We have 6 of 23 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
LAW, a closed-loop VLM--WAM framework that unifies language reasoning, action generation, and world modeling through semantic subtask progress, is presented, establishing a new open-source state of the art on RoboTwin.
As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memory reintroduces visual evidence during reasoning. We conduct a controlled analysis of visual memory along three axes: curation, organization, and access. We find that l...
Multimodal large language models (MLLMs) have demonstrated impressive performance in multimodal understanding, but processing large numbers of visual tokens results in high computational costs. While many methods have been proposed to reduce the number of visual tokens, most of them rely on heuristics and are prone to...
WorldEcho is introduced, which probes action following over a broader action distribution using visual integrity and SE(3) trajectory alignment, and WorldSync is proposed, which strengthens action following along three complementary axes: distributional coverage, representational grounding, and intervention-effect alig...
These findings show that effective pruning should preserve broad visual coverage before fusion and progressively refine the retained tokens as cross-modal evidence evolves during fusion, and propose STAR-Pro (STage-Wise Adaptive Token Reduction with Progressive Refinement), a training-free two-stage framework.
This work proposes SpIDER (Spatially Informed Dense Embedding Retrieval), a dense retrieval approach that integrates LLM-based reasoning with graph-based exploration of the codebase and introduces SpIDER-Bench, a graph-structured benchmark curated from SWEPolyBench, SWEBench-Verified and Multi-SWE-bench, spanning Pytho...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
