MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 187
Xiaosen Zheng
xszheng2020
AI & ML interests
Code AI and Data-Centric AI.
Recent Activity
liked a model about 9 hours ago
nvidia/nemotron-climb-fasttext-classifiers liked a dataset 8 days ago
princeton-nlp/SWE-bench_oracle liked a model 17 days ago
ricdomolm/mini-coder-1.7bOrganizations
upvoted a paper 2 months ago
upvoted an article 5 months ago
Article
Agents vs. Workflows
VirtualOasis
• • 6 upvoted a paper 5 months ago
upvoted a paper 6 months ago
upvoted a paper 7 months ago
upvoted 6
papers 8 months ago
Learning to Reason as Action Abstractions with Scalable Mid-Training RL
Paper • 2509.25810 • Published • 6
On Predictability of Reinforcement Learning Dynamics for Large Language Models
Paper • 2510.00553 • Published • 9
GEM: A Gym for Agentic LLMs
Paper • 2510.01051 • Published • 92
Muon Outperforms Adam in Tail-End Associative Memory Learning
Paper • 2509.26030 • Published • 20
Variational Reasoning for Language Models
Paper • 2509.22637 • Published • 69
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
Paper • 2509.22638 • Published • 70
upvoted a collection 8 months ago
upvoted 3
papers 9 months ago
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 84
TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training
Paper • 2508.17677 • Published • 14
CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Paper • 2502.07316 • Published • 50
upvoted 2
collections 10 months ago
upvoted 3
papers 10 months ago