Zhiyuan Ning's picture

42

Zhiyuan Ning

nzynzy

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 11 hours ago

Large-Scale Data Selection for Instruction Tuning

upvoted a paper about 11 hours ago

Multi-Turn Code Generation Through Single-Step Rewards

upvoted a paper 1 day ago

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

View all activity

Organizations

None yet

nzynzy's activity

upvoted 2 papers about 11 hours ago

Large-Scale Data Selection for Instruction Tuning

Paper • 2503.01807 • Published 2 days ago • 9

Multi-Turn Code Generation Through Single-Step Rewards

Paper • 2502.20380 • Published 6 days ago • 28

upvoted 2 papers 1 day ago

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Paper • 2503.01307 • Published 2 days ago • 23

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

Paper • 2503.00808 • Published 3 days ago • 48

upvoted 3 papers 6 days ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published 8 days ago • 62

Towards an AI co-scientist

Paper • 2502.18864 • Published 7 days ago • 38

TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding

Paper • 2502.19400 • Published 7 days ago • 41

upvoted a paper 8 days ago

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model

Paper • 2502.13449 • Published 15 days ago • 42

upvoted a paper 11 days ago

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Paper • 2502.14499 • Published 13 days ago • 171

upvoted 3 papers 12 days ago

Small Models Struggle to Learn from Strong Reasoners

Paper • 2502.12143 • Published 16 days ago • 28

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 14 days ago • 154

S*: Test Time Scaling for Code Generation

Paper • 2502.14382 • Published 13 days ago • 59

upvoted 3 papers 14 days ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published 17 days ago • 139

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Paper • 2502.08235 • Published 21 days ago • 54

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published 22 days ago • 46

upvoted 3 papers 19 days ago

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

Paper • 2502.06772 • Published 23 days ago • 20

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Paper • 2502.06703 • Published 23 days ago • 141

LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Paper • 2502.07374 • Published 22 days ago • 36

upvoted a paper 21 days ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published 26 days ago • 121

upvoted a paper 22 days ago

LIMO: Less is More for Reasoning

Paper • 2502.03387 • Published 28 days ago • 57