Peking University

university

https://www.pku.edu.cn/

Activity Feed Request to join this org

AI & ML interests

nlu

Recent Activity

zbhpku submitted a paper 2 days ago

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

xishushu submitted a paper 6 days ago

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

zyh200727 submitted a paper 11 days ago

PEARL: Personalized Streaming Video Understanding Model

View all activity

Papers

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

View all Papers

submitted a paper to Daily Papers 2 days ago

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published 9 days ago • 153

submitted a paper to Daily Papers 6 days ago

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models

Paper • 2603.22782 • Published 12 days ago • 18

submitted a paper to Daily Papers 11 days ago

PEARL: Personalized Streaming Video Understanding Model

Paper • 2603.20422 • Published 16 days ago • 40

submitted a paper to Daily Papers 17 days ago

Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models

Paper • 2603.15618 • Published 20 days ago • 21

submitted a paper to Daily Papers 26 days ago

MWM: Mobile World Models for Action-Conditioned Consistent Prediction

Paper • 2603.07799 • Published 27 days ago

submitted a paper to Daily Papers about 1 month ago

StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation

Paper • 2602.16915 • Published Feb 18

submitted 4 papers to Daily Papers about 2 months ago

MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation

Paper • 2602.14534 • Published Feb 16 • 3

Light4D: Training-Free Extreme Viewpoint 4D Video Relighting

Paper • 2602.11769 • Published Feb 12 • 2

Code2Worlds: Empowering Coding LLMs for 4D World Generation

Paper • 2602.11757 • Published Feb 12 • 4

GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning

Paper • 2602.04315 • Published Feb 4 • 1

submitted a paper to Daily Papers 2 months ago

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published Feb 2 • 46

submitted a paper to Daily Papers 3 months ago

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Paper • 2601.10061 • Published Jan 15 • 32

submitted a paper to Daily Papers 3 months ago

AnyDepth: Depth Estimation Made Easy

Paper • 2601.02760 • Published Jan 6 • 10

submitted a paper to Daily Papers 3 months ago

DocDancer: Towards Agentic Document-Grounded Information Seeking

Paper • 2601.05163 • Published Jan 8 • 7

submitted a paper to Daily Papers 3 months ago

MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics

Paper • 2601.02075 • Published Jan 5 • 8

submitted a paper to Daily Papers 3 months ago

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Paper • 2512.21004 • Published Dec 24, 2025 • 13

submitted 2 papers to Daily Papers 4 months ago

VABench: A Comprehensive Benchmark for Audio-Video Generation

Paper • 2512.09299 • Published Dec 10, 2025 • 8

Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

Paper • 2512.12675 • Published Dec 14, 2025 • 41

submitted a paper to Daily Papers 4 months ago

DragMesh: Interactive 3D Generation Made Easy

Paper • 2512.06424 • Published Dec 6, 2025 • 1

submitted a paper to Daily Papers 4 months ago

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs

Paper • 2512.06776 • Published Dec 7, 2025 • 26