Peking University

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

77Hui authored a paper about 23 hours ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

laolida-w authored a paper 26 days ago

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

laolida-w authored a paper 26 days ago

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

View all activity

Papers

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

View all Papers

authored a paper about 23 hours ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 9 days ago • 83

authored 2 papers 26 days ago

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

Paper • 2510.18876 • Published Oct 21, 2025 • 37

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Paper • 2606.19534 • Published Jun 17 • 65

submitted a paper to Daily Papers about 2 months ago

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Paper • 2606.06155 • Published Jun 4 • 10

authored 4 papers about 2 months ago

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning

Paper • 2604.14922 • Published Apr 16 • 7

SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework

Paper • 2605.20373 • Published May 19

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Paper • 2606.06155 • Published Jun 4 • 10

A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation

Paper • 2601.11076 • Published Jan 16

submitted a paper to Daily Papers 2 months ago

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

Paper • 2605.07363 • Published May 8 • 12

submitted a paper to Daily Papers 4 months ago

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

Paper • 2604.01569 • Published Apr 2 • 14

submitted a paper to Daily Papers 5 months ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 60

submitted a paper to Daily Papers 6 months ago

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

Paper • 2601.21996 • Published Jan 29 • 5

submitted a paper to Daily Papers 6 months ago

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation

Paper • 2601.11258 • Published Jan 16 • 10

authored a paper 7 months ago

RecTok: Reconstruction Distillation along Rectified Flow

Paper • 2512.13421 • Published Dec 15, 2025 • 5

submitted a paper to Daily Papers 7 months ago

RecTok: Reconstruction Distillation along Rectified Flow

Paper • 2512.13421 • Published Dec 15, 2025 • 5

authored a paper 8 months ago

Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation

Paper • 2512.02457 • Published Dec 2, 2025 • 14

authored a paper 9 months ago

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

Paper • 2510.16888 • Published Oct 19, 2025 • 22

authored a paper 10 months ago

ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving

Paper • 2404.16771 • Published Dec 28, 2024 • 19

authored a paper 12 months ago

Tool-integrated Reinforcement Learning for Repo Deep Search

Paper • 2508.03012 • Published Aug 5, 2025 • 20

authored a paper about 1 year ago

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Paper • 2505.23606 • Published May 29, 2025 • 14