Peking University

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Skywalker0410 authored a paper 2 days ago

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

Skywalker0410 authored a paper 2 days ago

RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes

ShiyuHuang authored a paper 2 days ago

AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding

View all activity

Papers

Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

View all Papers

PKU 's papers 11

Submitted by

Jiahao Meng

Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence

PKU

Peking University

Submitted by

Qize Yu

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

PKU

Peking University

2

Submitted by

Zhifei Yang

AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation

PKU

Peking University

2

Submitted by

Chengqian Ma

Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue

PKU

Peking University

2

Submitted by

Jianhui Chen

From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution

PKU

Peking University

Submitted by

mengfanxu

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

PKU

Peking University

2

Submitted by

Jiahao Meng

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

PKU

Peking University

Submitted by

Feng Chaoran

Enhancing Spatial Understanding in Image Generation via Reward Modeling

PKU

Peking University

ProAct: A Dual-System Framework for Proactive Embodied Social Agents

PKU

Peking University

Submitted by

Jianhui Chen

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

PKU

Peking University

Submitted by

Stanley Tang

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation

PKU

Peking University

3