相关论文: Mixture-of-Visual-Thoughts: Exploring Context-Adap…

Virtual environments provide a rich and controlled setting for collecting detailed data on human behavior, offering unique opportunities for predicting human trajectories in dynamic scenes. However, most existing approaches have overlooked…

Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via…

Human visual reasoning is governed by active vision, a process where metacognitive control drives top-down goal-directed attention, dynamically routing foveal focus toward task-relevant details while maintaining peripheral awareness of the…

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

Multimodal summarization requires models to jointly understand textual and visual inputs to generate concise, semantically coherent summaries. Existing methods often inject shallow visual features into deep language models, leading to…

Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still require an additional fusion network for VL reasoning,…

Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification. Prior work assumes the modification text fully specifies the visual changes, overlooking after-effects and implicit consequences…

Large pre-trained Vision Language Models (VLMs) demonstrate excellent generalization capabilities but remain highly susceptible to adversarial examples, posing potential security risks. To improve the robustness of VLMs against adversarial…

Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-only paradigms that fail to ground inferences in visual evidence. This limitation not only…

Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform reasoning primarily with textual CoT, which limits their…

Reasoning about visual relationships is central to how humans interpret the visual world. This task remains challenging for current deep learning algorithms since it requires addressing three key technical problems jointly: 1) identifying…

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…

Abstract Visual Reasoning (AVR) problems are commonly used to approximate human intelligence. They test the ability of applying previously gained knowledge, experience and skills in a completely new setting, which makes them particularly…

Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to…

Visual Language Models have demonstrated remarkable capabilities across tasks, including visual question answering and image captioning. However, most models rely on text-based instructions, limiting their effectiveness in human-machine…

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

By extending the advantage of chain-of-thought (CoT) reasoning in human-like step-by-step processes to multimodal contexts, multimodal CoT (MCoT) reasoning has recently garnered significant research attention, especially in the integration…

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to…

Recently, prompt-based methods have emerged as a new alternative `parameter-efficient fine-tuning' paradigm, which only fine-tunes a small number of additional parameters while keeping the original model frozen. However, despite achieving…

Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and…