Dylan PRO

shizhuo2's activity

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

upvoted 2 papers 24 minutes ago

MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

Paper • 2610.21091 • Published 10 days ago • 3

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

Paper • 2610.27450 • Published 5 days ago • 22

upvoted a paper 18 days ago

MiniCorp: The Last Mile of the AI Agent Firm

Paper • 2610.05912 • Published 20 days ago • 39

upvoted 2 papers 25 days ago

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published 28 days ago • 38

Learning from Teacher Continuations at Student States

Paper • 2609.36246 • Published 27 days ago • 41

upvoted a paper 2 months ago

Modular Cognitive Architecture Emerges in Large Language Models

Paper • 2608.13567 • Published Jun 27 • 17

upvoted a paper 3 months ago

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published Jul 30 • 193

upvoted a paper 4 months ago

Trimming the Long-Tail of Visual World Modeling Evaluation

Paper • 2606.24256 • Published Jun 23 • 41

upvoted 3 papers 5 months ago

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

Paper • 2605.26029 • Published May 28 • 14

Code as Agent Harness

Paper • 2605.18747 • Published May 18 • 226

Useful Memories Become Faulty When Continuously Updated by LLMs

Paper • 2605.12978 • Published May 13 • 19

upvoted 2 papers 8 months ago

Large Language Model Reasoning Failures

Paper • 2602.06176 • Published Feb 5 • 12

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Paper • 2602.07276 • Published Feb 7 • 11

upvoted a paper 9 months ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published Feb 1 • 45

upvoted a paper 10 months ago

Adaptation of Agentic AI

Paper • 2512.16301 • Published Dec 18, 2025 • 87

upvoted a paper 11 months ago

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Paper • 2511.21689 • Published Nov 26, 2025 • 129

upvoted a collection over 1 year ago

Enigmata

Collection

Resources for the Enigmata Project: https://seed-enigmata.github.io. • 4 items • Updated Mar 2 • 3

upvoted a paper over 1 year ago

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published May 30, 2025 • 146

upvoted a collection over 1 year ago

long-cot-dataset

Collection

14 items • Updated Mar 17 • 14

upvoted a paper over 1 year ago

Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarsity

Paper • 2502.11901 • Published Feb 17, 2025 • 6