Recent advances in Vision-Language Models (VLMs) have led to rapid progress in video understanding across a wide range of benchmark tasks. However, existing evaluations largely focus on short-term reasoning, failing to assess a critical capability: maintaining cumulative temporal consistency over extended time horizons...
Leon D. Mayer, Lucas Luttner, P. Godau et al.· 0 citations
This work proposes DenseTRF, a self-supervised representation adaptation framework based on texture-centric attention that leverages slot attention to learn texture-aware representations that capture invariant visual structures and significantly improves robustness to domain shifts.
Gui-Qiu Liao, Matjaž Jogan, Daniel A. Hashimoto· arXiv.org· 0 citations
This work focuses on domains where images differ substantially from common image datasets and additional data are expensive to obtain, and evaluates the downstream classifier performance improvements yielded by two schools of generative sparse data extension: distribution modeling and sample perturbation.
Edward Zhang, Marcel Hussing, Tanay Tandon et al.· 0 citations
Slot2Text, a dual-mode surgical MLLM that replaces dense representations of visual input with a compact set of regions encoded as slot latents, establishes compact slot latents as an efficient default visual interface for surgical MLLMs, with grounded reasoning invoked when greater spatial traceability is required.
Guiqiu Liao, M. Jogan, Daniel A. Hashimoto· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
