Adam Lee

Abecid's activity

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

upvoted 2 papers about 6 hours ago

Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning

Paper • 2608.09926 • Published 5 days ago • 10

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Paper • 2608.13552 • Published 1 day ago • 31

upvoted 2 papers about 7 hours ago

Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

Paper • 2608.10708 • Published 4 days ago • 14

From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection

Paper • 2608.11562 • Published 3 days ago • 9

upvoted a paper about 8 hours ago

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation

Paper • 2608.13489 • Published 1 day ago • 79

upvoted a paper 1 day ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 4 days ago • 176

upvoted a paper 3 days ago

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Paper • 2608.03573 • Published 9 days ago • 51

upvoted a paper 4 days ago

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

Paper • 2608.07468 • Published 8 days ago • 103

upvoted 2 papers 5 days ago

Quo Vadis, World Modeling?

Paper • 2608.02713 • Published 11 days ago • 37

Scaling Properties of Text Conditioning in Visual Generation

Paper • 2607.29679 • Published 15 days ago • 38

upvoted 2 papers 6 days ago

InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Paper • 2608.02437 • Published 12 days ago • 67

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

Paper • 2608.05102 • Published 10 days ago • 65

upvoted a collection 6 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

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 4 days ago • 18

upvoted a paper 6 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 9 days ago • 94

upvoted a paper 7 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 8 days ago • 239

upvoted a paper 9 days ago

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

Paper • 2608.01628 • Published 12 days ago • 22

upvoted a paper 10 days ago

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 12 days ago • 58

upvoted 3 papers 11 days ago

Mental World Modeling

Paper • 2607.27201 • Published 17 days ago • 104

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

Paper • 2607.23802 • Published 20 days ago • 105

Meshy T2: Fast Native Mesh Generation with Flow Matching

Paper • 2607.28675 • Published 18 days ago • 56