Artigos de Pesquisa em IA Diários

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

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

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

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

Presto! Distilling Steps and Layers for Accelerating Music Generation

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

Named Clinical Entity Recognition Benchmark

UniMuMo: Unified Text, Music and Motion Generation

Autonomous Character-Scene Interaction Synthesis from Text Instruction

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

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

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

Differential Transformer

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach

Grounding Language in Multi-Perspective Referential Communication

What Matters for Model Merging at Scale?

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

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

FAN: Fourier Analysis Networks

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

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

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

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment