Zhenyi Shen's picture

Zhenyi Shen

zen-E

·

https://www.zhenyishen.com/

AI & ML interests

LLM Reasoning

Recent Activity

updated a model 4 days ago

zen-E/off-policy_student-qwen3-1b-base_teacher-qwen25-math-1b_math_e1

published a model 4 days ago

zen-E/off-policy_student-qwen3-1b-base_teacher-qwen25-math-1b_math_e1

updated a model 8 days ago

zen-E/grpo_nokl_qwen3_1b_e20_last_ckpt

View all activity

Organizations

None yet

upvoted 2 papers 24 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 187

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning

Paper • 2505.16022 • Published May 21 • 4

upvoted a paper 27 days ago

SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space

Paper • 2511.20102 • Published Nov 25 • 26

upvoted a paper 29 days ago

DeepSeek-OCR: Contexts Optical Compression

Paper • 2510.18234 • Published Oct 21 • 84

upvoted a paper 30 days ago

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Paper • 2511.08892 • Published Nov 12 • 201

upvoted 2 papers about 1 month ago

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance

Paper • 2510.03528 • Published Oct 3 • 17

SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation

Paper • 2412.13649 • Published Dec 18, 2024 • 21

upvoted an article about 2 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

+21

Jul 8

•

739

upvoted a paper 2 months ago

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

Paper • 2510.11052 • Published Oct 13 • 51

upvoted 2 papers 4 months ago

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

Paper • 2508.19827 • Published Aug 27 • 33

Direct Preference Optimization Using Sparse Feature-Level Constraints

Paper • 2411.07618 • Published Nov 12, 2024 • 17

upvoted 3 papers 5 months ago

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Paper • 2508.07407 • Published Aug 10 • 98

Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation

Paper • 2508.05909 • Published Aug 8 • 21

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Paper • 2502.21074 • Published Feb 28 • 4