Submitted by AIcell 18 Guava: An Effective and Universal Harness for Embodied Manipulation · 8 authors 1
Submitted by JingyuanHuang 11 Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding University of Georgia 1
Submitted by jiyatai 10 Reinforcing Dual-Path Reasoning in Spatial Vision Language Models University of Hong Kong 3 1
Submitted by adamdad 10 SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior The Hong Kong Polytechnic University 3 1
Submitted by harryhsing 5 Native Active Perception as Reasoning for Omni-Modal Understanding Qwen 9 1
Submitted by ChrisDing1105 4 Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games Intern Large Models 1 1
Submitted by cedzhang 1 Learning User Simulators with Turing Rewards Massachusetts Institute of Technology 1 1
Submitted by alphadl 1 IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products 1688 multimodal & industrial AI 3 1
Submitted by taesiri - Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness · 18 authors 12
Submitted by taesiri - PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation · 28 authors
AIcell
