Large language models

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

31,367 stories · RSS feed

arXiv Computer Vision

Sep 22

GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents

arXiv:2609.22308v1 Announce Type: new Abstract: Coding-agent benchmarks usually evaluate implementation after the target behavior has been specified in text, code, or demonstrations. Existing researc...

By Boyu Qiao, Zixin Tang, Xiaoshuai Hao, Wenbo Li

llms agents multimodal benchmarks

arXiv Computer Vision

Sep 22

Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act

arXiv:2609.22588v1 Announce Type: new Abstract: Vision-language models (VLMs) perform strongly on visual question answering benchmarks, yet often make decisions that contradict visual evidence they h...

By Yuyang Dai, Bofei Huang, Hongbo Zhang, Haoran Xie

llms nlp multimodal benchmarks

arXiv Computer Vision

Sep 22

Math2Visual-X: A Modular Framework for Pedagogically Aligned Lower-Primary Math Visuals Generation

arXiv:2609.22647v1 Announce Type: new Abstract: Visual representations can help lower-primary learners understand Math Word Problems, but generating classroom-usable visuals remains difficult. Existi...

By H. D. E. Maduranga, S. K. Munasinghe, K. P. T. I. Weerasekara, Surangika Ranathunga, Nisansa de Silva

llms diffusion

arXiv Computer Vision

Sep 22

Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling

arXiv:2609.22688v1 Announce Type: new Abstract: Generating parametric CAD models requires accurate geometry and stable feature dependencies. Existing methods face challenges in selecting geometric re...

By Xi Cheng, Chenxi Zhai, Hang Cheng, Mingyu Fan, Pingfa Feng, Long Zeng

llms agents multimodal benchmarks

arXiv Computer Vision

Sep 22

PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining

arXiv:2609.22789v1 Announce Type: new Abstract: Image-to-layer decomposition converts a flattened image into editable RGBA layers, enabling element-level editing in design workflows. Existing diffusi...

By Zelin Jia, Zhao Zhang, Zhicong Tang, Yuhui Yuan, Shixia Liu

llms diffusion multimodal benchmarks

arXiv Computer Vision

Sep 22

D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction

arXiv:2609.22941v1 Announce Type: new Abstract: Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and m...

By Yunqi Gao, Zhanfeng Liao, Hanzhang Tu, Zhaoqi Su, Guoqing Zheng, Songtao Wang, Hongwen Zhang, Zhou Xue, Leyuan Liu, Yebin Liu

llms diffusion benchmarks

arXiv Computer Vision

Sep 22

CrowdCue: Specialist-Cue Conditioning for Vision-Language Crowd Counting

arXiv:2609.23012v1 Announce Type: new Abstract: Generative vision-language models (VLMs) offer a counting paradigm in which one model produces both a count and a natural-language account of the scene...

By Moshiur Farazi, Bekir Ciftler, Abdulhalim Dandoush, Reda Bendraou

llms fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Sep 22

Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains

arXiv:2609.23655v1 Announce Type: new Abstract: Imbalanced gradient magnitudes between the visual and language pathways of a vision-language model are often treated as a defect to be corrected. We te...

By Kiran Naseer, Samreen Azhar, Dwarikanath Mahapatra

llms fine-tuning multimodal

arXiv Computer Vision

Sep 22

PRISM-RAG: Multimodal Hypergraph Retrieval-Augmented Generation for Tobacco Product and Legislative Policy Reasoning

arXiv:2609.23769v1 Announce Type: new Abstract: The disambiguation of semantically similar statutory text across jurisdictions is a retrieval problem that existing methods do not solve. This inter-co...

By Manuel Serna-Aguilera, Raegan Anderes, Page Dobbs, Khoa Luu

llms rag multimodal benchmarks

arXiv Computer Vision

Sep 22

Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene

arXiv:2609.23796v1 Announce Type: new Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challe...

By Yang-Tian Sun, Tianjia Liu, Zehuan Huang, Yi-Hua Huang, Xiaoyang Lyu, Ziyi Yang, Zi-Xin Zou, Yuan-Chen Guo, Yan-Pei Cao, Xiaojuan Qi

llms diffusion multimodal safety

arXiv Computer Vision

Sep 22

U-PEN Mamba: Progressive Expansion with Selective State-Space Modeling for Efficient Retinal Vessel Segmentation

arXiv:2609.24049v1 Announce Type: new Abstract: Accurate retinal vessel segmentation is important for computer-aided ophthalmic analysis, yet thin vessels, low contrast, and severe foreground-backgro...

By Abel A. Reyes-Angulo, Sidike Paheding, Vijayan K. Asari, Mohammad Alam, Jeevan Devagiri

llms computer-vision benchmarks

arXiv Computer Vision

Sep 22

An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond

arXiv:2609.24170v1 Announce Type: new Abstract: Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency,...

By Wenbo Zhang, Kaixuan Wang, Yutao Ouyang, Xiaoyu Huang, Liyang Li, Kailun Su, Weiyang Jin, Wenhao Chai, Haotian Liang, Zhiyang Dou, Yue Chen, Tianxing Chen

llms robotics fine-tuning

arXiv Computer Vision

Sep 22

Benchmarking Off-the-Shelf Multimodal AI Models Against Dermatologists on Patient-Captured Skin Images

arXiv:2609.24190v1 Announce Type: new Abstract: Artificial intelligence (AI) has advanced at a rapid pace in recent years. Initially, breakthroughs in large language models caught widespread attentio...

By Rian Dolphin, Laura Knowles

llms multimodal benchmarks

arXiv Computer Vision

Sep 22

SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentation

arXiv:2609.24204v1 Announce Type: new Abstract: Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems t...

By Anja Deli\'c, Jurica Runtas, Marin Or\v{s}i\'c, Ivan Markovi\'c, Ivan Petrovi\'c

llms agents computer-vision benchmarks

arXiv Computer Vision

Sep 22

SRPR-Net: Semantic and Relational Prompt Refinement for Automated SAM-based Instance Segmentation

arXiv:2609.24226v1 Announce Type: new Abstract: Instance segmentation is a fundamental computer vision task with diverse real-world applications. Recently, prompt-driven foundation models have shown...

By Lufei Liu, Guojie Li, Suncheng Xiang, Fan Zhang

llms computer-vision benchmarks

arXiv Computer Vision

Sep 22

Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy

arXiv:2609.24470v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly explored as interfaces for scientific image analysis, where a visual question-answering (VQA)...

By Samia Mohinta, Albert Cardona

llms agents computer-vision multimodal

arXiv Computer Vision

Sep 22

ME-VLM:A Unified VLM for Embodied Cognition and Agent Coordination

arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and...

By Foundation Model, Li Auto Inc

llms agents reinforcement-learning robotics efficiency multimodal benchmarks

arXiv Computer Vision

Sep 22

HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space

arXiv:2609.24564v1 Announce Type: new Abstract: CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encode...

By Zelin Peng, Zhengqin Xu, Changsong Wen, Yu Huang, Yaoming Wang, Xiaokang Yang, Wei Shen

llms rag computer-vision fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Sep 22

PixelDiT2: Representation-Grounded Pixel Diffusion Transformers

arXiv:2609.24919v1 Announce Type: new Abstract: Recent advances in pixel-space diffusion models have narrowed the image quality gap with latent-space diffusion, but still converge more slowly and lag...

By Yongsheng Yu, Wei Xiong, Yichen Sheng, Shiqiu Liu, Jiebo Luo

llms diffusion

arXiv Computer Vision

Sep 22

Multicentre Bi-atrial Segmentation from LGE-MRI for Atrial Fibrillation with a 2D and 3D Framework

arXiv:2609.22398v1 Announce Type: cross Abstract: Accurate delineation of bi-atrial structures from late gadolinium enhancement MRI (LGE-MRI) is an important prerequisite for structural analysis and...

By Malitha Gunawardhana, Gregory B. Sands, Mark L. Trew, Jichao Zhao

llms computer-vision fine-tuning benchmarks

Get the daily briefing