相关论文: ExoViP: Step-by-step Verification and Exploration …

Recent advances in visual-language machine learning models have demonstrated exceptional ability to use natural language and understand visual scenes by training on large, unstructured datasets. However, this training paradigm cannot…

This paper addresses the problem of planning complex manipulation tasks, in which multiple robots with different end-effectors and capabilities, informed by computer vision, must plan and execute concatenated sequences of actions on a…

Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of…

Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or document analysis, due to perception limitations and visual fragmentation. To address these challenges,…

Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved…

Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their performance is still lacking in physical domains that require…

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from…

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

Recent works have shown that Large Language Models (LLMs) could empower traditional neuro-symbolic models via programming capabilities to translate language into module descriptions, thus achieving strong visual reasoning results while…

Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking…

Large language models (LLMs) are increasingly used for program verification, and yet little is known about \emph{how} they reason about program semantics during this process. In this work, we focus on abstract interpretation based-reasoning…

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending…

Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level…

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow…

As multimodal large language models (MLLMs) continue to demonstrate increasingly competitive performance across a broad spectrum of tasks, more intricate and comprehensive benchmarks have been developed to assess these cutting-edge models.…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

Visual Language Models (VLMs) show remarkable performance in visual reasoning tasks, successfully tackling college-level challenges that require high-level understanding of images. However, some recent reports of VLMs struggling to reason…

Recent advances in large language models (LLMs) have shown great potential in automating the process of visualization authoring through simple natural language utterances. However, instructing LLMs using natural language is limited in…

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…