相关论文: VideoPASTA: 7K Preference Pairs That Matter for Vi…

Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundation models: many still rely on models without large-scale…

Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, the focus of prior research has been predominantly on devising…

With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g.,…

Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely on text prompts for evaluation, which often require complex…

Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem…

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human preferences. However, existing techniques overlook the…

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…

Visual Planning for Assistance (VPA) aims to predict a sequence of user actions required to achieve a specified goal based on a video showing the user's progress. Although recent advances in multimodal large language models (MLLMs) have…

Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence. Employing large language models (LLMs) for comprehending video becomes an emerging and promising method. However,…

Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Large Language Models (vLLMs) hold promise as a viable solution…

Advancements in Large Language Models (LLMs) inspire various strategies for integrating video modalities. A key approach is Video-LLMs, which incorporate an optimizable interface linking sophisticated video encoders to LLMs. However, due to…

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…

This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original and augmented image pairs, and conduct preference alignment…

Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into…

Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key…

Video understanding typically requires fine-tuning the large backbone when adapting to new domains. In this paper, we leverage the egocentric video foundation models (Ego-VFMs) based on video-language pre-training and propose a…

Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human preference alignment. This paper introduces OmniAlign-V, a…

Training an effective video-and-language model intuitively requires multiple frames as model inputs. However, it is unclear whether using multiple frames is beneficial to downstream tasks, and if yes, whether the performance gain is worth…

Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data structured as ``image - winner text - loser text'' triplets.…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…