Related papers: Visual Instruction Bottleneck Tuning

Deeper Vision Transformers often perform worse than shallower ones, which challenges common scaling assumptions. Through a systematic empirical analysis of ViT-S, ViT-B, and ViT-L on ImageNet, we identify a consistent three-phase…

Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new visual question answering (VQA) tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, does not always improve…

Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate…

We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained region-based visual reasoning without any model retraining or…

Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing…

The Information Bottleneck (IB) principle offers a compelling theoretical framework to understand how neural networks (NNs) learn. However, its practical utility has been constrained by unresolved theoretical ambiguities and significant…

Multimodal LLMs (MLLMs) have reached remarkable levels of proficiency in understanding multimodal inputs. However, understanding and interpreting the behavior of such complex models is a challenging task, not to mention the dynamic shifts…

Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they…

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…

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely…

Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering. However, outputs of these models rarely…

Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input language. This phenomenon has been termed as Image-induced…

Despite remarkable advancements in Multimodal Large Language Models (MLLMs), a fundamental question remains: are MLLMs robust to contradicting modalities? To rigorously study this, we introduce MMA-Bench comprising videos and tasks that…

Integration of data from multiple omics techniques is becoming increasingly important in biomedical research. Due to non-uniformity and technical limitations in omics platforms, such integrative analyses on multiple omics, which we refer to…

This paper presents Hyper-VIB, a hypernetwork-enhanced information bottleneck (IB) approach designed to enable efficient task-oriented communications in 6G collaborative intelligent systems. Leveraging IB theory, our approach enables an…

Compact neural networks are essential for affordable and power efficient deep learning solutions. Binary Neural Networks (BNNs) take compactification to the extreme by constraining both weights and activations to two levels, $\{+1, -1\}$.…

While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliability. Consolidating agent consistency requires distilling trial-error trajectories into…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success in cross-modal tasks such as zero-shot image classification and text-image retrieval by effectively aligning visual and textual representations. However, the…

Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers and the original optimization objective could…

Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and audio-language tasks. However, a critical challenge remains: these models often suffer…