AI Research Papers Daily

Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation

JudgeLRM: Large Reasoning Models as a Judge

Multi-Token Attention

Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models

Scaling Language-Free Visual Representation Learning

Z1: Efficient Test-time Scaling with Code

Command A: An Enterprise-Ready Large Language Model

Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?

YourBench: Easy Custom Evaluation Sets for Everyone

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Towards Trustworthy GUI Agents: A Survey

MixerMDM: Learnable Composition of Human Motion Diffusion Models

OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models

Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs

Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base

ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning

DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting

MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing