相关论文: ChimpVLM: Ethogram-Enhanced Chimpanzee Behaviour R…

We empirically investigate proper pre-training methods to build good visual tokenizers, making Large Language Models (LLMs) powerful Multimodal Large Language Models (MLLMs). In our benchmark, which is curated to evaluate MLLMs visual…

The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image…

How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data,…

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual…

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various…

In this paper, we present a comprehensive and systematic analysis of vision-language models (VLMs) for disparate meme classification tasks. We introduced a novel approach that generates a VLM-based understanding of meme images and…

Animal ethology is an crucial aspect of animal research, and animal behavior labeling is the foundation for studying animal behavior. This process typically involves labeling video clips with behavioral semantic tags, a task that is…

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the…

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and…

Joint vision-language models have shown great performance over a diverse set of tasks. However, little is known about their limitations, as the high dimensional space learned by these models makes it difficult to identify semantic errors.…

Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Recent vision-language formulations improve semantic reasoning and support language-conditioned…

Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Segmenting long-form videos into semantically coherent scenes is a fundamental task in large-scale video understanding. Existing encoder-based methods are limited by visual-centric biases, classify each shot in isolation without leveraging…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs,…