Artigos de Pesquisa em IA Diários

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models

GenXD: Generating Any 3D and 4D Scenes

AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents

DynaSaur: Large Language Agents Beyond Predefined Actions

Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Constrained Diffusion Implicit Models

Training-free Regional Prompting for Diffusion Transformers

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Adaptive Caching for Faster Video Generation with Diffusion Transformers

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

How Far is Video Generation from World Model: A Physical Law Perspective

MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

Sparsing Law: Towards Large Language Models with Greater Activation Sparsity

AutoVFX: Physically Realistic Video Editing from Natural Language Instructions

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

Survey of Cultural Awareness in Language Models: Text and Beyond

LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding