Training-free visual-token pruning often uses token importance, redundancy, or related selection criteria as proxies for safe removal. We show that these signals alone do not fully characterize removability, which is conditioned on both representation depth and the surrounding deletion set. Controlled interventions dem...
Sheng-Li He, Yong-Chao Liang, Rou-Meng He et al.· 0 citations
QCPruner fuses two cross-modal cues into utility and applies it to both visual targets and candidate representatives within visual-affinity-based coverage, which achieves the highest average relative performance among evaluated complete-system pruning methods at every reported token budget.
Sheng-Li He, Yong-Chao Liang, Rou-Meng He et al.· 1 citation· ⚡1
This work proposes Adaptive Evidential Multimodal Representation Learning (AEMRL), a framework aligned with this multi-level view of uncertainty that consistently enhances task accuracy, reduces calibration error, and improves robustness to noise, semantic conflict, and missing modalities.
Yu-Peng Han, Kai Zhang, Xian-Quan Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
CAT is introduced, a paradigm in which the agent writes Playwright code to drive the browser, gathers feedback, and autonomously explores web applications to uncover bugs, revealing a clear gap between current VLM capabilities and the demands of real-world testing in AI web development.
Bin Hong, Zhen-Chao Zhang, Ji-Yuan He et al.· 0 citations
Meta-Task is proposed, a framework that redefines terminal task synthesis as a Terminal-Bench-format task itself: an agent operates within a real container environment to iteratively generate, execute, and verify tasks, so that synthesized components are checked for internal consistency and executability within the gen...
Zhi-Hong Pan, Ji-Yuan He, Kai Zhang et al.· arXiv.org· 1 citation
ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings, starts from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent, and introduces three key designs.
Zhongyuan Peng, Dan Huang, Chuyu Zhang et al.· arXiv.org· 3 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
