a lab reference range, a causal or conditional link, or patient-specific details to be judged correctly, and atom-level decomposition can frag…
arxiv.org4 days agoView details
LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification
arXiv:2609.12915v1 Announce Type: new Abstract: Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of thousands of candidate labels. Although pretrained language models have improved semantic text representations, most r…
arxiv.org4 days agoView details
Fewer Words, Not Fewer Tokens: Measuring the Sanskrit Tokenization Penalty per Proposition
arXiv:2609.12960v1 Announce Type: new Abstract: Sanskrit fuses case, number, person and tense into word endings and chains clauses into compounds, so it is information-dense per word. Whether that density survives subword tokenization is a separate question, to be asked per unit of meaning rather than per word. On ide…
arxiv.org4 days agoView details
Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage
arXiv:2609.13003v1 Announce Type: new Abstract: Binary-choice truth benchmarks ask models to choose between a correct and an incorrect answer, but if the two answers differ systematically in surface-level features, models can exceed chance without performing the intended reasoning. We show that this failure mode is de…
arxiv.org4 days agoView details
arXiv:2609.13005v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are increasingly adept at multi-hop reasoning. However, these benchmarks are typically short-horizon, requiring only a small n…
arxiv.org4 days agoView details
Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
arXiv:2609.13045v1 Announce Type: new Abstract: Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-linguistic information. However, these models struggle with predicting high-bitrate speech tokens in LLMs, and face the chall…
arxiv.org4 days agoView details
Expert-Space Exploration in MoE Reinforcement Learning
arXiv:2609.13058v1 Announce Type: new Abstract: Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have primarily focused on improving optimization stability and training efficiency, while treating the expert selection as…
arxiv.org4 days agoView details
Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
arXiv:2609.13117v1 Announce Type: new Abstract: Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: continuing to speak while incorporating what the listener just contributed. The contribution may be a missing word, a corre…
arxiv.org4 days agoView details
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
arXiv:2609.13141v1 Announce Type: new Abstract: Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for each query. Existing trainable methods usually use a lightweight selector to score context u…
arxiv.org4 days agoView details
PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews
arXiv:2609.11559v1 Announce Type: cross Abstract: Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 an…
arxiv.org4 days agoView details
arXiv:2609.11959v1 Announce Type: cross Abstract: Space is a foundational concept across mathematics, physics, spatial cognition, urban science, and embodied intelligence, yet these fields often treat spatial structure either as a shared geometric container or as a collection of disconnected representations. Such appr…
arxiv.org4 days agoView details
Cortex: Content Analysis Support Software, a Resource for Qualitative Research
arXiv:2609.11970v1 Announce Type: cross Abstract: Qualitative research is widely used in the human and social sciences, characterized by a deep understanding of phenomena through the interpretation of meanings and contexts. Among qualitative data analysis methods, content analysis stands out as a consolidated techniqu…
arxiv.org4 days agoView details
Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents
arXiv:2609.11999v1 Announce Type: cross Abstract: In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results in coding, but enterprise work also involves moving between applications and services, coordinating with coworkers, and…
arxiv.org4 days agoView details
Creating an Atomic User Model for Personality-Aware Large Language Model Interaction
arXiv:2609.12086v1 Announce Type: cross Abstract: Assistants built on large language models are expected to write as their user would, and the dominant approach is single-channel: preferences summarised from conversation history and reinserted into context. This inverts the order of inference. Preferences are the task…
arxiv.org4 days agoView details
Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis
arXiv:2609.12403v1 Announce Type: cross Abstract: Cognitive Diagnosis Models (CDMs) play a pivotal role in personalized online learning. Traditional CDMs rely on discrete, ID-based embeddings to represent students, exercises, and concepts. This paradigm diverges from the nature of learner cognition, where knowledge is…
arxiv.org4 days agoView details
Confidence-Gated Transductive Test Generation for Code Reranking
arXiv:2609.12489v1 Announce Type: cross Abstract: Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test cases remains challenging because reliable expected outputs are often difficult to obtain. We propose Confidence-Gated…
arxiv.org4 days agoView details
Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents
arXiv:2609.12533v1 Announce Type: cross Abstract: Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare data, perform domain computations, and derive conclusions from runtime evidence. Existing EO agents typically start from s…
arxiv.org4 days agoView details
Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size
arXiv:2609.12686v1 Announce Type: cross Abstract: Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increases proportionally to input length. Although model optimization and lossy prompt compression are widely used, these meth…
arxiv.org4 days agoView details
What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
arXiv:2609.12746v1 Announce Type: cross Abstract: Agentic pipelines for structured-query generation are rapidly expanding, but it is unclear which part of the loop produces the gain. We use LAST-CQ -- a five-agent, training-free, execution-grounded Text-to-Cypher framework -- as an instrumented testbed, running three…
arxiv.org4 days agoView details
Models
View all models →Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh
image-text-to-text · transformers · safetensors · qwen3_5
huggingface.co5 days ago348 ptsView detailsJoin discussion
image-text-to-text · gguf · llama.cpp · qwen3_8
huggingface.co4 days ago207 ptsView details
text-generation · transformers · safetensors · gguf
huggingface.co5 days ago1 ptsView details
text-generation · transformers · safetensors · qwen2
huggingface.co5 days agoView details
Open source
View all open source →<details open> common : move llama_n_rs_seq to before llama_decode (#28749) This commit moves the llama_n_rs_seq function call to before the llama_decode call and returns directly if the check is true, removing the setting of res and the goto statement. The motivation for this c…
github.com4 days agoView details
<details open> ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) * ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA) * apply logic to NVIDIA as well --------- Co-authored-by: Johanne…
github.com4 days agoView details
<details open> vulkan: workaround NV queuesubmit driver bug (#28830) There is a driver bug where two queues on the same VkDevice simultaneously submitting can break some internal synchronization. Until it's fixed, add a mutex around queuesubmit. </details> **Website:** - <https:…
github.com5 days agoView details
<details open> opencl: apply the noshuffle row-alignment rule to q4_K, q5_K and q8_0, not just q6_K (#28575) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/47132459> **macOS/iOS:** - [macOS Apple Silicon (arm…
github.com5 days agoView details