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...
Ting-Hao Wang, Yi-Chen Guo, Qi-Zhe Zhang et al.· 0 citations
Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an unverified assumption: generated futures faithfully reflect arbitrary valid actions. Existing benchmarks are typically confined to expert demonstrations, leaving off-exp...
Si-Xiang Chen, Jia-Ming Liu, Ji-Xin Wu et al.· 0 citations
Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose substantial computational overhead, motivating training-free visual token pruning. In this work, we conduct two complementary analyses of visual token pruning. First, we measu...
Yi-Chen Guo, Tinghao Wang, Qizhe Zhang et al.· 0 citations
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...
Shravan Chaudhari, Rahul Thomas Jacob, Mononito Goswami et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
