AI研究論文每日精選

Differential Transformer

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide

FAN: Fourier Analysis Networks

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

UniMuMo: Unified Text, Music and Motion Generation

MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Presto! Distilling Steps and Layers for Accelerating Music Generation

Named Clinical Entity Recognition Benchmark

TLDR: Token-Level Detective Reward Model for Large Vision Language Models

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs

TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles

OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction

What Matters for Model Merging at Scale?

SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification

Autonomous Character-Scene Interaction Synthesis from Text Instruction

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach

Grounding Language in Multi-Perspective Referential Communication

SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation