Joel Wang

joelhenwang's activity

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

New activity in joelhenwang/OdinNext-138M-Base about 2 hours ago

Awesome Model

3

#1 opened about 13 hours ago by

Datdanboi25

updated 2 models about 2 hours ago

joelhenwang/OdinNext-138M-Instruct

Text Generation • 0.1B • Updated about 2 hours ago • 22 • 2

joelhenwang/OdinNext-138M-Base

Text Generation • 0.1B • Updated about 2 hours ago • 60 • 1

upvoted a paper about 5 hours ago

Why Muon Outperforms Adam: A Curvature Perspective

Paper • 2606.04662 • Published 7 days ago • 8

upvoted a paper about 15 hours ago

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Paper • 2606.09079 • Published 2 days ago • 42

upvoted 3 papers about 20 hours ago

OpenSkill: Open-World Self-Evolution for LLM Agents

Paper • 2606.06741 • Published 6 days ago • 24

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Paper • 2605.31264 • Published 12 days ago • 111

Mellum2 Technical Report

Paper • 2605.31268 • Published 12 days ago • 54

liked a model about 20 hours ago

ideogram-ai/ideogram-4-fp8

Text-to-Image • Updated 6 days ago • 5.92k • 438

upvoted 2 papers about 20 hours ago

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Paper • 2606.04703 • Published 7 days ago • 21

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Paper • 2606.03458 • Published 8 days ago • 59

upvoted 9 papers 1 day ago

Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation

Paper • 2606.02684 • Published 9 days ago • 16

MemTrain: Self-Supervised Context Memory Training

Paper • 2606.03197 • Published 8 days ago • 17

Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning

Paper • 2605.30039 • Published 12 days ago • 18

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Paper • 2606.06473 • Published 6 days ago • 19

ESPO: Early-Stopping Proximal Policy Optimization

Paper • 2605.29860 • Published 13 days ago • 19

Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging

Paper • 2606.01717 • Published 9 days ago • 21

MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection

Paper • 2605.30288 • Published 12 days ago • 22

Self-Distilled Policy Gradient

Paper • 2606.04036 • Published 8 days ago • 24

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

Paper • 2605.29796 • Published 13 days ago • 25