SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
Paper • 2607.21553 • Published • 39
Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper about 15 hours ago
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation upvoted a paper about 17 hours ago
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models upvoted a paper about 17 hours ago
Dual Latent Memory in Vision-Language-Action Models for Robotic ManipulationOrganizations
None yet
upvoted a paper about 15 hours ago
upvoted 6
papers about 17 hours ago
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
Paper • 2607.03751 • Published • 20
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
Paper • 2607.07608 • Published • 57
OpenCoF: Learning to Reason Through Video Generation
Paper • 2607.08763 • Published • 29
Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process
Paper • 2607.03748 • Published • 41
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Paper • 2607.01793 • Published • 8
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Paper • 2607.00597 • Published • 31
upvoted 6
papers 2 days ago
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Paper • 2607.05804 • Published • 19
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Paper • 2607.04425 • Published • 73
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Paper • 2607.03451 • Published • 34
Perceptual Flow Matching for Few-Step Generative Modeling
Paper • 2607.03524 • Published • 19
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Paper • 2607.02461 • Published • 41
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Paper • 2607.04428 • Published • 19
upvoted 7
papers 3 days ago
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 39
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Paper • 2607.07386 • Published • 13
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Paper • 2607.02980 • Published • 83
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 407
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Paper • 2607.01232 • Published • 8
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Paper • 2607.02512 • Published • 238
AlayaWorld: Long-Horizon and Playable Video World Generation
Paper • 2607.06291 • Published • 91