AI研究论文每日精选

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

Thus Spake Long-Context Large Language Model

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

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

Audio-FLAN: A Preliminary Release

GCC: Generative Color Constancy via Diffusing a Color Checker

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

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning

CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models

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

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

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

Beyond Release: Access Considerations for Generative AI Systems

X-Dancer: Expressive Music to Human Dance Video Generation

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

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

Grounded Persuasive Language Generation for Automated Marketing

Forecasting Open-Weight AI Model Growth on Hugging Face

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

Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties

InductionBench: LLMs Fail in the Simplest Complexity Class

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

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

Can Community Notes Replace Professional Fact-Checkers?

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

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

Early-Exit and Instant Confidence Translation Quality Estimation

Self-Taught Agentic Long Context Understanding

MONSTER: Monash Scalable Time Series Evaluation Repository

MegaLoc: One Retrieval to Place Them All

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

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

The snake in the Brownian sphere