CORTEXA
← Browse
arxivcs.AI2026-07-20

ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding

Keuntae Kim, Beomseok Lee, Hyunwoo Kim, Yong Suk Choi

Vision Language Models (VLMs) achieve strong reasoning with Chain-of-Thought (CoT) prompting but incur high sequential-generation cost, error accumulation, and limited self-correction. Diffusion Multimodal Large Language Models (dMLLMs) unmask tokens in an order-agnostic process, improving efficiency and enabling iterative refinement, yet their reasoning and how to enhance it remain underexplored. We propose a training-free method, Spatio-Temporal Token Veto (ST-Veto), which leverages the ability to observe all token positions at each diffusion step. Rather than relying only on current-step confidence, ST-Veto vetoes temporally unstable tokens via second-order Taylor prediction of confidence dynamics and filters weakly grounded tokens using image-attention mass, swapping them with safer candidates. Across multiple dMLLMs and multimodal reasoning benchmarks, ST-Veto consistently outperforms standard decoding policies and prior VLM reasoning methods, improving accuracy by up to 9% with no additional training or generation cost. Analyses show that ST-Veto steers generation toward higher-confidence, better-grounded paths.

View free PDFSource page

Related papers

arxivcs.NIcs.AI2026-07-09

Spatio-Temporal Scheduling Prediction Under Backhaul Delay for Resilient Coordinated Beamforming

Prashant Kumar Singh, Shubham Vaishnav, Ahmet Hasim Gökceoglu, Li Wang

Coordinated beamforming in distributed 5G networks relies on the timely exchange of inter-cell scheduling information, but backhaul latency makes this information stale. Even a single transmission time interval (TTI) of delay can reduce CBF-SLNR performance below the uncoordinate…

View free PDFSource page
arxivcs.LGcs.AI2026-07-14

STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting

Sicong Lai, Yuehong Hu, Siru Zhong, Si Qiao, Yuxuan Liang, Guangyin Jin

Real-world traffic data exhibit heterogeneous spatial correlations and nonlinear temporal dynamics, posing substantial challenges for accurate spatio-temporal forecasting. Existing approaches have developed increasingly sophisticated graph, attention, and decomposition architectu…

View free PDFSource page
arxivcs.CVcs.AI2026-07-15

ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding

Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang

Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression. However, most advanced methods struggle to balance global context modeling with precise boundary localization. Due…

View free PDFSource page
arxivcs.LGcs.AI2026-07-20

MambaLSTM: A Spatio-Temporal Framework for Enhanced Traffic Accident Risk Prediction

Zhen Yu, Yachao Yuan, Zixiang Peng, Muting Li, Thar Baker

In traffic accident risk prediction, most studies overlook the extra noise that could be incorporated when fusing temporal features into spatial features, and some models struggle to capture global correlations among spatial regions. To address these challenges, we propose a nove…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-03

HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

Dongyeun Lee, Amir Zandieh, Vahab Mirrokni, Junmo Kim, Insu Han

Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundamentally constrained by the quadratic complexity of the self-attention mechanism. Recent clustering-ba…

View free PDFSource page