Byeong Hun Bang

bangpro's activity

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

upvoted a paper 5 days ago

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

Paper • 2610.37386 • Published 6 days ago • 25

upvoted a paper 6 days ago

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

Paper • 2610.32195 • Published 10 days ago • 43

authored a paper 7 days ago

Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay

Paper • 2610.27954 • Published 13 days ago • 1

upvoted a paper 25 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 26 days ago • 44

upvoted a paper 26 days ago

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Paper • 2610.05140 • Published 29 days ago • 40

upvoted 4 papers about 1 month ago

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

Paper • 2609.39982 • Published Sep 30 • 97

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

Paper • 2609.40340 • Published Sep 30 • 94

Follow the Entities: A Corpus Map for Agentic Search

Paper • 2609.37226 • Published Sep 29 • 69

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

Paper • 2609.34327 • Published Sep 28 • 40

upvoted a paper 4 months ago

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published Jun 23 • 166

upvoted 4 papers 5 months ago

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Paper • 2606.04743 • Published Jun 3 • 47

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published May 28 • 78

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published May 27 • 90

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Paper • 2605.28775 • Published May 27 • 35

upvoted 2 papers 6 months ago

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Paper • 2605.20258 • Published May 18 • 30

PREPING: Building Agent Memory without Tasks

Paper • 2605.13880 • Published May 11 • 28

upvoted a paper 7 months ago

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

Paper • 2603.22341 • Published Mar 21 • 37

liked a model 8 months ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated Nov 4, 2025 • 2.06M • • 3.46k

upvoted a paper 8 months ago

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

Paper • 2602.17602 • Published Feb 19 • 56

liked a model 9 months ago

Qwen/Qwen3-4B-Thinking-2507-FP8

Text Generation • 4B • Updated Aug 6, 2025 • 30.6k • 76