相关论文: GazeQwen: Lightweight Gaze-Conditioned LLM Modulat…

Remote Sensing Visual Question Answering (RSVQA) is a challenging task that involves interpreting complex satellite imagery to answer natural language questions. Traditional approaches often rely on separate visual feature extractors and…

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…

The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction --…

We present GazeGen, a user interaction system that generates visual content (images and videos) for locations indicated by the user's eye gaze. GazeGen allows intuitive manipulation of visual content by targeting regions of interest with…

Large Language Models (LLMs), primarily trained on text-based datasets, exhibit exceptional proficiencies in understanding and executing complex linguistic instructions via text outputs. However, they falter when requests to generate…

Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

We present a semantics modulated, multi scale Transformer for 3D gaze estimation. Our model conditions CLIP global features with learnable prototype banks (illumination, head pose, background, direction), fuses these prototype-enriched…

Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive computational cost of processing dense frame sequences. Prevailing solutions, which select a keyframe subset,…

Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV…

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

Large Multimodal Models (LMMs) such as LLaVA are typically trained with an autoregressive language modeling objective, providing only indirect supervision to visual tokens. This often yields weak internal visual representations and brittle…

The success of large language models (LLMs) has fostered a new research trend of multi-modality large language models (MLLMs), which changes the paradigm of various fields in computer vision. Though MLLMs have shown promising results in…

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long…

Previous studies have illustrated the potential of analysing gaze behaviours in collaborative learning to provide educationally meaningful information for students to reflect on their learning. Over the past decades, machine learning…

The rapid proliferation of user-generated content (UGC) on short-form video platforms has made video engagement prediction increasingly important for optimizing recommendation systems and guiding content creation. However, this task remains…

The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating a high-quality…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter…

Where someone looks is a nonverbal communication cue that children and adults readily use. How well can Vision-Language Models (VLMs) infer gaze targets? To construct evaluation stimuli, we captured 1,360 real-world photos of scenes in…

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To…