Joakim Lee

Reinforcement4All's activity

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

upvoted a paper 26 minutes ago

ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution

Paper • 2603.02510 • Published 2 days ago • 1

upvoted a paper 31 minutes ago

Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?

Paper • 2603.03202 • Published 1 day ago • 1

upvoted 3 papers 32 minutes ago

AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation

Paper • 2602.17100 • Published 14 days ago • 2

QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs

Paper • 2602.20629 • Published 9 days ago • 2

SciDER: Scientific Data-centric End-to-end Researcher

Paper • 2603.01421 • Published 3 days ago • 4

upvoted 5 papers 33 minutes ago

Chain of World: World Model Thinking in Latent Motion

Paper • 2603.03195 • Published 1 day ago • 5

Next Embedding Prediction Makes World Models Stronger

Paper • 2603.02765 • Published 1 day ago • 12

Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance

Paper • 2603.02175 • Published 2 days ago • 14

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published 4 days ago • 18

PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference

Paper • 2603.02479 • Published 2 days ago • 18

upvoted 2 papers 41 minutes ago

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models

Paper • 2603.01571 • Published 3 days ago • 28

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

Paper • 2603.03194 • Published 1 day ago • 46

upvoted 2 papers 43 minutes ago

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published 1 day ago • 49

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published 1 day ago • 73

upvoted 6 papers 1 day ago

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos

Paper • 2602.23543 • Published 6 days ago • 2

SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation

Paper • 2602.23359 • Published 6 days ago • 3

ArtLLM: Generating Articulated Assets via 3D LLM

Paper • 2603.01142 • Published 3 days ago • 3

CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production

Paper • 2603.01973 • Published 2 days ago • 5

Tool Verification for Test-Time Reinforcement Learning

Paper • 2603.02203 • Published 2 days ago • 4

Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training

Paper • 2603.02208 • Published 2 days ago • 4