Articles de Recherche en IA Quotidiens

Qwen2 Technical Report

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs

GRUtopia: Dream General Robots in a City at Scale

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation

Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion

DataDream: Few-shot Guided Dataset Generation

Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity

Video Occupancy Models

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

LAB-Bench: Measuring Capabilities of Language Models for Biology Research

SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning

MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction Large Language Models

LLM Circuit Analyses Are Consistent Across Training and Scale

Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models