paper-with-me

Papers

STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models

2025-12-07 · Xinhao Sun, Huaijin Zhao, Maoliang Li, Zihao Zheng, Jiayu Chen, Yun Liang, Xiang Chen arxiv

Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence thresholds, overlooking the spatial-temporal dynamics of token confidence, causing unnecessary remasking. We propose Spatial-Temporal Token-Dynamics-Aware Responsive Remasking (STaRR), a training-free framework that dynamically adapts remasking decisions based on token confidence evolution. STaRR introduces two metrics, temporal variance and spatial deviance, to guide fine-grained, step-wise dynamic thresholding. We further introduce a step-wise dynamic thresholding strategy, further enhanced with responsiveness optimizations for scalability and robustness. Experiments show that STaRR achieves an average speedup of 4.1 and up to 8.9 while maintaining comparable accuracy.

📄 PDF Abstract BibTeX arXiv:2601.04205

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation

2026-04-29 · Yuxuan Tian, Yurun Jin, Bin Yu, Yukun Shi 외 arxiv

Robotic manipulation requires reasoning about future spatial-temporal interactions and geometric constraints, yet existing Vision-Language-Action (VLA) policies often leave predictive representation weakly coupled with a…

Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature

2025-09-20 · Zheng Liu, Mengjie Liu, Siwei Wen, Mengzhang Cai 외 arxiv

Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typically treat it as a discrete filter or post-…

Reinforcement LearningMathematical Reasoning

Token Dynamics: Towards Efficient and Dynamic Video Token Representation for Video Large Language Models

2025-03-21 · Haichao Zhang, Yun Fu

Token-based video representation has emerged as a promising approach for enabling LLMs to interpret video content. However, existing token reduction, such as token pruning and token merging, often disrupt essential spati…

Computational EfficiencyToken Reduction

T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding

2026-03-07 · Chaohong Guo, Yihan He, Yongwei Nie, Fei Ma 외 arxiv

Video Temporal Grounding (VTG) aims to localize the video segment that corresponds to a natural language query, which requires a comprehensive understanding of complex temporal dynamics. Existing Vision-LMMs typically pe…

Temporal Sequences

Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs

2026-05-10 · Yigui Feng, Qinglin Wang, Yang Liu, Jie Liu arxiv

Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampli…