Joakim Lee

Reinforcement4All's activity

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

upvoted a paper about 14 hours ago

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs

Paper • 2512.06776 • Published 3 days ago • 3

upvoted 2 papers about 19 hours ago

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

Paper • 2512.07951 • Published 2 days ago • 39

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Paper • 2512.08153 • Published 2 days ago • 4

upvoted 7 papers 1 day ago

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

Paper • 2512.07831 • Published 2 days ago • 15

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

Paper • 2512.07783 • Published 2 days ago • 25

LongCat-Image Technical Report

Paper • 2512.07584 • Published 2 days ago • 15

EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing

Paper • 2512.06065 • Published 5 days ago • 23

Voxify3D: Pixel Art Meets Volumetric Rendering

Paper • 2512.07834 • Published 2 days ago • 35

Unified Video Editing with Temporal Reasoner

Paper • 2512.07469 • Published 2 days ago • 40

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

Paper • 2512.07525 • Published 2 days ago • 51

upvoted 5 papers 2 days ago

AI & Human Co-Improvement for Safer Co-Superintelligence

Paper • 2512.05356 • Published 6 days ago • 8

Self-Improving VLM Judges Without Human Annotations

Paper • 2512.05145 • Published 8 days ago • 15

SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

Paper • 2512.05905 • Published 5 days ago • 17

EditThinker: Unlocking Iterative Reasoning for Any Image Editor

Paper • 2512.05965 • Published 5 days ago • 36

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published 8 days ago • 60

upvoted 2 papers 4 days ago

LATTICE: Democratize High-Fidelity 3D Generation at Scale

Paper • 2512.03052 • Published 17 days ago • 9

NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation

Paper • 2512.05106 • Published 6 days ago • 15

upvoted 3 papers 6 days ago

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Paper • 2512.04678 • Published 6 days ago • 38

Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

Paper • 2512.04987 • Published 6 days ago • 71

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling

Paper • 2512.03000 • Published 8 days ago • 34