Minki Kang

Nardien's activity

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

upvoted 2 papers 4 days ago

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

Paper • 2606.04743 • Published 6 days ago • 40

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Paper • 2605.17873 • Published 22 days ago • 12

upvoted 2 papers 5 days ago

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 8 days ago • 102

Benchmarking Visual State Tracking in Multimodal Video Understanding

Paper • 2606.03920 • Published 7 days ago • 23

upvoted a paper 11 days ago

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published 12 days ago • 77

upvoted 2 papers 12 days ago

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

Paper • 2605.28775 • Published 13 days ago • 38

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published 13 days ago • 90

upvoted a paper 19 days ago

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

Paper • 2605.20258 • Published 22 days ago • 30

upvoted a paper 22 days ago

Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

Paper • 2605.15726 • Published 25 days ago • 34

upvoted a paper 25 days ago

PREPING: Building Agent Memory without Tasks

Paper • 2605.13880 • Published 29 days ago • 28

upvoted 2 papers about 2 months ago

OpenGame: Open Agentic Coding for Games

Paper • 2604.18394 • Published Apr 20 • 81

Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents

Paper • 2604.14004 • Published Apr 15 • 30

upvoted a paper 2 months ago

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

Paper • 2603.22341 • Published Mar 21 • 37

upvoted 2 papers 3 months ago

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents

Paper • 2603.09827 • Published Mar 10 • 30

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

Paper • 2602.17602 • Published Feb 19 • 56

upvoted 3 papers 4 months ago

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

Paper • 2601.23143 • Published Jan 30 • 39

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Paper • 2601.16746 • Published Jan 23 • 91

Self-Refining Video Sampling

Paper • 2601.18577 • Published Jan 26 • 25

upvoted 2 papers 5 months ago

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Paper • 2601.00664 • Published Jan 2 • 57

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models

Paper • 2512.22238 • Published Dec 23, 2025 • 30