Visual latent reasoning compresses rendered derivations into compact intermediate states, reducing textual reasoning overhead. Existing approaches differ in how they represent these states: continuous methods avoid vocabulary constraints, whereas discrete methods improve accuracy through quantization into a finite code...
Zhao-Yang Wei, Bo-Wen Jiang, Yan-Chao Hao et al.· 0 citations
Multimodal large language models (MLLMs) have advanced image geolocalization mainly by improving how they reason about geographic cues. How that reasoning isdecoded into coordinates, however, has lagged behind. Predicting a place name for a geocoding API is discrete and lossy: it ignores image evidence and collapses mu...
Zhi-Yang Dou, Xumeng Han, Feng-De Peng et al.· 0 citations
Video-HolmesV2 is presented, a novel benchmark designed for Deep Audio-Visual Coupling that enforces an Evidence-Based Evaluation, requiring models to justify answers with precise spatio-temporal audio-visual evidence, thereby reducing confounding effects of guessing and hallucinated evidence.
Zhao-Yang Wei, Zi-Peng Wang, Yu-She Cao et al.· 0 citations
Evidence-grounded visual reasoning (EGVOR) is proposed, departing from implicit inference, EGVOR reformulates reasoning as the explicit generation of Evidence Atoms–structured triplets that enforce strict spatial-semantic alignment.
Zhao-Yang Wei, Bo-Wen Jiang, Xumeng Han et al.· International Journal of Com...· 6 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
