Search posts, papers, and topics
This paper introduces PhysVista, a new benchmark to evaluate the physical intelligence of Vision-Language Models (VLMs) using a closed perception-reasoning-assessment loop. Experiments reveal significant limitations in current VLMs' physical reasoning and plausibility assessment capabilities.
AnswerMap is a novel, training-free, black-box method for generating faithful spatial interpretability maps for Vision-Language Models (VLMs) directly from their output posteriors. It queries the VLM with image bands and yes/no relevance questions, demonstrating higher faithfulness than attention maps and enabling new applications like object localization and hallucination detection.
EditHero is a new benchmark for long‑horizon, part‑level 3D editing that supplies natural‑language instructions, geometry and texture targets, and a deterministic engine that produces the exact result after each edit. Using it, the authors show that bottom‑up LLM/VLM agents preserve unchanged parts better than top‑down non‑agentic methods, though they run slower (minutes per edit).
