Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems Paper • 2606.05985 • Published 14 days ago • 7
IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products Paper • 2606.14383 • Published 6 days ago • 2
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation Paper • 2606.18375 • Published 3 days ago • 3
Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness Paper • 2606.18874 • Published 1 day ago • 2
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games Paper • 2606.19338 • Published 1 day ago • 35
Guava: An Effective and Universal Harness for Embodied Manipulation Paper • 2606.18363 • Published 3 days ago • 22
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models Paper • 2606.17539 • Published 3 days ago • 12
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior Paper • 2606.18322 • Published 3 days ago • 14
Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding Paper • 2606.18101 • Published 3 days ago • 13
Native Active Perception as Reasoning for Omni-Modal Understanding Paper • 2606.19341 • Published 1 day ago • 9
Sumi: Open Uniform Diffusion Language Model from Scratch Paper • 2606.19005 • Published 1 day ago • 7
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks Paper • 2606.15872 • Published 4 days ago • 3