Senqiao Yang

Senqiao's activity

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

upvoted 8 papers 6 days ago

Native Action-Prior Learning from Videos for World Action Models

Paper • 2610.03391 • Published 10 days ago • 88

On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training

Paper • 2609.36659 • Published 13 days ago • 87

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 10 days ago • 103

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

Paper • 2609.38839 • Published 12 days ago • 125

MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation

Paper • 2609.38078 • Published 13 days ago • 114

Does Learning Protein Folding Generalize to Broader Reasoning?

Paper • 2609.38879 • Published 12 days ago • 62

Octrees as an Explicit 3D Language

Paper • 2610.02388 • Published 11 days ago • 17

World Action Modeling with Progressive Visual Planning

Paper • 2610.02508 • Published 11 days ago • 97

upvoted 2 papers about 1 month ago

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

Paper • 2609.00188 • Published Aug 31 • 54

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

Paper • 2608.27550 • Published Aug 27 • 83

upvoted a collection about 1 month ago

VLAct

Collection

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models • 12 items • Updated Aug 31 • 3

upvoted a paper about 2 months ago

StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding

Paper • 2608.16320 • Published Aug 17 • 9

upvoted a collection 2 months ago

Mage

Collection

A family of lightweight multimodal models, including understanding and generation. • 8 items • Updated Jul 26 • 30

upvoted 2 papers 2 months ago

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

Paper • 2608.05703 • Published Aug 6 • 17

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published Jul 27 • 37

upvoted 2 papers 3 months ago

SciForma: Structure-Faithful Generation of Scientific Diagrams

Paper • 2607.18091 • Published Jul 20 • 25

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published Jul 21 • 78

upvoted 2 papers 5 months ago

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Paper • 2605.20342 • Published May 19 • 31

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published May 18 • 117

upvoted a paper 6 months ago

FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing

Paper • 2604.22586 • Published Apr 24 • 15