Articles de Recherche en IA Quotidiens

Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation

Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics

MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving

Reconstructing Humans with a Biomechanically Accurate Skeleton

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

Your ViT is Secretly an Image Segmentation Model

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

Challenges and Paths Towards AI for Software Engineering

OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning

AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

A Refined Analysis of Massive Activations in LLMs

Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Model

Segment Any Motion in Videos

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback

SWI: Speaking with Intent in Large Language Models

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency

X^{2}-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction

4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding

On Large Multimodal Models as Open-World Image Classifiers