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.CVcs.AI2026-07-24

TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution

Sicheng Gao, Zhuyun Zhou, Yixuan Liu, Tong Shen, Zongwei Wu, Radu Timofte

Video super-resolution (VSR) using large-scale Diffusion Transformer (DiT) priors achieves exceptional perceptual quality but is often impractical due to the quadratic computational cost of processing dense spatio-temporal token sequences. Existing efficiency-oriented methods ris…

View free PDFSource page
arxivcs.ROcs.AI2026-07-31

ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency

Wenda Yu, Tianshi Wang, Fengling Li, Xin Li, Jingjing Li, Lei Zhu

Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguard…

View free PDFSource page
arxivcs.CVcs.AI2026-07-31

Dense Temporal Contrast Synthesis via Conditioned Latent Transport

Smriti Joshi, Apostolia Tsirikoglou, Daniel M. Lang, Richard Osuala, Noah Márquez Varaa, Alejandro Guzman, et al.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is essential for breast cancer management, but reliance on gadolinium-based contrast agents (GBCAs) restricts use in contraindicated populations, prolongs scan protocols, and presents environmental toxicity concerns.…

View free PDFSource page
arxivcs.SIcs.AI2026-07-31

Multi-Granularity Position Embedding of Graphs via Granular-Ball for Link Prediction

Sen Zhao, Cheng Liu, Shuyin Xia, Zhiyuan Liu, Yi Liu, Yi Wang, et al.

Link prediction aims to identify potential or future connections within a given graph structure. Position information is essential for link prediction, as it distinguishes homogeneous nodes through their relative relationships, facilitating the accurate capture of structural patt…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-24

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization

Hao Wang, Kun Yuan, Wenlin Zhong, Minglei Zhang, Han Xiao, Ming Sun, et al.

Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD). However, full-vocabulary OPD typically assumes a shared tokenizer, while existing cross-tokenizer me…

View free PDFSource page