Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
V-CoLA: Vision Token Compression with Linear Attention
Hao Jiang, Yiru Mao, Tianpeng Bu +9
Vision-language models (VLMs) have demonstrated impressive capabilities but suffer from substantial computational overhead, as vision tokens dominate the input sequence. This motiv…
cs.CV2026
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
Tianpeng Bu, Xin Liu, Qihua Chen +7
While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation…