相关论文: HMVLM: Human Motion-Vision-Lanuage Model via MoE L…

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA)…

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive…

Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments without prior maps or task-specific training which remains a significant challenge. Although recent advancements in vision-language…

Following the success of GPT4, there has been a surge in interest in multimodal large language model (MLLM) research. This line of research focuses on developing general-purpose LLMs through fine-tuning pre-trained LLMs and vision models.…

Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still…

Explorations in fine-tuning Vision-Language Models (VLMs), such as Low-Rank Adaptation (LoRA) from Parameter Efficient Fine-Tuning (PEFT), have made impressive progress. However, most approaches rely on explicit weight updates, overlooking…

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in…

The advancement of embodied intelligence is accelerating the integration of robots into daily life as human assistants. This evolution requires robots to not only interpret high-level instructions and plan tasks but also perceive and adapt…

Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation. Existing approaches often necessitate expensive language model…

Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods update a visual projector to translate visual information for…

This paper explores training medical vision-language models (VLMs) -- where the visual and language inputs are embedded into a common space -- with a particular focus on scenarios where training data is limited, as is often the case in…

Vision-Language-Action (VLA) models have advanced general-purpose robotic manipulation by leveraging pretrained visual and linguistic representations. However, they struggle with contact-rich tasks that require fine-grained control…

Recent advances in Vision-Language-Action (VLA) models have shown promising capabilities in autonomous driving by leveraging the understanding and reasoning strengths of Large Language Models(LLMs).However, our empirical analysis reveals…

Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe systematically erodes the VLM's multimodal competence, a side…

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Recent human-object interaction detection (HOID) methods highly require prior knowledge from vision-language models (VLMs) to enhance the interaction recognition capabilities. The training strategies and model architectures for connecting…

Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Existing fine-tuning approaches treat MoE models as monolithic learners,…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

While Multimodal Large Language Models (MLLMs) excel at generalizing across modalities and tasks, effectively adapting them to specific downstream tasks while simultaneously retaining both general and specialized knowledge remains…