Recent advancements in multimodal diffusion language models (MDLMs) have exhibited strong global modeling capabilities through iterative refinement. We observe that mask uncertainty follows an overall downward trend during iterative denoising, while a few denoising steps exhibit localized entropy spikes closely associa...
Zhong-Xing Xu, Zhong-Hua Wang, Zhe Qian et al.· 0 citations
Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiveness depends on whether models can successfully act on the guidance provided by their harnesses. However, we find that harness benefits are not uniform across model capabil...
Zhi-Hao Yang, Haojin Wang, Jun-Cheng Wu et al.· 0 citations
Language models as Research World Models (RWMs), which predict the outcomes of candidate interventions across research environments, are investigated andlations across 13 language models used as RWMs show that adding research knowledge can improve intervention ranking more than changing models or increasing reasoning e...
Zi-Jun Wang, Ze-Wen Liu, Min-hua Lin et al.· 3 citations
This work presents VERA, which builds precise and verifiable environments at scale and lets agents evolve on them, and creates a verifier which gates model checkpoints and harness edits using explicit development-set acceptance criteria.
Jun-Qi Liu, Yong-Yang Pan, Zhuo-Song Jiang et al.· 1 citation
Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images. While token pruning has emerged as a promising approach to reduce the inference cost of MLLMs, existing methods typically reassign position embeddings to the retained t...
Ya-Hong Wang, Zhang-Kai Ni, Jun-Cheng Wu et al.· 0 citations
Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi-stage and data-sensitive, while expert trajectories remain scarce and difficult to share. Structured benchmarks can localize failures through stage-level rubrics, but...
Junqi Liu, Yu-Fan He, Ye-Xiao He et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.