EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
Paper • 2606.27277 • Published • 2
mini
mini0999
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting upvoted a paper about 4 hours ago
How Post-Training Shapes Biological Reasoning Models upvoted a paper about 4 hours ago
OpenBioRQ: Unsolved Biomedical Research Questions for AgentsOrganizations
None yet
upvoted 20
papers about 4 hours ago
How Post-Training Shapes Biological Reasoning Models
Paper • 2606.16517 • Published • 3
OpenBioRQ: Unsolved Biomedical Research Questions for Agents
Paper • 2606.21959 • Published • 3
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
Paper • 2606.23835 • Published • 2
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
Paper • 2606.26299 • Published • 3
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Paper • 2606.27288 • Published • 3
Information-Aware KV Cache Compression for Long Reasoning
Paper • 2606.26875 • Published • 5
CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies
Paper • 2606.16613 • Published • 7
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Paper • 2606.26080 • Published • 6
Discretizing Reward Models
Paper • 2606.21795 • Published • 6
Hallucination in World Models is Predictable and Preventable
Paper • 2606.27326 • Published • 7
Confidence-Aware Tool Orchestration for Robust Video Understanding
Paper • 2606.26904 • Published • 9
PhysiFormer: Learning to Simulate Mechanics in World Space
Paper • 2606.27364 • Published • 8
In-Context World Modeling for Robotic Control
Paper • 2606.26025 • Published • 37
LISA: Likelihood Score Alignment for Visual-condition Controllable Generation
Paper • 2606.27192 • Published • 12
Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments
Paper • 2606.14397 • Published • 14
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Paper • 2606.26027 • Published • 14
Fast LeWorldModel
Paper • 2606.26217 • Published • 20
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
Paper • 2606.05622 • Published • 44
Trust Region On-Policy Distillation
Paper • 2606.01249 • Published • 45