Shaobai Jiang

shaobaij's activity

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

upvoted a paper 16 minutes ago

Trees from Marginals: Autoregressive drafting with factorized priors

Paper • 2607.06763 • Published 5 days ago • 1

upvoted a paper about 1 hour ago

Native Video-Action Pretraining for Generalizable Robot Control

Paper • 2607.08639 • Published 3 days ago • 1

upvoted 3 papers about 4 hours ago

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 5 days ago • 89

Infinite Worlds with Versatile Interactions

Paper • 2607.07534 • Published 4 days ago • 29

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 4 days ago • 46

upvoted 2 papers about 5 hours ago

Vision Pretraining for Dense Spatial Perception

Paper • 2607.05247 • Published 6 days ago • 42

Gemma 4 Technical Report

Paper • 2607.02770 • Published 10 days ago • 57

upvoted a paper about 6 hours ago

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2606.15007 • Published 30 days ago • 19

upvoted 4 papers about 18 hours ago

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Paper • 2606.02373 • Published Jun 1 • 60

A Primer in Post-Training Reasoning Data: What We Know About How It Works

Paper • 2606.02113 • Published Jun 1 • 1

Learn from your own latents and not from tokens: A sample-complexity theory

Paper • 2605.27734 • Published May 26 • 3

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Paper • 2606.05080 • Published Jun 3 • 31

upvoted 2 papers about 19 hours ago

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Paper • 2605.30621 • Published May 28 • 23

Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence

Paper • 2606.01444 • Published May 31 • 1

upvoted 2 papers about 20 hours ago

LLM-as-a-Verifier: A General-Purpose Verification Framework

Paper • 2607.05391 • Published 6 days ago • 14

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs

Paper • 2607.04371 • Published 7 days ago • 5

upvoted 3 papers 2 days ago

PACE: A Proxy for Agentic Capability Evaluation

Paper • 2607.02032 • Published 10 days ago • 18

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning

Paper • 2607.02509 • Published 10 days ago • 2

OpenJarvis: Personal AI, On Personal Devices

Paper • 2605.17172 • Published May 16 • 1

upvoted a paper 4 days ago

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Paper • 2605.25624 • Published May 25 • 35