Large language models

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

28,678 stories · RSS feed

arXiv Computer Vision

Oct 2

Video-Index: A Curated Meta-Benchmark for Video Understanding

arXiv:2610.00960v1 Announce Type: new Abstract: A video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence....

By Enxin Song, Yinuo Xu, Shusheng Yang, Wenhao Chai, Jiatao Gu

llms agents benchmarks

arXiv Computer Vision

Oct 2

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...

By Xianda Du, Max Ku, Weiming Ren, Zhi Rui Tam, Chunlin Ren, Ping Nie, Min-Hung Chen, Wenhu Chen

llms diffusion fine-tuning multimodal benchmarks

arXiv Computer Vision

Oct 2

Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation

arXiv:2610.01022v1 Announce Type: new Abstract: Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory r...

By Arash Rocky, Q. M. Jonathan Wu

llms computer-vision benchmarks

arXiv Computer Vision

Oct 2

HAWK: Rethinking Multimodal Drafting for Speculative Decoding

arXiv:2610.00623v1 Announce Type: new Abstract: Speculative decoding has achieved substantial lossless speedups for LLMs, but remains less effective for large vision-language models (LVLMs), where li...

By Wenhan Yang, Anirudh Rao, Ashwin Chandra

llms efficiency multimodal benchmarks

arXiv Computer Vision

Oct 2

Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language Models

arXiv:2610.01180v1 Announce Type: new Abstract: Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently str...

By Yuliang Cai, Mohammad Rostami, Jesse Thomason

llms nlp multimodal benchmarks

arXiv Computer Vision

Oct 2

FlashBack: Knowing When to Remember in Streaming Vision-Language Models

arXiv:2610.01192v1 Announce Type: new Abstract: Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between...

By Yi Chen, MingMing Yu, Rui-Qi Wang, Boran Wang, Xiaohang Cao, Chu Tang, Jingmin Chen, Jie Gu

llms multimodal

arXiv Computer Vision

Oct 2

FFBL-Coop: Association-Decoupled Cooperative 3D Multi-Object Tracking

arXiv:2610.01750v1 Announce Type: new Abstract: Cooperative 3D tracking must integrate complementary observations across agents and time while maintaining consistent identities. When evidence integra...

By Haoxin Wu, Xiaokai Bai

llms agents

arXiv Computer Vision

Oct 2

GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design

arXiv:2610.01778v1 Announce Type: new Abstract: Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cov...

By Baoke Dou, Ziye Wang, Hao Wang, Guoqing Cai, Wende Tan, Chenyang Si, Liucheng Guo, Yueming Lyu

llms robotics benchmarks

arXiv Computer Vision

Oct 2

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

arXiv:2610.01939v1 Announce Type: new Abstract: Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant obser...

By Ruiyang Si, Jianxin Bi, Shunyu Yang, Rui Ni, Wenbo Huang, Qiang Wang, Shulong Jiang, Duomin Wang, Xiuyu Li, Haiwen Feng, Zhen Dong, Daquan Zhou

llms agents robotics multimodal

arXiv Computer Vision

Oct 2

Token-Level Video Reinforcement Learning

arXiv:2610.01973v1 Announce Type: new Abstract: Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: som...

By Yifan Wang, Gordon Guocheng Qian, Yanyu Li, Anil Kag, Yun Fu

llms diffusion reinforcement-learning multimodal

arXiv Computer Vision

Oct 2

OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning

arXiv:2610.02181v1 Announce Type: new Abstract: We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with nativ...

By Haibo Wang, Jiteng Mu, Jialu Li, Jingru Yi, Yuanjun Xiong, Jianming Zhang, Lifu Huang, Mingze Xu

llms agents reinforcement-learning multimodal benchmarks

arXiv Computer Vision

Oct 2

Moore, Escher, Penrose: A Conformal Golden Braid

arXiv:2610.02210v1 Announce Type: new Abstract: I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall o...

By Sophia Feldman, Assaf Shocher

llms diffusion

arXiv Computer Vision

Oct 2

Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure

arXiv:2610.00680v1 Announce Type: cross Abstract: Curvature is often treated as an intrinsic property of a representation, although its empirical effect also depends on coordinate scale, learned logi...

By Athanasios Angelakis, Marta Gomez-Barrero

llms computer-vision safety

arXiv Computer Vision

Oct 2

From Reasoning Failures to Composable Video Spatial Intelligence

arXiv:2610.01999v1 Announce Type: new Abstract: Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities ac...

By Pengzhan Sun, Junbin Xiao, Ramanathan Rajaraman, Shiu-hong Kao, Angela Yao

llms agents multimodal benchmarks

arXiv Computer Vision

Oct 2

SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning

arXiv:2610.01962v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of...

By Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham, Kwok-Yan Lam

llms multimodal benchmarks

arXiv Computer Vision

Oct 2

InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation

arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills...

By Zhuo Lin, Sirui Xu, Liuyu Bian, Yu-Xiong Wang, Liang-Yan Gui

llms agents robotics

arXiv Computer Vision

Oct 2

REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detection

arXiv:2502.14994v2 Announce Type: replace Abstract: The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on spec...

By Yun-Yun Tsai, Qingyuan Liu, Ruijian Zha, Victoria Li, Pengyuan Shi, Chengzhi Mao, Junfeng Yang

llms diffusion multimodal benchmarks safety

arXiv Computer Vision

Oct 2

VideoSTF: Stress-Testing Output Repetition in Video Large Language Models

arXiv:2602.10639v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) have achieved strong performance on video understanding tasks, yet existing benchmarks evaluate only what m...

By Yuxin Cao, Wei Song, Shangzhi Xu, Jingling Xue, Jin Song Dong

llms benchmarks

arXiv Computer Vision

Oct 2

Compressing History into Memory: Distilling Transformers into Recurrent Transformers

arXiv:2606.21562v2 Announce Type: replace Abstract: Transformers are AI's workhorse but their computational cost becomes prohibitive when processing long sequences. We target long-horizon streaming v...

By Philippe Weinzaepfel, Christian Wolf, Mert B\"ulent Sariyildiz, Guillaume Bono, Gianluca Monaci

llms nlp robotics efficiency

arXiv Computer Vision

Oct 2

Subtoken Vision Transformer for Fine-grained Recognition

arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...

By Jie Zhu, Ivy Zhang, Minchul Kim, Xiaoming Liu

llms computer-vision nlp

Get the daily briefing