Visual-token compression for vision--language models is posed almost entirely as a selection problem: decide which tokens to keep and discard the rest. The criteria that work best rank tokens by the attention the language model pays them, which makes the ranking a function of the question being asked. That is invisible...
Hong-Bo Zhang, Zi-Hao Yang, Liu-Yang Song et al.· 0 citations
An agent that remembers what it did on a web page must decide when two pages count as the same. Memories built on observation similarity merge pages that look alike but behave differently, and GUIs are full of such pages: two tabs of one widget or two rows of one menu answer the same click differently. We define the me...
Hong-Bo Zhang, Liu-Yang Song, Quan-Quan Li et al.· 0 citations
This work proposes Visual Difference DeepStack (VD-DeepStack), which explicitly conditions language reasoning on query-reference visual differences on query-reference visual differences, and supports mitigating the visual comparison-reasoning gap through the joint design of comparison representations and their integrat...
Meng-Yang Zhao, Zhuo-Lin He, Hai-Yang Yu et al.· 1 citation
Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions. Existing agent memory systems, however, often reduce visual experiences into textual summaries or rely on static retrieve-then-reason pipelines, which are inefficient at query time an...
Jingyu Sun, Yang Lin, Yuyang Xue et al.· 0 citations
This method generates candidate responses from the target policy, evaluates helpfulness, factuality, and conciseness with rubric-specialized evaluators, applies a process-critic correction, and retains only high-consensus desirable or undesirable examples.
PreDiff-LM preserves causal attention within the observed prompt while allowing full bidirectional attention within the masked target, position hybrid attention as a complementary mechanism for adapting pretrained causal backbones, while making explicit the remaining quality and inference-efficiency gaps to optimized A...
TrajWiki is proposed, a trajectory-based memory framework for long-horizon conversational agents that improves long-horizon dialogue performance across both open-source and closed-source LLM backbones, while providing greater interpretability and diagnostic visibility into memory evolution, retrieval failures, and answ...
Jingyu Sun, Yuyang Xue, Ming-Yang Li 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.
