相关论文: Conflict Adaptation in Vision-Language Models

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric models. We present the first mechanistic interpretability (MI)…

The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language models (LLMs) show misaligned behaviors, such as strategic…

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…

Vision-Language-Action models (VLAs) have recently demonstrated remarkable progress in embodied environments, enabling robots to perceive, reason, and act through unified multimodal understanding. Despite their impressive capabilities, the…

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite…

Ambivalence and hesitancy (A/H) are subtle affective states where a person shows conflicting signals through different channels -- saying one thing while their face or voice tells another story. Recognising these states automatically is…

The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training, while post-training is about giving a model the right style and format. We re-examine these claims by…

Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been limited to everyday scenarios. To close this gap, we introduce CLASH (Character…

This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a…

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential…

Self-supervised learning techniques are celebrating immense success in natural language processing (NLP) by enabling models to learn from broad language data at unprecedented scales. Here, we aim to leverage the success of these techniques…

Speech Emotion Recognition (SER) in real-world scenarios remains challenging due to severe class imbalance and the prevalence of spontaneous, natural speech. While recent approaches leverage self-supervised learning (SSL) representations…

Psychophysical experiments remain the most reliable approach for perceptual image quality assessment (IQA), yet their cost and limited scalability encourage automated approaches. We investigate whether Vision Language Models (VLMs) can…

Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. Only a few research explored the…

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…

When a Vision-Language Model (VLM) sees a blue banana and answers "yellow", is the problem of perception or arbitration? We explore the question in ten VLMs with various sizes and reveal an Encoding-Grounding Dissociation: models that fail…