minbeomkim

mbkim's activity

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

upvoted a paper 11 days ago

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

Paper • 2609.18805 • Published 12 days ago • 66

upvoted a paper 26 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 28 days ago • 97

upvoted a paper 3 months ago

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Paper • 2606.29985 • Published Jun 29 • 19

upvoted a paper 5 months ago

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

Paper • 2605.14454 • Published May 14 • 5

upvoted 2 papers 6 months ago

ReflectCAP: Detailed Image Captioning with Reflective Memory

Paper • 2604.12357 • Published Apr 14 • 2

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published Mar 25 • 58

upvoted a paper 7 months ago

Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty

Paper • 2603.15500 • Published Mar 16 • 12

upvoted a paper 8 months ago

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

Paper • 2602.07918 • Published Feb 8 • 6

upvoted a paper 11 months ago

Drift: Decoding-time Personalized Alignments with Implicit User Preferences

Paper • 2502.14289 • Published Feb 20, 2025 • 1

upvoted a paper 12 months ago

FlowRL: Matching Reward Distributions for LLM Reasoning

Paper • 2509.15207 • Published Sep 18, 2025 • 119

upvoted a paper about 1 year ago

Critic-Guided Decoding for Controlled Text Generation

Paper • 2212.10938 • Published Dec 21, 2022 • 2