Joakim Lee

Reinforcement4All's activity

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

upvoted 12 papers 1 day ago

Specificity-aware reinforcement learning for fine-grained open-world classification

Paper • 2603.03197 • Published 3 days ago • 11

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

Paper • 2603.03823 • Published 3 days ago • 3

RIVER: A Real-Time Interaction Benchmark for Video LLMs

Paper • 2603.03985 • Published 2 days ago • 4

InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions

Paper • 2603.03646 • Published 3 days ago • 7

V_1: Unifying Generation and Self-Verification for Parallel Reasoners

Paper • 2603.04304 • Published 2 days ago • 11

Phi-4-reasoning-vision-15B Technical Report

Paper • 2603.03975 • Published 2 days ago • 15

CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

Paper • 2603.04291 • Published 2 days ago • 11

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Paper • 2603.04338 • Published 2 days ago • 19

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Paper • 2603.03447 • Published 3 days ago • 24

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published 3 days ago • 105

Heterogeneous Agent Collaborative Reinforcement Learning

Paper • 2603.02604 • Published 4 days ago • 136

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 2 days ago • 127

upvoted 8 papers 2 days ago

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

Paper • 2603.02510 • Published 4 days ago • 3

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

Paper • 2603.03202 • Published 3 days ago • 14

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

Paper • 2602.17100 • Published 16 days ago • 2

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

Paper • 2602.20629 • Published 11 days ago • 3

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

Paper • 2603.01421 • Published 5 days ago • 4

Chain of World: World Model Thinking in Latent Motion

Paper • 2603.03195 • Published 3 days ago • 6

Next Embedding Prediction Makes World Models Stronger

Paper • 2603.02765 • Published 4 days ago • 16

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

Paper • 2603.02175 • Published 4 days ago • 17