Shaobai Jiang

shaobaij's activity

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

upvoted 2 papers about 18 hours ago

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

Paper • 2603.18886 • Published 6 days ago • 4

Hyperagents

Paper • 2603.19461 • Published 6 days ago • 32

upvoted a paper about 23 hours ago

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Paper • 2603.19312 • Published 12 days ago • 4

upvoted 8 papers 3 days ago

AutoHarness: improving LLM agents by automatically synthesizing a code harness

Paper • 2603.03329 • Published Feb 10 • 2

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

Paper • 2603.13398 • Published 14 days ago • 145

Mixture-of-Depths Attention

Paper • 2603.15619 • Published 9 days ago • 77

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

Paper • 2603.19228 • Published 6 days ago • 64

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published 6 days ago • 50

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

Paper • 2603.18429 • Published 7 days ago • 24

Alignment Makes Language Models Normative, Not Descriptive

Paper • 2603.17218 • Published 8 days ago • 46

Efficient Reasoning with Balanced Thinking

Paper • 2603.12372 • Published 13 days ago • 141

upvoted 2 papers 4 days ago

Mamba-3: Improved Sequence Modeling using State Space Principles

Paper • 2603.15569 • Published 9 days ago • 6

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published 6 days ago • 58

upvoted a paper 5 days ago

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published 13 days ago • 90

upvoted 2 papers 8 days ago

Temporal Straightening for Latent Planning

Paper • 2603.12231 • Published 13 days ago • 2

P-EAGLE: Parallel-Drafting EAGLE with Scalable Training

Paper • 2602.01469 • Published Feb 1 • 3

upvoted 3 papers 9 days ago

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

Paper • 2603.08640 • Published 16 days ago • 1

Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet

Paper • 2603.08163 • Published 16 days ago • 5

CHMv2: Improvements in Global Canopy Height Mapping using DINOv3

Paper • 2603.06382 • Published 19 days ago • 1

upvoted a paper 10 days ago

GLM-OCR Technical Report

Paper • 2603.10910 • Published 14 days ago • 7