相关论文: HAWAII: Hierarchical Visual Knowledge Transfer for…

Benefiting from recent advancements in large language models and modality alignment techniques, existing Large Vision-Language Models(LVLMs) have achieved prominent performance across a wide range of scenarios. However, the excessive…

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models. Existing work often faces three key challenges: (1) information loss from hard pruning, (2)…

Audio-visual representation learning is crucial for advancing multimodal speech processing tasks, such as lipreading and audio-visual speech recognition. Recently, speech foundation models (SFMs) have shown remarkable generalization…

Large-scale vision-language models (VLMs) have recently achieved remarkable multimodal understanding, but their massive size makes them impractical for deployment on mobile or edge devices. This raises the need for compact yet capable VLMs…

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models (MLLMs) via…

Vision-language-action (VLA) models provide a powerful approach to training control policies for physical systems, such as robots, by combining end-to-end learning with transfer of semantic knowledge from web-scale vision-language model…

Large language models (LLMs) have demonstrated immense capabilities in understanding textual data and are increasingly being adopted to help researchers accelerate scientific discovery through knowledge extraction (information retrieval),…

We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods…

Weakly-supervised vision-language (V-L) pre-training (W-VLP) aims at learning cross-modal alignment with little or no paired data, such as aligned images and captions. Recent W-VLP methods, which pair visual features with object tags, help…

Vision-Language models (VLMs) have proven to be effective at aligning image and text representations, producing superior zero-shot results when transferred to many downstream tasks. However, these representations suffer from some key…

Cross-modal encoders for vision-language (VL) tasks are often pretrained with carefully curated vision-language datasets. While these datasets reach an order of 10 million samples, the labor cost is prohibitive to scale further. Conversely,…

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…

When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning beyond what proprioception alone can achieve. However, vision-enabled policies tend to…