相关论文: Improved Visual Grounding through Self-Consistent …

Visual Grounding (VG) in Visual Question Answering (VQA) systems describes how well a system manages to tie a question and its answer to relevant image regions. Systems with strong VG are considered intuitively interpretable and suggest an…

Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an…

Recent progress on automatic generation of image captions has shown that it is possible to describe the most salient information conveyed by images with accurate and meaningful sentences. In this paper, we propose an image caption system…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

Multimodal large language models (MLLMs) have made significant advancements in vision understanding and reasoning. However, the autoregressive Transformer architecture used by MLLMs requries tokenization on input images, which limits their…

Recent advances in legged locomotion learning are still dominated by the utilization of geometric representations of the environment, limiting the robot's capability to respond to higher-level semantics such as human instructions. To…

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many…

Video grounding aims to localize the corresponding video moment in an untrimmed video given a language query. Existing methods often address this task in an indirect way, by casting it as a proposal-and-match or fusion-and-detection…

Unlike most neural language models, humans learn language in a rich, multi-sensory and, often, multi-lingual environment. Current language models typically fail to fully capture the complexities of multilingual language use. We train an…

This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The…

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as…

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using…

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, including new ground truth…

We propose an end-to-end approach for phrase grounding in images. Unlike prior methods that typically attempt to ground each phrase independently by building an image-text embedding, our architecture formulates grounding of multiple phrases…

Significant progress has been made in recent years in image captioning, an active topic in the fields of vision and language. However, existing methods tend to yield overly general captions and consist of some of the most frequent…

Providing Language Models (LMs) with relevant evidence in the context (either via retrieval or user-provided) can significantly improve their ability to provide better-grounded responses. However, recent studies have found that LMs often…

We introduce EaGERS, a fully training-free and model-agnostic pipeline that (1) generates natural language rationales via a vision language model, (2) grounds these rationales to spatial sub-regions by computing multimodal embedding…

Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical…

Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks,…