Shaobai Jiang

shaobaij's activity

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

upvoted a paper about 18 hours ago

GLM-OCR Technical Report

Paper • 2603.10910 • Published 5 days ago • 5

upvoted 3 papers about 20 hours ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Paper • 2603.12180 • Published 4 days ago • 57

Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights

Paper • 2603.12228 • Published 4 days ago • 8

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 4 days ago • 45

upvoted a paper 1 day ago

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 6 days ago • 105

upvoted 2 papers 2 days ago

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Paper • 2603.09906 • Published 6 days ago • 64

EvoSkill: Automated Skill Discovery for Multi-Agent Systems

Paper • 2603.02766 • Published 14 days ago • 1

upvoted 3 papers 5 days ago

How Far Can Unsupervised RLVR Scale LLM Training?

Paper • 2603.08660 • Published 7 days ago • 49

Scalable Training of Mixture-of-Experts Models with Megatron Core

Paper • 2603.07685 • Published 8 days ago • 1

OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning

Paper • 2603.08655 • Published 7 days ago • 3

upvoted a paper 6 days ago

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published 10 days ago • 105

upvoted 4 papers 7 days ago

AgentIR: Reasoning-Aware Retrieval for Deep Research Agents

Paper • 2603.04384 • Published 12 days ago • 3

NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches

Paper • 2603.06492 • Published 10 days ago • 2

Progressive Residual Warmup for Language Model Pretraining

Paper • 2603.05369 • Published 11 days ago • 33

Learning Personalized Agents from Human Feedback

Paper • 2602.16173 • Published 27 days ago • 9

upvoted 3 papers 8 days ago

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published 13 days ago • 114

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published 18 days ago • 80

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Paper • 2603.04257 • Published 12 days ago • 19

upvoted 2 papers 9 days ago

If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence

Paper • 2601.14351 • Published Jan 20 • 1

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Paper • 2602.06717 • Published Feb 6 • 72