Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

27,837 stories · RSS feed

arXiv AI

Oct 5

ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling

arXiv:2602.09009v2 Announce Type: replace-cross Abstract: Scaling network depth has been a central driver behind the success of modern foundation models, yet recent investigations suggest that deep l...

By Yilang Zhang, Bingcong Li, Niao He, Georgios B. Giannakis

llms diffusion

arXiv AI

Oct 5

$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training

arXiv:2609.32791v2 Announce Type: replace Abstract: Reinforcement mid-training lets language models learn internal thoughts from unlabeled text, but efficient token-level credit assignment remains ch...

By Nan Qiao, Yebin Yang, Weinong Wang, Shuning Wang, Shangpin Peng, Fengyuan Lu, Xinming Wang, Zhehan Kan, Ruixu Zhang, Songyang Zhang, Sheng Yue, Yonglong Tian, Ju Ren

llms reinforcement-learning benchmarks

arXiv Machine Learning

Oct 5

SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention

arXiv:2610.02953v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compres...

By Zihan Teng, Jiayu Zhao, Wentao Ren, Minhao Fan, Tianrui Ma, Song Chen, Weichen Liu

llms rag efficiency

arXiv Machine Learning

Oct 5

Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization

arXiv:2610.02798v1 Announce Type: new Abstract: The Muon optimizer applies spectral orthogonalization to matrix-valued updates and has shown strong performance in large-scale neural network training,...

By Xuheng Li, Qiwei Di, Yuan Cao, Quanquan Gu

llms rag

arXiv Machine Learning

Oct 5

All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR

arXiv:2610.02835v1 Announce Type: new Abstract: During post-training of large language models (LLMs) with Reinforcement Learning with Verifiable Rewards (RLVR), GRPO-style algorithms can exhibit seve...

By Qiyuan Huang, Tianshi Xu, Meng Li

llms reinforcement-learning efficiency

arXiv Machine Learning

Oct 5

Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering

arXiv:2610.02391v1 Announce Type: new Abstract: When a large language model solves a mathematical problem, its reasoning is largely hierarchical, and the solution often branches at a few tokens where...

By Zeyong Zhang, Tung Sum Thomas Kwok, Tengfei Ma, Mengjia Xu

llms

arXiv Machine Learning

Oct 5

Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning

arXiv:2605.10247v2 Announce Type: replace Abstract: Applying Large Language Models (LLMs) to graph-structured data usually involves multi-step pipelines in which textual node attributes are compresse...

By Dario Vajda

llms fine-tuning benchmarks

arXiv Machine Learning

Oct 5

From Patching to Pruning Visual Computation in Vision Language Models

arXiv:2610.03389v1 Announce Type: cross Abstract: Vision language models (VLMs) incur substantial inference cost because every visual token is processed by the attention and MLP projections of every...

By Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen, Shaoyi Huang, Pu Zhao, Yanzhi Wang

llms efficiency multimodal benchmarks safety

arXiv Machine Learning

Oct 5

RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models

arXiv:2610.02817v1 Announce Type: cross Abstract: Large Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remai...

By Yi Wang, Baicheng Chen, Yu Wang, Jian Zhao, Yilei Chen, Tianxing He

llms safety

arXiv Machine Learning

Oct 5

Localized Conformal Safety Monitoring with Vision-Language Models for Autonomous Driving

arXiv:2610.02765v1 Announce Type: cross Abstract: Monitoring planned driving trajectories requires accurately estimating the collision likelihood with actors whose motion is itself impacted by the eg...

By Lu\'is Marques, Rong Fang, Disha Kamale, Dmitry Berenson

llms agents robotics multimodal safety

arXiv Machine Learning

Oct 5

Metropolis-Hastings Dominates Importance Resampling for Policy Composition

arXiv:2610.03480v1 Announce Type: new Abstract: Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive...

By Alexey Kurennoy, Ramil Yarullin, Fergal Reid

llms safety

arXiv Computation and Language

Oct 5

Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks

arXiv:2610.02549v1 Announce Type: new Abstract: Time and event expression extraction are fundamental temporal reasoning tasks, but the problem remains difficult due to annotation ambiguity, domain se...

By Fahmid Shahriar Iqbal, Ritam Dutt, Soumitra Das, Arnav Verma, Sagnik Ray Choudhury

llms safety

arXiv Computation and Language

Oct 5

Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents

arXiv:2610.03448v1 Announce Type: cross Abstract: LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchma...

By Zhuowen Liu

llms agents benchmarks

arXiv Computer Vision

Oct 5

Octrees as an Explicit 3D Language

arXiv:2610.02388v1 Announce Type: new Abstract: Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes...

By Ran Dan, Si-Tong Wei, Pengfei Xiong, Wei Zhang, Yadong Mu, Peng-Shuai Wang

llms fine-tuning multimodal benchmarks

arXiv Computation and Language

Oct 5

WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models

arXiv:2510.22276v4 Announce Type: replace-cross Abstract: Contrastive vision-language models have achieved remarkable progress through large-scale pretraining. Recent work has shown that removing Eng...

By Issa Sugiura, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Yasuo Okabe, Naoaki Okazaki

llms fine-tuning multimodal benchmarks

arXiv Computation and Language

Oct 5

CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification

arXiv:2609.33212v2 Announce Type: replace Abstract: Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments. Making these systems...

By Massa Baali, Sarthak Bisht, Ziyue Qiu, Joseph Konan, Rita Singh, Bhiksha Raj

llms fine-tuning

arXiv Computation and Language

Oct 5

Authorship Verification of Transcribed German-Language Videos

arXiv:2607.29168v3 Announce Type: replace Abstract: Authorship Verification (AV) represents an important subfield of digital text forensics and addresses the fundamental question of whether two texts...

By Oren Halvani, Sophie Titze

llms

arXiv Computer Vision

Oct 5

Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models

arXiv:2610.02270v1 Announce Type: cross Abstract: Medical vision-language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and benchmark construction, yet most studies trea...

By Xinye Yang, Zhusi Zhong, Scott Collins, Grayson Baird, Xuyu Wang, Zhicheng Jiao

llms agents multimodal benchmarks

arXiv Computer Vision

Oct 5

LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder

arXiv:2610.03370v1 Announce Type: new Abstract: CLIP's visual encoder produces only global image representations, limiting its use in region-level tasks. Existing adaptations rely on visual prompting...

By Anh-Khoa Dinh-Duc, Duc-Tai Dinh, Tam V. Nguyen, Minh-Triet Tran

llms fine-tuning

arXiv Computer Vision

Oct 5

COSMI: COmpositional Synthesis of Multi-object Interactions

arXiv:2610.03252v1 Announce Type: new Abstract: Generative models of human-object interaction are bounded by the data that exists: everyday activities involve several objects, but most captured datas...

By Daniel Eskandar, Ilya A. Petrov, Gerard Pons-Moll

llms diffusion benchmarks safety

Get the daily briefing