AI研究論文デイリー

Video-R1: Reinforcing Video Reasoning in MLLMs

Large Language Model Agent: A Survey on Methodology, Applications and Challenges

UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models

VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition

FinAudio: A Benchmark for Audio Large Language Models in Financial Applications

Synthetic Video Enhances Physical Fidelity in Video Synthesis

Optimal Stepsize for Diffusion Sampling

Exploring the Evolution of Physics Cognition in Video Generation: A Survey

Unified Multimodal Discrete Diffusion

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

LLPut: Investigating Large Language Models for Bug Report-Based Input Generation

Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better

LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing