相关论文: CLEVR-POC: Reasoning-Intensive Visual Question Ans…

Vision-Language Models (VLMs), exemplified by CLIP, have emerged as foundational for multimodal intelligence. However, their capacity for logical understanding remains significantly underexplored, resulting in critical ''logical…

Visual Question Answering (VQA) holds great potential for assisting Blind and Low Vision (BLV) users, yet real-world usage remains challenging. Due to visual impairments, BLV users often take blurry or poorly framed photos and face…

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce…

Recently, large multi-modal models (LMMs) have emerged with the capacity to perform vision tasks such as captioning and visual question answering (VQA) with unprecedented accuracy. Applications such as helping the blind or visually impaired…

Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to…

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…

Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…

Reinforcement learning from verifiable rewards (RLVR) has recently been extended from text-only LLMs to vision-language models (VLMs) to elicit long-chain multimodal reasoning. However, RLVR-trained VLMs still exhibit two persistent failure…

Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically…

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…

This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). We design a novel…

Recognizing and reasoning about occluded (partially or fully hidden) objects is vital to understanding visual scenes, as occlusions frequently occur in real-world environments and act as obstacles for spatial comprehension. To test models'…

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question…

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…

Explanation and high-order reasoning capabilities are crucial for real-world visual question answering with diverse levels of inference complexity (e.g., what is the dog that is near the girl playing with?) and important for users to…

Vision-Language Models (VLMs) have recently demonstrated incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but less explored realm, and find previously unexposed…

Many vision and language tasks require commonsense reasoning beyond data-driven image and natural language processing. Here we adopt Visual Question Answering (VQA) as an example task, where a system is expected to answer a question in…

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level…

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal…