Related papers: CRIT: Graph-Based Automatic Data Synthesis to Enha…

Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In…

A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts…

After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains…

Knowledge-based Visual Question Answering (KVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing…

Recently, Interleaved-modal Chain-of-Thought (ICoT) reasoning has achieved remarkable success by leveraging both multimodal inputs and outputs, attracting increasing attention. While achieving promising performance, current ICoT methods…

Multimodal LLMs have advanced vision-language tasks but still struggle with understanding video scenes. To bridge this gap, Video Scene Graph Generation (VidSGG) has emerged to capture multi-object relationships across video frames.…

Despite significant progress in robotic systems for operation within human-centric environments, existing models still heavily rely on explicit human commands to identify and manipulate specific objects. This limits their effectiveness in…

Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often…

Technologies to predict human actions are extremely important for applications such as human robot cooperation and autonomous driving. However, a majority of the existing algorithms focus on exploiting visual features of the videos and do…

The deployment of Vision-Language Models (VLMs) in safety-critical domains like autonomous driving (AD) is critically hindered by reliability failures, most notably object hallucination. This failure stems from their reliance on ungrounded,…

Composed Image Retrieval (CIR) allows users to search for images by combining a reference image with a text prompt that describes desired modifications. While vision-language models like CLIP have popularized this task by embedding multiple…

Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent video streams remains poorly understood. Existing multi-video benchmarks rely largely…

Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in…

The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-language representation learned from a large scale of web-collected image-text data. In light of the well-learned visual features, some existing…

While Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), relying solely on linear text sequences remains a bottleneck for complex tasks. We observe that even…

Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing…

Vision-language models (VLMs) lag behind text-only language models on mathematical reasoning when the same problems are presented as images rather than text. We empirically characterize this as a modality gap: the same question in text form…

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…

Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, we focus on leveraging multi-modal content in the form of…

Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly…