Shaobai Jiang

shaobaij's activity

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

upvoted 2 papers about 7 hours ago

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 10 days ago • 161

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models

Paper • 2605.08513 • Published May 8 • 16

upvoted 2 papers about 10 hours ago

Memory Attention

Paper • 2609.28399 • Published 9 days ago • 1

LLM Agents Can Easily Tamper With Their Own Traces

Paper • 2609.30266 • Published 8 days ago • 1

upvoted a paper about 11 hours ago

Learning Generalizable Behaviors for Terminal Agents

Paper • 2608.22631 • Published Aug 23 • 2

upvoted 5 papers 1 day ago

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

Paper • 2609.14306 • Published 19 days ago • 20

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 11 days ago • 219

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

Paper • 2609.19644 • Published 15 days ago • 3

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

Paper • 2507.16806 • Published Jul 22, 2025 • 8

Calibration as a First-Class Criterion in LLM Evaluation

Paper • 2609.26489 • Published 10 days ago • 4

upvoted 4 papers 2 days ago

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Paper • 2609.22000 • Published 14 days ago • 79

FrogNano: Training a 4B Coding Agent via Online Task Synthesis

Paper • 2609.07925 • Published 25 days ago • 7

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Paper • 2609.09153 • Published 24 days ago • 44

SlopShape: Identifying AI-Generated Commercial Web Content

Paper • 2609.15369 • Published 15 days ago • 1

upvoted 2 papers 3 days ago

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 18 days ago • 432

Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

Paper • 2609.17320 • Published 17 days ago • 4

upvoted 4 papers 4 days ago

Principia: Relational Physics Tests for Video Models

Paper • 2609.04200 • Published 29 days ago • 18

VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement

Paper • 2609.03153 • Published 30 days ago • 15

TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation

Paper • 2609.05266 • Published 28 days ago • 2

SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving

Paper • 2609.03602 • Published 29 days ago • 1