Related papers: Preserving Localized Patch Semantics in VLMs

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly perceive text inputs lacking visual evidence as being part…

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…

Integrating large language models (LLMs) into embodied AI models is becoming increasingly prevalent. However, existing zero-shot LLM-based Vision-and-Language Navigation (VLN) agents either encode images as textual scene descriptions,…

Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with…

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood…

Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene…

We propose Concept Tokens, a lightweight method that adds a new special token to a pretrained LLM and learns only its embedding from multiple natural language definitions of a target concept, where occurrences of the concept are replaced by…

Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces…

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

This paper introduces LogitLens4LLMs, a toolkit that extends the Logit Lens technique to modern large language models. While Logit Lens has been a crucial method for understanding internal representations of language models, it was…

Fine-grained knowledge is crucial for vision-language models to obtain a better understanding of the real world. While there has been work trying to acquire this kind of knowledge in the space of vision and language, it has mostly focused…

Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and…

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon…

Modelling student knowledge is a key challenge when leveraging AI in education, with major implications for personalised learning. The Knowledge Tracing (KT) task aims to predict how students will respond to educational questions in…

Achieving better alignment between vision embeddings and Large Language Models (LLMs) is crucial for enhancing the abilities of Multimodal LLMs (MLLMs), particularly for recent models that rely on powerful pretrained vision encoders and…