RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Paper • 2606.29538 • Published • 139
🏗️ Building on HF
Adarsh Zolekar
adarshzolekar
AI & ML interests
Passionate about AI & ML, Deep Learning and related AI domains. Exploring models, datasets and applications while contributing to the Hugging Face community.
Recent Activity
liked a dataset 5 days ago
HuggingFaceFW/fineweb liked a dataset 5 days ago
wikimedia/wikipediaOrganizations
upvoted a paper 5 days ago
upvoted 2
papers 22 days ago
upvoted 3
papers about 1 month ago
upvoted 4
papers about 2 months ago
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Paper • 2606.02437 • Published • 240
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Paper • 2605.30611 • Published • 252
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 433
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 262
upvoted 3
papers 2 months ago
upvoted 5
papers 3 months ago
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Paper • 2605.03849 • Published • 129
Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
Paper • 2604.19748 • Published • 253
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 243
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 639
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 510
upvoted 2
papers 4 months ago