English
Related papers

Related papers: Thinking with Drafts: Speculative Temporal Reasoni…

200 papers

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…

Computer Vision and Pattern Recognition · Computer Science 2020-01-20 Anoop Cherian , Jue Wang , Chiori Hori , Tim K. Marks

Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Min Shi , Shihao Wang , Chieh-Yun Chen , Jitesh Jain , Kai Wang , Junjun Xiong , Guilin Liu , Zhiding Yu , Humphrey Shi

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Computation and Language · Computer Science 2026-02-17 Miles Williams , Young D. Kwon , Rui Li , Alexandros Kouris , Stylianos I. Venieris

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse…

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

Information Retrieval · Computer Science 2024-08-15 Jinxu Zhang

Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Jinho Park , Youbin Kim , Hogun Park , Eunbyung Park

Video Large Language Models (VLMs) have achieved strong performance on various vision-language tasks, yet their practical use is limited by the massive number of visual tokens produced from raw video frames, which quickly exhausts the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Guangyu Sun , Archit Singhal , Burak Uzkent , Mubarak Shah , Chen Chen , Garin Kessler

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Diankun Wu , Fangfu Liu , Yi-Hsin Hung , Yueqi Duan

Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Linghao Zhang , Jungang Li , Yonghua Hei , Sicheng Tao , Song Dai , Yibo Yan , Zihao Dongfang , Weiting Liu , Chenxi Qin , Hanqian Li , Xin Zou , Jiahao Zhang , Shuhang Xun , Haiyun Jiang , Xuming Hu

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any…

Machine Learning · Computer Science 2025-07-15 Ziyi Chen , Xiaocong Yang , Jiacheng Lin , Chenkai Sun , Kevin Chen-Chuan Chang , Jie Huang

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Vaggelis Dorovatas , Soroush Seifi , Gunshi Gupta , Rahaf Aljundi

Temporal reasoning is a critical challenge in video-language understanding, as it requires models to align semantic concepts consistently across time. While existing large vision-language models (LVLMs) and large language models (LLMs)…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Rafael Souza , Jia-Hao Lim , Alexander Davis

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Henghao Zhao , Ge-Peng Ji , Rui Yan , Huan Xiong , Zechao Li

Understanding fine-grained temporal dynamics is crucial for multimodal video comprehension and generation. Due to the lack of fine-grained temporal annotations, existing video benchmarks mostly resemble static image benchmarks and are…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Mu Cai , Reuben Tan , Jianrui Zhang , Bocheng Zou , Kai Zhang , Feng Yao , Fangrui Zhu , Jing Gu , Yiwu Zhong , Yuzhang Shang , Yao Dou , Jaden Park , Jianfeng Gao , Yong Jae Lee , Jianwei Yang

The "Thinking with Text" and "Thinking with Images" paradigms significantly improve the reasoning abilities of large language models (LLMs) and Vision-Language Models (VLMs). However, these paradigms have inherent limitations. (1) Images…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Jingqi Tong , Yurong Mou , Hangcheng Li , Mingzhe Li , Yongzhuo Yang , Ming Zhang , Qiguang Chen , Tianyi Liang , Xiaomeng Hu , Yining Zheng , Xinchi Chen , Jun Zhao , Xuanjing Huang , Xipeng Qiu

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Wanyue Zhang , Wenxiang Wu , Wang Xu , Jiaxin Luo , Helu Zhi , Yibin Huang , Shuo Ren , Zitao Liu , Jiajun Zhang

Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Ji-jun Park , Soo-joon Choi

Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Apratim Bhattacharyya , Sunny Panchal , Mingu Lee , Reza Pourreza , Pulkit Madan , Roland Memisevic