Shaobai Jiang

shaobaij's activity

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

upvoted 2 papers about 5 hours ago

Agentic Critical Training

Paper • 2603.08706 • Published 29 days ago • 14

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

Paper • 2603.11327 • Published 27 days ago • 9

upvoted 2 papers about 12 hours ago

ActionParty: Multi-Subject Action Binding in Generative Video Games

Paper • 2604.02330 • Published 5 days ago • 5

Therefore I am. I Think

Paper • 2604.01202 • Published 5 days ago • 28

upvoted a paper about 13 hours ago

Meta-Harness: End-to-End Optimization of Model Harnesses

Paper • 2603.28052 • Published 8 days ago • 14

upvoted a paper about 15 hours ago

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published 5 days ago • 38

upvoted 14 papers 1 day ago

FlashSampling: Fast and Memory-Efficient Exact Sampling

Paper • 2603.15854 • Published 22 days ago • 9

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation

Paper • 2603.10899 • Published 27 days ago • 7

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

Paper • 2603.12252 • Published 26 days ago • 12

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Paper • 2603.06577 • Published Mar 6 • 48

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

Paper • 2603.10145 • Published 28 days ago • 12

Exclusive Self Attention

Paper • 2603.09078 • Published 28 days ago • 3

Adaptive Loops and Memory in Transformers: Think Harder or Know More?

Paper • 2603.08391 • Published 27 days ago • 1

FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling

Paper • 2603.05451 • Published Mar 5 • 1

Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

Paper • 2603.05344 • Published Mar 5 • 7

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

Paper • 2603.11382 • Published 26 days ago • 1

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published 28 days ago • 43

AgentRx: Diagnosing AI Agent Failures from Execution Trajectories

Paper • 2602.02475 • Published Feb 2 • 1

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

Paper • 2603.10098 • Published 28 days ago • 3

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation

Paper • 2603.09723 • Published 28 days ago • 7