Artigos de Pesquisa em IA Diários

Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing

Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration

X-Dancer: Expressive Music to Human Dance Video Generation

InductionBench: LLMs Fail in the Simplest Complexity Class

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning

MutaGReP: Execution-Free Repository-Grounded Plan Search for Code-Use

Slamming: Training a Speech Language Model on One GPU in a Day

MONSTER: Monash Scalable Time Series Evaluation Repository

Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties

Mind the Gap! Static and Interactive Evaluations of Large Audio Models

Beyond Release: Access Considerations for Generative AI Systems

The snake in the Brownian sphere

TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning

CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models

Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

Early-Exit and Instant Confidence Translation Quality Estimation

MegaLoc: One Retrieval to Place Them All

Diagnosing COVID-19 Severity from Chest X-Ray Images Using ViT and CNN Architectures

Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models

Forecasting Open-Weight AI Model Growth on Hugging Face

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers

GCC: Generative Color Constancy via Diffusing a Color Checker

Audio-FLAN: A Preliminary Release

Self-Taught Agentic Long Context Understanding

M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment

Thus Spake Long-Context Large Language Model

Grounded Persuasive Language Generation for Automated Marketing

Can Community Notes Replace Professional Fact-Checkers?