相关论文: PinPoint: Prompting with Informative Interior Poin…

This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection…

Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate commonsense reasoning…

Single-point annotation in visual tasks, with the goal of minimizing labelling costs, is becoming increasingly prominent in research. Recently, visual foundation models, such as Segment Anything (SAM), have gained widespread usage due to…

The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach. With the zero-shot segmentation capacity, SAM achieved impressive flexibility and precision on various…

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…

Promptable segmentation has emerged as a powerful paradigm in computer vision, enabling users to guide models in parsing complex scenes with prompts such as clicks, boxes, or textual cues. Recent advances, exemplified by the Segment…

In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly…

Prompt-based learning is susceptible to intrinsic bias present in pre-trained language models (LMs), leading to sub-optimal performance in prompt-based zero/few-shot settings. In this work, we propose a null-input prompting method to…

Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically ignore explicit…

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model…

Vision-Language Models (VLMs) combine a vision encoder and a large language model (LLM) through alignment training, showing strong performance on multimodal tasks. A central component in this architecture is the projection layer, which maps…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Understanding freely moving animal behavior is central to neuroscience, where pose estimation and behavioral understanding form the foundation for linking neural activity to natural actions. Yet both tasks still depend heavily on human…

In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction…

Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. However, effective utilization of LLMs for zero-shot visual question-answering (VQA) remains challenging, primarily due to the modality…

In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the "pretrain-then-finetune"…

Medical image segmentation has immense clinical applicability but remains a challenge despite advancements in deep learning. The Segment Anything Model (SAM) exhibits potential in this field, yet the requirement for expertise intervention…

Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception across both images and videos remains limited. Foundation segmentation models such as the SAM…