Peking University

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

ShiyuHuang authored a paper 12 days ago

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

Skywalker0410 submitted a paper 12 days ago

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

Skywalker0410 submitted a paper 20 days ago

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation

View all activity

Papers

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation

View all Papers

authored a paper 4 days ago

Vision-Language Models Are Joint Denoisers in Robotic Action Generation

Paper • 2611.01215 • Published 8 days ago • 2

submitted a paper to Daily Papers 6 days ago

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

Paper • 2610.39276 • Published 11 days ago • 10

authored a paper 6 days ago

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

Paper • 2610.39276 • Published 11 days ago • 10

authored a paper 12 days ago

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

Paper • 2610.33079 • Published 19 days ago • 12

authored a paper 12 days ago

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

Paper • 2610.33079 • Published 19 days ago • 12

submitted a paper to Daily Papers 12 days ago

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

Paper • 2610.33079 • Published 19 days ago • 12

submitted a paper to Daily Papers 20 days ago

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation

Paper • 2609.22332 • Published 22 days ago • 18

authored a paper 21 days ago

Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels

Paper • 2607.26121 • Published Jul 28 • 1

authored 2 papers 25 days ago

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

Paper • 2602.05758 • Published 28 days ago • 10

RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes

Paper • 2610.11480 • Published Oct 8 • 4

authored a paper 25 days ago

AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding

Paper • 2610.16985 • Published 28 days ago • 12

authored a paper 25 days ago

AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding

Paper • 2610.16985 • Published 28 days ago • 12

submitted a paper to Daily Papers 25 days ago

AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding

Paper • 2610.16985 • Published 28 days ago • 12

submitted a paper to Daily Papers 25 days ago

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

Paper • 2602.05758 • Published 28 days ago • 10

submitted a paper to Daily Papers 26 days ago

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

Paper • 2610.17656 • Published 27 days ago • 19

authored 3 papers 26 days ago

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation

Paper • 2609.22332 • Published 22 days ago • 18

UniWAM: Unified World-Action Model

Paper • 2610.02054 • Published Oct 1 • 61

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Paper • 2609.39600 • Published Sep 30 • 34

authored a paper 26 days ago

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Paper • 2609.39600 • Published Sep 30 • 34

authored a paper 26 days ago

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published Sep 30 • 93