AI研究論文每日精選

RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Quantizing Large Language Models for Code Generation: A Differentiated Replication

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?

More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG

Motion Anything: Any to Motion Generation

VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary

Cost-Optimal Grouped-Query Attention for Long-Context LLMs

Monte Carlo Diffusion for Generalizable Learning-Based RANSAC

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

WildIFEval: Instruction Following in the Wild

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

Understanding and Mitigating Distribution Shifts For Machine Learning Force Fields

Multi Agent based Medical Assistant for Edge Devices

Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

Multimodal Language Modeling for High-Accuracy Single Cell Transcriptomics Analysis and Generation

Self-Taught Self-Correction for Small Language Models

TPDiff: Temporal Pyramid Video Diffusion Model

Reangle-A-Video: 4D Video Generation as Video-to-Video Translation