Related papers: FiLA-Video: Spatio-Temporal Compression for Fine-G…
Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck:…
In recent years, data-driven techniques have greatly advanced autonomous driving systems, but the need for rare and diverse training data remains a challenge, requiring significant investment in equipment and labor. World models, which…
Recent advancements in deep learning techniques have significantly improved the quality of compressed videos. However, previous approaches have not fully exploited the motion characteristics of compressed videos, such as the drastic change…
In recent years, large-scale vision-language models (VLMs) have demonstrated remarkable performance on multimodal understanding and reasoning tasks. However, handling high-dimensional visual features often incurs substantial computational…
Understanding long videos requires extracting query-relevant information from long sequences under tight compute budgets. Existing text-then-LLM pipelines lose fine-grained visual cues, while video-based multimodal large language models…
Long video understanding is a key challenge that plagues the advancement of \emph{Multimodal Large language Models} (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and…
One of the most exciting applications of vision models involve pixel-level reasoning. Despite the abundance of vision foundation models, we still lack representations that effectively embed spatio-temporal properties of visual scenes at the…
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…
Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources,…
Frozen Large Video Language Models (LVLMs) are increasingly employed in micro-video recommendation due to their strong multimodal understanding. However, their integration lacks systematic empirical evaluation: practitioners typically…
The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view…
Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…
Crash detection from video feeds is a critical problem in intelligent transportation systems. Recent developments in large language models (LLMs) and vision-language models (VLMs) have transformed how we process, reason about, and summarize…
Long-form video understanding has always been a challenging problem due to the significant redundancy in both temporal and spatial contents. This challenge is further exacerbated by the limited context length of Multimodal Large Language…
Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and…
Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed…
Vision-Language Models (VLMs) have enabled substantial progress in video understanding by leveraging cross-modal reasoning capabilities. However, their effectiveness is limited by the restricted context window and the high computational…
Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input.…
As the most essential property in a video, motion information is critical to a robust and generalized video representation. To inject motion dynamics, recent works have adopted frame difference as the source of motion information in video…
Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been…