Boyu Chen

boyuboyu94's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

Paper • 2609.39490 • Published 10 days ago • 27

upvoted 2 papers 4 days ago

RPTune: Learned Context Curation for LLM Catalog Search

Paper • 2610.00964 • Published 9 days ago • 37

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

Paper • 2610.00906 • Published 9 days ago • 83

upvoted a paper 5 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 11 days ago • 425

upvoted a paper 6 days ago

WorldAttention: An Efficient Attention Architecture for Interactive Video World Models

Paper • 2609.34606 • Published 12 days ago • 50

upvoted a paper 12 days ago

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published 17 days ago • 56

upvoted a paper 15 days ago

Recursive self-improvement of AI research agents

Paper • 2609.26457 • Published 18 days ago • 27

upvoted 7 papers 17 days ago

Learning Foresight without Explicit Trajectories for 3D Diffusion Policies

Paper • 2609.20669 • Published 23 days ago • 9

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published Sep 4 • 119

Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models

Paper • 2609.21094 • Published 23 days ago • 6

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 22 days ago • 151

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 479

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

Paper • 2609.21749 • Published 22 days ago • 19

DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation

Paper • 2609.18620 • Published 23 days ago • 24

upvoted a paper 18 days ago

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Paper • 2609.17653 • Published 25 days ago • 45

upvoted 2 papers 19 days ago

Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training

Paper • 2609.14306 • Published 27 days ago • 20

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published 25 days ago • 559

upvoted a paper 20 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 25 days ago • 147

upvoted a paper 22 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 376

upvoted a paper 23 days ago

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Paper • 2609.11638 • Published about 1 month ago • 656