Large language models

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

29,118 stories · RSS feed

arXiv Computer Vision

Oct 1

VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understanding

arXiv:2609.38413v1 Announce Type: new Abstract: Vision-language models (VLMs) can answer questions about hour-long videos, but processing every frame is prohibitively expensive, even though the evide...

By Susan Liang, Jianmin Wu, Daxiang Dong

llms agents multimodal benchmarks

arXiv Computer Vision

Oct 1

ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing

arXiv:2609.38541v1 Announce Type: new Abstract: Instruction-guided video editing has made significant progress, yet existing methods use multimodal large language models (MLLMs) primarily as semantic...

By Donghao Zhou, Haoyang He, Fan Zhang, Hao Yang, Guisheng Liu, Xin Gao, Zhongwei Wan, Xingyuan Bu, Jie Wang, Qiangpeng Yang, Shilei Wen, Chi-Wing Fu, Pheng-Ann Heng

llms multimodal benchmarks

arXiv Computer Vision

Oct 1

Distill the Visual Evidence, Not Just the Answer: Cross-World On-Policy Distillation for Vision-Language Models

arXiv:2609.38777v1 Announce Type: new Abstract: A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding. Howeve...

By Yuanhao Sun, Huawei Ji, Jiaxin Ding, Luoyi Fu, Xinbing Wang

llms efficiency multimodal

arXiv Computer Vision

Oct 1

Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting

arXiv:2609.38979v1 Announce Type: new Abstract: Multiple object hallucination, where large vision-language models (LVLMs) generate objects not supported by the visual input, is a persistent challenge...

By Chang Liu, Yu Tian, Rui Xie

llms multimodal benchmarks safety

arXiv Computer Vision

Oct 1

Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers

arXiv:2609.39184v1 Announce Type: new Abstract: Fiber orientation and compartmental microstructure are central to the characterization of white matter tissue in diffusion MRI, yet existing methods ei...

By Sebastian Endt, Marcus Wirth, Johannes Reinhold Schlund, Marion Irene Menzel

llms diffusion computer-vision benchmarks

arXiv Computer Vision

Oct 1

Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-Identification

arXiv:2609.39492v1 Announce Type: new Abstract: Matching the same vehicle across front and rear cameras is difficult because the cameras do not share a view and the vehicle's appearance changes subst...

By Moseli Mots'oehli, Thulani Babeli

llms multimodal benchmarks

arXiv Computer Vision

Oct 1

TexTailor: Texture-Preserving Video Virtual Try-On via Adaptive Garment Conditioning

arXiv:2609.39335v1 Announce Type: new Abstract: Video virtual try-on has attracted increasing attention due to its broad potential in digital fashion and intelligent e-commerce. However, existing met...

By Zijing Qin, Jun Zhou, Ruicheng Zhang, Jiaqi Hou, Zunnan Xu, Ronghui Li, Zhenyu Xie, Xiu Li

llms diffusion multimodal benchmarks

arXiv Computer Vision

Oct 1

MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation

arXiv:2609.39681v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g...

By Ivan Martinovi\'c, Josip \v{S}ari\'c, Yuki M. Asano, Sini\v{s}a \v{S}egvi\'c

llms computer-vision fine-tuning benchmarks safety

arXiv Computer Vision

Oct 1

Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models

arXiv:2609.39899v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging (CMR) enables assessment of cardiac anatomy, ventricular function, and myocardial tissue characteristics. Clinicians...

By Bangwei Guo, Xiao Chen, Boris Mailhe, Jia Yao, Yiqing Wang, Ankush Mukherjee, Yikang Liu, Zheyuan Zhang, Hang Yu, Terrence Chen, Shanhui Sun

llms nlp multimodal

arXiv Computer Vision

Oct 1

LOCI: Spatial Linear Memory for Streaming World Models

arXiv:2609.40222v1 Announce Type: new Abstract: When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past ob...

By Ji Xia, Tingting Liao, Xuezhi Liang, Hao Li, Guangyi Liu

llms benchmarks

arXiv Computer Vision

Oct 1

Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction

arXiv:2609.39757v1 Announce Type: cross Abstract: Black-box distillation is a practical route for transferring capabilities from API-accessible large language models that expose only text outputs int...

By Xiao Cui, Mo Zhu, Yulei Qin, Yuze Wu, Wengang Zhou, Houqiang Li

llms efficiency safety

arXiv Computer Vision

Oct 1

SPROUT: A Scalable Diffusion Foundation Model for Multi-Crop Plant Phenotyping

arXiv:2603.27519v4 Announce Type: replace Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, orga...

By Shuai Xiang, James Burridge, Shouyang Liu, Hao Lu, Tokihiro Fukatsu, Yinqiang Zheng, Wei Guo

llms diffusion computer-vision

arXiv Computer Vision

Oct 1

PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry Transformers

arXiv:2605.08371v2 Announce Type: replace Abstract: Multi-view geometry transformers are feed-forward 3D foundation models that jointly predict depth maps, point maps, and camera poses for N images i...

By Haotang Li, Zhenyu Qi, Shaohan Henry Wang, Kebin Peng, Zi Wang, Qing Guo, Sen He, Huanrui Yang

llms efficiency

arXiv Computer Vision

Oct 1

SegRAG: Retrieval Augmented Spatial Prompting for Open Vocabulary Semantic Segmentation

arXiv:2605.17630v3 Announce Type: replace Abstract: Frozen segmentation foundation models often fail when the target class appears in a form that is weakly represented during pretraining. To address...

By Abderrahmene Boudiaf, Irfan Hussain, Sajid Javed

llms rag computer-vision efficiency

arXiv Computer Vision

Oct 1

D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation

arXiv:2609.34792v2 Announce Type: replace Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-actio...

By Zijian Ye, Chengqi Wei, Wei Huang, Anlin Zheng, Chunyu Zou, Liangyu Wu, Zikang Zhao, Zhenjie Peng, Yushuo Yang, Shuman Zhao, Zhongrui Wang, Xiaojuan Qi

llms robotics multimodal benchmarks

arXiv Statistics ML

Oct 1

Mining Causality: AI-Assisted Search for Instrumental Variables

arXiv:2409.14202v4 Announce Type: replace-cross Abstract: The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process...

By Sukjin Han

llms agents

arXiv AI

Oct 1

ORACLE: Agentic AI Orchestrator Routing Via Adaptive Verifier Calibration Feedback

arXiv:2607.22465v3 Announce Type: replace Abstract: Modern enterprise agent deployments consist of a heterogeneous pool of large language models (LLMs) having diverse capabilities and cost. Existing...

By Ritik Raj, Souvik Kundu, Dheemanth Joshi, Tushar Krishna

llms agents efficiency benchmarks

arXiv AI

Oct 1

Learning to Route in Visual Space via Multi-Step Embedding Retrieval

The paper introduces VHOP, a data generation framework and benchmark for visual agentic search, and VHOP-Router, an end‑to‑end training pipeline that turns a standard embedding model into an autoregressive multi‑step retriever operating directly in visual latent space. VHOP-Router eliminates the need for intermediate text queries, boosting retrieval accuracy from under 5% to 76.3% and improving task success rates by 52.7% while dramatically reducing token usage and API payloads. The approach generalizes to unseen difficulty levels and realistic test sets, offering an efficient solution that preserves native LLM capabilities.

By Tianyu Chen, Mingyuan Zhou, Jiaxing Wu

llms rag agents diffusion reinforcement-learning fine-tuning benchmarks

arXiv AI

Oct 1

From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs

arXiv:2609.38516v1 Announce Type: cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to wor...

By Kunal Jha, Max Kleiman-Weiner, Natasha Jaques

llms agents

arXiv Computer Vision

Oct 1

It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at $\epsilon \leq 4/255$

arXiv:2609.38298v1 Announce Type: new Abstract: Vision Language Models (VLMs) are widely deployed in safety-critical scenarios, and understanding to which extent they can be controlled by adversarial...

By Binchi Zhang, Atrisha Sarkar, Apurva Narayan

llms multimodal safety

Get the daily briefing