Adam Lee

Abecid's activity

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

upvoted a collection about 1 hour ago

recursive task synthesis

Collection

CC BY 4.0 datasets and SFT/RL checkpoints for recursive task synthesis; base-model and third-party terms still apply. • 6 items • Updated 1 day ago • 13

upvoted a paper about 2 hours ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 2 days ago • 73

upvoted a paper about 10 hours ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 3 days ago • 213

liked a model 2 days ago

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated 1 day ago • 18.1k • • 3k

upvoted a paper 3 days ago

Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations

Paper • 2608.01628 • Published 5 days ago • 22

upvoted 2 papers 4 days ago

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 5 days ago • 58

Mental World Modeling

Paper • 2607.27201 • Published 10 days ago • 102

upvoted 4 papers 5 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 13 days ago • 100

Meshy T2: Fast Native Mesh Generation with Flow Matching

Paper • 2607.28675 • Published 11 days ago • 53

QQWorld: Quantile-Quantile Matching for World Model Regularization

Paper • 2607.28415 • Published 9 days ago • 30

Enhancing Rubric-based RL via Self-Distillation

Paper • 2607.18082 • Published 18 days ago • 25

upvoted 2 papers 6 days ago

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published 9 days ago • 181

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Paper • 2607.25895 • Published 11 days ago • 156

upvoted 2 papers 7 days ago

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Paper • 2607.27372 • Published 10 days ago • 19

StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation

Paper • 2607.26754 • Published 10 days ago • 18

upvoted 2 papers 9 days ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published 11 days ago • 83

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Paper • 2607.26057 • Published 11 days ago • 33

upvoted a paper 12 days ago

Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering

Paper • 2607.21848 • Published 16 days ago • 9

upvoted 2 papers 16 days ago

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 18 days ago • 77

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Paper • 2607.18722 • Published 18 days ago • 35