中文
相关论文

相关论文: Investigating and Enhancing Vision-Audio Capabilit…

200 篇论文

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Qianhao Yuan , Jie Lou , Xing Yu , Hongyu Lin , Le Sun , Xianpei Han , Yaojie Lu

Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Qianhan Feng , Wenshuo Li , Tong Lin , Xinghao Chen

Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities. Although some priors introduce Knowledge Distillation to…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Ze Feng , Sen Yang , Boqiang Duan , Wankou Yang , Jingdong Wang

The success of Large Language Models (LLMs) has inspired the development of Multimodal Large Language Models (MLLMs) for unified understanding of vision and language. However, the increasing model size and computational complexity of…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Yuxuan Cai , Jiangning Zhang , Haoyang He , Xinwei He , Ao Tong , Zhenye Gan , Chengjie Wang , Zhucun Xue , Yong Liu , Xiang Bai

Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for real-world applications. In this regard, the knowledge…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Jiwan Kim , Kibum Kim , Sangwoo Seo , Chanyoung Park

Knowledge distillation (KD) is widely used in audio tasks, such as speaker verification (SV), by transferring knowledge from a well-trained large model (the teacher) to a smaller, more compact model (the student) for efficiency and…

音频与语音处理 · 电气工程与系统科学 2024-09-17 Wenhao Yang , Jianguo Wei , Wenhuan Lu , Xugang Lu , Lei Li

Vision-language models (VLMs) exhibit uneven performance across languages, a problem that is often exacerbated when the model size is reduced. While Knowledge distillation (KD) demonstrates promising results in transferring knowledge from…

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…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Fangxun Shu , Lei Zhang , Hao Jiang , Cihang Xie

Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of…

计算机视觉与模式识别 · 计算机科学 2023-10-13 Xuanlin Li , Yunhao Fang , Minghua Liu , Zhan Ling , Zhuowen Tu , Hao Su

Audio large language models (LLMs) are considered experts at recognizing sound objects, yet their performance relative to LLMs in other sensory modalities, such as visual or audio-visual LLMs, and to humans using their ears, eyes, or both…

声音 · 计算机科学 2025-05-13 Xilin Jiang , Junkai Wu , Vishal Choudhari , Nima Mesgarani

Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy…

计算与语言 · 计算机科学 2024-10-16 Qihuang Zhong , Kunfeng Chen , Liang Ding , Juhua Liu , Bo Du , Dacheng Tao

There is a gap in the understanding of occluded objects in existing large-scale visual language multi-modal models. Current state-of-the-art multi-modal models fail to provide satisfactory results in describing occluded objects through…

计算机视觉与模式识别 · 计算机科学 2024-10-04 Shuxin Yang , Xinhan Di

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

计算与语言 · 计算机科学 2024-12-19 Tianyu Peng , Jiajun Zhang

Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Distillation (KD) offers…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Haoyi Sun , Xiaoxiao Wang , Ning Mao , Qian Wang , Lifu Mu , Wen Zheng , Tao Wei , Wei Chen

Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Pume Tuchinda , Parinthapat Pengpun , Romrawin Chumpu , Sarana Nutanong , Peerat Limkonchotiwat

While Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have shown strong generalisation in detecting image and video deepfakes, their use for audio deepfake detection remains largely unexplored. In this work, we…

声音 · 计算机科学 2026-01-05 Akanksha Chuchra , Shukesh Reddy , Sudeepta Mishra , Abhijit Das , Abhinav Dhall

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

计算与语言 · 计算机科学 2023-01-31 Jan Philip Wahle

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We…

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate…

计算与语言 · 计算机科学 2026-05-13 Maxime Guigon , Lucas Dixon , Michaël E. Sander

The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without additional training. In current AV-LLMs, audio and video features are typically…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Chaeyoung Jung , Youngjoon Jang , Jongmin Choi , Joon Son Chung
‹ 上一页 1 2 3 10 下一页 ›