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 formalizes Observable Simulator Contract, a minimal contract that any action-conditioned physical simulator should satisfy: supplied actions must induce corresponding agent motion, and environment responses must be grounded in that realized motion.
P. Co, Sichen Hu, Chun-Xuan Jiao et al.· 1 citation
JarvisHub is introduced, a canvas-native creative agent harness for long-horizon multimodal creation, where agents can progressively plan, generate, revise, and organize multimodal projects while users remain able to inspect, guide, and intervene throughout the process.
DeepSearch-Evolve is presented, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools that enables scalable self-evolution for long-horizon web agents.
This work introduces Robo-Dopamine 2.0, a history- and OOD-aware process reward model with a pairwise prediction interface that combines history-conditioned pairwise rewards that use source-aligned reference panels for synthetic OOD queries and observed rollout history for online queries, while preserving the queried e...
Yijie Xu, Hao-Peng Jin, Run Zhou et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
