Chanuk Lee

tally0818's activity

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

upvoted a paper 4 days ago

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

Paper • 2610.37386 • Published 5 days ago • 24

upvoted a paper 5 days ago

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

Paper • 2610.32195 • Published 9 days ago • 42

upvoted a paper 12 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 16 days ago • 56

upvoted a paper 13 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 19 days ago • 153

upvoted a paper 18 days ago

AutoEnvScaling: Automating the Data Flywheel with Terminal Agents

Paper • 2610.14163 • Published 23 days ago • 13

upvoted a paper 19 days ago

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper • 2610.13166 • Published 23 days ago • 147

upvoted a paper 23 days ago

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Paper • 2610.11959 • Published 24 days ago • 89

upvoted a paper 24 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 25 days ago • 44

upvoted a paper 25 days ago

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Paper • 2610.05140 • Published 28 days ago • 41

upvoted 11 papers about 1 month ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published Sep 30 • 119

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Paper • 2609.40340 • Published Sep 30 • 112

Follow the Entities: A Corpus Map for Agentic Search

Paper • 2609.37226 • Published Sep 29 • 79

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published Sep 16 • 47

FrogNano: Training a 4B Coding Agent via Online Task Synthesis

Paper • 2609.07925 • Published Sep 7 • 8

Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

Paper • 2609.34327 • Published Sep 28 • 40

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Paper • 2609.33781 • Published Sep 27 • 46

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL

Paper • 2602.03773 • Published Feb 3 • 15

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published Sep 7 • 69

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published Sep 8 • 69

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 35