Related papers: EchoDistill:Alignment Noisy-to-Clean Self-Distilla…

Large Language Models (LLMs) enable advanced natural language processing but face deployment challenges on resource-constrained edge devices due to high computational, memory, and energy demands. Optimizing these models requires addressing…

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…

The success of deep learning has brought forth a wave of interest in computer hardware design to better meet the high demands of neural network inference. In particular, analog computing hardware has been heavily motivated specifically for…

Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, they often correlate poorly with perceptual quality and…

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning,…

Respiratory sound datasets are limited in size and quality, making high performance difficult to achieve. Ensemble models help but inevitably increase compute cost at inference time. Soft label training distills knowledge efficiently with…

Spoken Language Understanding (SLU) is a core component of conversational systems, enabling machines to interpret user utterances. Despite its importance, developing effective SLU systems remains challenging due to the scarcity of labeled…

Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs. These models are typically adapted from text-based large language models (LLMs) through additional training on…

Speech enhancement is designed to enhance the intelligibility and quality of speech across diverse noise conditions. Recently, diffusion model has gained lots of attention in speech enhancement area, achieving competitive results. Current…

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This…

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

Depth refinement aims to infer high-resolution depth with fine-grained edges and details, refining low-resolution results of depth estimation models. The prevailing methods adopt tile-based manners by merging numerous patches, which lacks…

Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a result, applying SSL on noisy data…

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards.…

Automatic speech recognition (ASR) is critical for language accessibility, yet low-resource Cantonese remains challenging due to limited annotated data, six lexical tones, tone sandhi, and accent variation. Existing ASR models, such as…

The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and…