相关论文: Crab$^{+}$: A Scalable and Unified Audio-Visual Sc…

Contrastive language-image pre-training (CLIP) is a powerful vision-language model that has shown great benefits for various tasks. However, we have identified some issues with its explainability, which undermine its credibility and limit…

We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Despite considerable progress in multi-task learning, most efforts focus on learning from multi-label data: a single image…

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…

Collaborative game-based learning environments offer rich opportunities for small-group knowledge construction, yet automatically predicting student collaboration satisfaction remains challenging. A critical barrier is modality degradation:…

This paper presents Audio-Visual LLM, a Multimodal Large Language Model that takes both visual and auditory inputs for holistic video understanding. A key design is the modality-augmented training, which involves the integration of…

This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs), aimed at simultaneously reinforcing generation and understanding…

As Vision and Language models (VLMs) are reaching users across the globe, assessing their cultural understanding has become a critical challenge. In this paper, we introduce CROPE, a visual question answering benchmark designed to probe the…

Developing versatile quadruped robots that can smoothly perform various actions and tasks in real-world environments remains a significant challenge. This paper introduces a novel vision-language-action (VLA) model, mixture of robotic…

Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually requires. This…

The field of Abstract Visual Reasoning (AVR) encompasses a wide range of problems, many of which are inspired by human IQ tests. The variety of AVR tasks has resulted in state-of-the-art AVR methods being task-specific approaches.…

Automated radiology report generation aims to expedite the tedious and error-prone reporting process for radiologists. While recent works have made progress, learning to align medical images and textual findings remains challenging due to…

Learning from multiple data streams in real-world scenarios is fundamentally challenging due to intrinsic heterogeneity and unpredictable concept drifts. Existing methods typically assume homogeneous streams and employ static architectures…

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…

Robotic manipulation in 3D requires effective computation of N degree-of-freedom joint-space trajectories that enable precise and robust control. To achieve this, robots must integrate semantic understanding with visual perception to…

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They…

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

Scene understanding is a vital part of autonomous driving systems, which requires the use of deep learning models. Deep learning methods are intrinsically black box models, which lack transparency and safety in autonomous driving. To make…

Training large language representation models has become a standard in the natural language processing community. This allows for fine tuning on any number of specific tasks, however, these large high capacity models can continue to train…

Learning robust audio-visual embeddings requires bringing genuinely related audio and visual signals together while filtering out incidental co-occurrences - background noise, unrelated elements, or unannotated events. Most contrastive and…

This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering)…