arXiv subjects

Yanghao Zhou

Publications and source records attributed to Yanghao Zhou.

28 records · Page 2Linked to original sources

arXiv2026

Pardon? Evaluating Conversational Repair in Large Audio-Language Models

Large Audio-Language Models (LALMs) have demonstrated strong performance in spoken question answering (QA), with existing evaluations primarily focusing on answer accuracy and robustness to acoustic perturbations. However, such evaluations implicitly assume that spoken inputs remain semantically answerable, an assumption that often fails in real-world interaction when essential information is missing. In this work, we introduce a repair-aware evaluation setting that explicitly distinguishes between answerable and unanswerable audio inputs. We define answerability as a property of the input itself and construct paired evaluation conditions using a semantic-acoustic masking protocol. Based on this setting, we propose the Evaluability Awareness and Repair (EAR) score, a non-compensatory metric that jointly evaluates task competence under answerable conditions and repair behavior under unanswerable conditions. Experiments on two spoken QA benchmarks across diverse LALMs reveal a consistent gap between answer accuracy and conversational reliability: while many models perform well when inputs are answerable, most fail to recognize semantic unanswerability and initiate appropriate conversational repair. These findings expose a limitation of prevailing accuracy-centric evaluation practices and motivate reliability assessments that treat unanswerable inputs as cues for repair and continued interaction.

cs.CL↗

arXiv2025

SimToken: A Simple Baseline for Referring Audio-Visual Segmentation

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment specific objects in videos based on natural language expressions involving audio, vision, and text information. This task poses significant challenges in cross-modal reasoning and fine-grained object localization. In this paper, we propose a simple framework, SimToken, that integrates a multimodal large language model (MLLM) with the Segment Anything Model (SAM). The MLLM is guided to generate a special semantic token representing the referred object. This compact token, enriched with contextual information from all modalities, acts as a prompt to guide SAM to segment objectsacross video frames. To further improve semantic learning, we introduce a novel target-consistent semantic alignment loss that aligns token embeddings from different expressions but referring to the same object. Experiments on the Ref-AVS benchmark demonstrate that our approach achieves superior performance compared to existing methods.

cs.CV↗

arXiv2025

MiniCPM4: Ultra-Efficient LLMs on End Devices

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems. Specifically, in terms of model architecture, we propose InfLLM v2, a trainable sparse attention mechanism that accelerates both prefilling and decoding phases for long-context processing. Regarding training data, we propose UltraClean, an efficient and accurate pre-training data filtering and generation strategy, and UltraChat v2, a comprehensive supervised fine-tuning dataset. These datasets enable satisfactory model performance to be achieved using just 8 trillion training tokens. Regarding training algorithms, we propose ModelTunnel v2 for efficient pre-training strategy search, and improve existing post-training methods by introducing chunk-wise rollout for load-balanced reinforcement learning and data-efficient tenary LLM, BitCPM. Regarding inference systems, we propose CPM.cu that integrates sparse attention, model quantization, and speculative sampling to achieve efficient prefilling and decoding. To meet diverse on-device requirements, MiniCPM4 is available in two versions, with 0.5B and 8B parameters, respectively. Furthermore, we construct a hybrid reasoning model, MiniCPM4.1, which can be used in both deep reasoning mode and non-reasoning mode. Evaluation results demonstrate that MiniCPM4 and MiniCPM4.1 outperform similar-sized open-source models across benchmarks, with the 8B variants showing significant speed improvements on long sequence understanding and generation.

cs.CL↗

arXiv2025

Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment target objects in audible videos based on given reference expressions. Prior works typically rely on learning latent embeddings via multimodal fusion to prompt a tunable SAM/SAM2 decoder for segmentation, which requires strong pixel-level supervision and lacks interpretability. From a novel perspective of explicit reference understanding, we propose TGS-Agent, which decomposes the task into a Think-Ground-Segment process, mimicking the human reasoning procedure by first identifying the referred object through multimodal analysis, followed by coarse-grained grounding and precise segmentation. To this end, we first propose Ref-Thinker, a multimodal language model capable of reasoning over textual, visual, and auditory cues. We construct an instruction-tuning dataset with explicit object-aware think-answer chains for Ref-Thinker fine-tuning. The object description inferred by Ref-Thinker is used as an explicit prompt for Grounding-DINO and SAM2, which perform grounding and segmentation without relying on pixel-level supervision. Additionally, we introduce R\textsuperscript{2}-AVSBench, a new benchmark with linguistically diverse and reasoning-intensive references for better evaluating model generalization. Our approach achieves state-of-the-art results on both standard Ref-AVSBench and proposed R\textsuperscript{2}-AVSBench. Code will be available at https://github.com/jasongief/TGS-Agent.

cs.MM↗

arXiv2025

CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization

The Dense Audio-Visual Event Localization (DAVEL) task aims to temporally localize events in untrimmed videos that occur simultaneously in both the audio and visual modalities. This paper explores DAVEL under a new and more challenging weakly-supervised setting (W-DAVEL task), where only video-level event labels are provided and the temporal boundaries of each event are unknown. We address W-DAVEL by exploiting \textit{cross-modal salient anchors}, which are defined as reliable timestamps that are well predicted under weak supervision and exhibit highly consistent event semantics across audio and visual modalities. Specifically, we propose a \textit{Mutual Event Agreement Evaluation} module, which generates an agreement score by measuring the discrepancy between the predicted audio and visual event classes. Then, the agreement score is utilized in a \textit{Cross-modal Salient Anchor Identification} module, which identifies the audio and visual anchor features through global-video and local temporal window identification mechanisms. The anchor features after multimodal integration are fed into an \textit{Anchor-based Temporal Propagation} module to enhance event semantic encoding in the original temporal audio and visual features, facilitating better temporal localization under weak supervision. We establish benchmarks for W-DAVEL on both the UnAV-100 and ActivityNet1.3 datasets. Extensive experiments demonstrate that our method achieves state-of-the-art performance.

cs.CV↗

arXiv2025

Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation

We present \textbf{Met}a-\textbf{T}oken \textbf{Le}arning (Mettle), a simple and memory-efficient method for adapting large-scale pretrained transformer models to downstream audio-visual tasks. Instead of sequentially modifying the output feature distribution of the transformer backbone, Mettle utilizes a lightweight \textit{Layer-Centric Distillation (LCD)} module to distill in parallel the intact audio or visual features embedded by each transformer layer into compact meta-tokens. This distillation process considers both pretrained knowledge preservation and task-specific adaptation. The obtained meta-tokens can be directly applied to classification tasks, such as audio-visual event localization and audio-visual video parsing. To further support fine-grained segmentation tasks, such as audio-visual segmentation, we introduce a \textit{Meta-Token Injection (MTI)} module, which utilizes the audio and visual meta-tokens distilled from the top transformer layer to guide feature adaptation in earlier layers. Extensive experiments on multiple audiovisual benchmarks demonstrate that our method significantly reduces memory usage and training time while maintaining parameter efficiency and competitive accuracy.

cs.CV↗

arXiv2025

AdaKWS: Towards Robust Keyword Spotting with Test-Time Adaptation

Spoken keyword spotting (KWS) aims to identify keywords in audio for wide applications, especially on edge devices. Current small-footprint KWS systems focus on efficient model designs. However, their inference performance can decline in unseen environments or noisy backgrounds. Test-time adaptation (TTA) helps models adapt to test samples without needing the original training data. In this study, we present AdaKWS, the first TTA method for robust KWS to the best of our knowledge. Specifically, 1) We initially optimize the model's confidence by selecting reliable samples based on prediction entropy minimization and adjusting the normalization statistics in each batch. 2) We introduce pseudo-keyword consistency (PKC) to identify critical, reliable features without overfitting to noise. Our experiments show that AdaKWS outperforms other methods across various conditions, including Gaussian noise and real-scenario noises. The code will be released in due course.

eess.AS↗

arXiv2025

SignDiff: Diffusion Model for American Sign Language Production

In this paper, we propose a dual-condition diffusion pre-training model named SignDiff that can generate human sign language speakers from a skeleton pose. SignDiff has a novel Frame Reinforcement Network called FR-Net, similar to dense human pose estimation work, which enhances the correspondence between text lexical symbols and sign language dense pose frames, reduces the occurrence of multiple fingers in the diffusion model. In addition, we propose a new method for American Sign Language Production (ASLP), which can generate ASL skeletal pose videos from text input, integrating two new improved modules and a new loss function to improve the accuracy and quality of sign language skeletal posture and enhance the ability of the model to train on large-scale data. We propose the first baseline for ASL production and report the scores of 17.19 and 12.85 on BLEU-4 on the How2Sign dev/test sets. We evaluated our model on the previous mainstream dataset PHOENIX14T, and the experiments achieved the SOTA results. In addition, our image quality far exceeds all previous results by 10 percentage points in terms of SSIM.

cs.CV↗

arXiv2022

Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic Convolution

It was shown recently that a combination of ASR and TTS models yield highly competitive performance on standard voice conversion tasks such as the Voice Conversion Challenge 2020 (VCC2020). To obtain good performance both models require pretraining on large amounts of data, thereby obtaining large models that are potentially inefficient in use. In this work we present a model that is significantly smaller and thereby faster in processing while obtaining equivalent performance. To achieve this the proposed model, Dynamic-GAN-VC (DYGAN-VC), uses a non-autoregressive structure and makes use of vector quantised embeddings obtained from a VQWav2vec model. Furthermore dynamic convolution is introduced to improve speech content modeling while requiring a small number of parameters. Objective and subjective evaluation was performed using the VCC2020 task, yielding MOS scores of up to 3.86, and character error rates as low as 4.3\%. This was achieved with approximately half the number of model parameters, and up to 8 times faster decoding speed.

eess.AS↗

arXiv2020

Temporal Network Representation Learning via Historical Neighborhoods Aggregation

Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes such as authorship networks, while others support removal of nodes or edges such as internet data routing. If patterns exist in the changes of the network structure, we can better understand the relationships between nodes and the evolution of the network, which can be further leveraged to learn node representations with more meaningful information. In this paper, we propose the Embedding via Historical Neighborhoods Aggregation (EHNA) algorithm. More specifically, we first propose a temporal random walk that can identify relevant nodes in historical neighborhoods which have impact on edge formations. Then we apply a deep learning model which uses a custom attention mechanism to induce node embeddings that directly capture temporal information in the underlying feature representation. We perform extensive experiments on a range of real-world datasets, and the results demonstrate the effectiveness of our new approach in the network reconstruction task and the link prediction task.

cs.LG↗