Related papers: Graph-of-Mark: Promote Spatial Reasoning in Multim…

Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the…

We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without…

Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the…

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…

Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}'…

Object Goal Navigation (ObjectNav) challenges robots to find objects in unseen environments, demanding sophisticated reasoning. While Vision-Language Models (VLMs) show potential, current ObjectNav methods often employ them superficially,…

Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms…

Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract…

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a…

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

The combination of strong visual backbones and Large Language Model (LLM) reasoning has led to Large Multimodal Models (LMMs) becoming the current standard for a wide range of vision and language (VL) tasks. However, recent research has…

One of the current trends in robotics is to employ large language models (LLMs) to provide non-predefined command execution and natural human-robot interaction. It is useful to have an environment map together with its language…

Graphical user interface (GUI) grounding is a fundamental task for building GUI agents. However, general vision-language models (VLMs) struggle with this task due to a lack of specific optimization. We identify a key gap in this paper:…

In Scene Graph Generation (SGG), structured representations are extracted from visual inputs as object nodes and connecting predicates, enabling image-based reasoning for diverse downstream tasks. While fully supervised SGG has improved…

In recent years, efforts have been made to use text information for better user profiling and item characterization in recommendations. However, text information can sometimes be of low quality, hindering its effectiveness for real-world…

This study explores the capability of Large Language Models (LLMs) to evaluate causality in causal graphs generated by conventional statistical causal discovery methods-a task traditionally reliant on manual assessment by human subject…

The emergence of large-scale pre-trained language models has revolutionized various AI research domains. Transformers-based Large Language Models (LLMs) have gradually replaced CNNs and RNNs to unify fields of computer vision and natural…

As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…

Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interactions. Current benchmarks test high level relationships ('left…