FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models
Paper • 2603.21315 • Published • 3
Joakim Lee
Reinforcement4All
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models upvoted a paper about 20 hours ago
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation upvoted a paper about 20 hours ago
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive RecipeOrganizations
None yet
upvoted 16
papers about 20 hours ago
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
Paper • 2603.21884 • Published • 4
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Paper • 2603.21972 • Published • 5
Agentic AI and the next intelligence explosion
Paper • 2603.20639 • Published • 7
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
Paper • 2603.18118 • Published • 12
REVERE: Reflective Evolving Research Engineer for Scientific Workflows
Paper • 2603.20667 • Published • 16
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
Paper • 2603.21383 • Published • 16
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
Paper • 2603.22117 • Published • 26
Manifold-Aware Exploration for Reinforcement Learning in Video Generation
Paper • 2603.21872 • Published • 33
Repurposing Geometric Foundation Models for Multi-view Diffusion
Paper • 2603.22275 • Published • 43
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
Paper • 2603.22057 • Published • 44
VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
Paper • 2603.22285 • Published • 50
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Paper • 2603.21065 • Published • 74
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
Paper • 2603.21986 • Published • 115
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 88
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
Paper • 2603.22212 • Published • 122
upvoted 4
papers 1 day ago
s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
Paper • 2603.14628 • Published • 3
Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
Paper • 2603.19470 • Published • 3
Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
Paper • 2603.19209 • Published • 5
AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
Paper • 2603.19005 • Published • 6