相关论文: AIBA: Attention-based Instrument Band Alignment fo…
Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior…
Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distribution data). To…
Audio tagging is an important task of mapping audio samples to their corresponding categories. Recently endeavours that exploit transformer models in this field have achieved great success. However, the quadratic self-attention cost limits…
Driver gaze estimation serves as a fundamental metric for evaluating driver attentiveness in modern monitoring systems. Beyond being vulnerable to sudden lighting changes and sensor noise, spatial-domain models struggle to disentangle…
The direction-of-arrival (DOA) of sound sources is an essential acoustic parameter used, e.g., for multi-channel speech enhancement or source tracking. Complex acoustic scenarios consisting of sources-of-interest, interfering sources,…
Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first…
While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…
In complex auditory environments, the human auditory system possesses the remarkable ability to focus on a specific speaker while disregarding others. In this study, a new model named SWIM, a short-window convolution neural network (CNN)…
Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target…
Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature…
The International Phonetic Alphabet (IPA) is indispensable in language learning and understanding, aiding users in accurate pronunciation and comprehension. Additionally, it plays a pivotal role in speech therapy, linguistic research,…
Explaining the behavior of end-to-end audio language models via Shapley value attribution is intractable under native tokenization: a typical utterance yields over $150$ encoder frames, inflating the coalition space by roughly $10^{42}$…
Many tool-based Retrieval Augmented Generation (RAG) systems lack precise mechanisms for tracing final responses back to specific tool components -- a critical gap as systems scale to complex multi-agent architectures. We present…
Ion Beam Analysis (IBA) comprises a set of analytical techniques suited for material analysis, many of which are rather closely related. Self-consistent analysis of several IBA techniques takes advantage of this close relationship to…
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain. It does not require access to both the source-domain data and the predictor…
Recent advancements in deep generative models present new opportunities for music production but also pose challenges, such as high computational demands and limited audio quality. Moreover, current systems frequently rely solely on text…
Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on…
Recent studies have revealed that text-to-image diffusion models are vulnerable to backdoor attacks, where attackers implant stealthy textual triggers to manipulate model outputs. Previous backdoor detection methods primarily focus on the…
Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…
Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on…