Related papers: Causal Probing for Internal Visual Representations…

Under pure textual modality, Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning tasks by decomposing them into simpler sub-problems. However, Multimodal Large Language Models (MLLMs) still struggle with…

Multi-modal large language models (MLLMs), such as GPT-4o, excel at integrating text and visual data but face systematic challenges when interpreting ambiguous or incomplete visual stimuli. This study leverages statistical modeling to…

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…

Although Large Language Models (LLMs) excel in reasoning and generation for language tasks, they are not specifically designed for multimodal challenges. Training Multimodal Large Language Models (MLLMs), however, is resource-intensive and…

Interleaved reasoning paradigms enhance Multimodal Large Language Models (MLLMs) with visual feedback but are hindered by the prohibitive computational cost of re-encoding pixel-dense images. A promising alternative, latent visual…

Mechanistic interpretability has revealed how concepts are encoded in large language models (LLMs), but emotional content remains poorly understood at the mechanistic level. We study whether LLMs process emotional valence through dedicated…

Can multi-modal large language models (MLLMs) truly understand what they can see? Extending Searle's Chinese Room into the multi-modal domain, this paper proposes the Visual Room argument: MLLMs may describe every visual detail precisely…

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

Humans possess the remarkable skill of Visual Perception, the ability to see and understand the seen, helping them make sense of the visual world and, in turn, reason. Multimodal Large Language Models (MLLM) have recently achieved…

The visual commonsense reasoning (VCR) task is to choose an answer and provide a justifying rationale based on the given image and textural question. Representative works first recognize objects in images and then associate them with key…

Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about memorized private data, outdated knowledge, and harmful…

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…