AI研究論文デイリー

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

MegaMath: Pushing the Limits of Open Math Corpora

Agentic Knowledgeable Self-awareness

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning

TransMamba: Flexibly Switching between Transformer and Mamba

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models

HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

MedSAM2: Segment Anything in 3D Medical Images and Videos

Slow-Fast Architecture for Video Multi-Modal Large Language Models

BEATS: Bias Evaluation and Assessment Test Suite for Large Language Models

EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling

Real-is-Sim: Bridging the Sim-to-Real Gap with a Dynamic Digital Twin for Real-World Robot Policy Evaluation

Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery

SPF-Portrait: Towards Pure Portrait Customization with Semantic Pollution-Free Fine-tuning