Adam Lee

Abecid's activity

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

upvoted a paper 1 day ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 5 days ago • 120

upvoted 2 papers 10 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 13 days ago • 137

What Does Privileged Information Add to On-Policy Self-Distillation?

Paper • 2609.20612 • Published 13 days ago • 36

upvoted a paper 14 days ago

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Paper • 2609.11638 • Published 20 days ago • 702

upvoted a paper 15 days ago

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Paper • 2609.15973 • Published 16 days ago • 33

upvoted a paper 18 days ago

Programmable World Model

Paper • 2609.10540 • Published 21 days ago • 115

upvoted a paper 20 days ago

Causal Foundation Models

Paper • 2609.03003 • Published 28 days ago • 29

upvoted 2 papers 21 days ago

The Attention Triangle in Audio-Video Models

Paper • 2609.03586 • Published 27 days ago • 44

EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents

Paper • 2609.01281 • Published 29 days ago • 15

upvoted 3 papers 22 days ago

To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

Paper • 2608.05879 • Published Aug 29 • 9

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published 27 days ago • 54

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 27 days ago • 20

upvoted 3 papers 25 days ago

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

Paper • 2609.04196 • Published 27 days ago • 71

Principia: Relational Physics Tests for Video Models

Paper • 2609.04200 • Published 27 days ago • 18

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Paper • 2608.31100 • Published about 1 month ago • 42

upvoted an article 25 days ago

view article

Article

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

• 
• 
• +1

iamleonie, burtenshaw, sergiopaniego

•

27 days ago

• 139

upvoted a paper 26 days ago

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published 29 days ago • 222

upvoted an article 26 days ago

view article

Article

Training a coding model to paint watercolours with TRL and OpenEnv

• 

sergiopaniego

•

27 days ago

• 75

upvoted 2 papers 27 days ago

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published 28 days ago • 118

Dynamic Important Example Mining for Reinforcement Finetuning

Paper • 2608.29252 • Published Aug 29 • 5