201 citations · 374 across the 45 of their papers we have counts for
50 papers
Cortex: Consolidating Context into Parametric Memory
Jintian Zhang, Feng He, Xinnian Liang +5
Context can improve large language model performance, but these gains may be lost after context removal. Inspired by biological systems consolidation, we formulate Memory Consolida…
Harness Learning Enables Generalizable Test-Time Adaptation
Alvin Zhang, Xuecheng Liu, Zixuan Wang +6
A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks c…
Message Passing Enables Efficient Reasoning
Xuecheng Liu, Daman Arora, Gokul Swamy +1
While inference-time scaling has improved the reasoning abilities of large language models (LLMs), the need to generate long chains-of-thought (CoTs) is a computational bottleneck.…
RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations
Hieu-Thi Luong, Xuechen Liu, Ivan Kukanov +2
RADAR Challenge 2026 is an APSIPA Grand Challenge on Robust Audio Deepfake Recognition under Media Transformations, designed to simulate realistic media conditions in real-world au…
Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room Task
Yurui Dong, Ziyue Wang, Shuyun Lu +5
Multimodal Large Language Models (MLLMs) have recently made rapid progress toward unified Omni models that integrate vision, language, and audio. However, existing environments lar…
Training Dynamics-Aware Multi-Factor Curriculum Learning for Target Speaker Extraction
Yun Liu, Xuechen Liu, Xiaoxiao Miao +1
Target speaker extraction (TSE) aims to isolate a specific speaker's voice from multi-speaker mixtures. Despite strong benchmark results, real-world performance often degrades due…
Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper
Hoan My Tran, Xin Wang, Wanying Ge +2
Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While…
ASVspoof 5: Evaluation of Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
Xin Wang, Héctor Delgado, Nicholas Evans +8
ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake detection solutions. A significant change from previous challenge…
WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection
Xi Xuan, Xuechen Liu, Wenxin Zhang +3
Modern front-end design for speech deepfake detection relies on full fine-tuning of large pre-trained models like XLSR. However, this approach is not parameter-efficient and may le…
Can External Sources Help the Knowledge Cut-off Issues in Audio Deepfake Detection?
Xuechen Liu, Xin Wang, Junichi Yamagishi +1
In conventional deepfake audio detection pipelines, inference and evaluation are typically conducted using standalone, parameterized models trained exclusively on a fixed dataset.…
SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution
Guoying Zhu, Meng Li, Haipeng Dai +6
The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consum…
LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
Xuechen Liu, Wanying Ge, Xin Wang +1
This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio…
From Sharpness to Better Generalization for Speech Deepfake Detection
Wen Huang, Xuechen Liu, Xin Wang +2
Generalization remains a critical challenge in speech deepfake detection (SDD). While various approaches aim to improve robustness, generalization is typically assessed through per…
Post-training for Deepfake Speech Detection
Wanying Ge, Xin Wang, Xuechen Liu +1
We introduce a post-training approach that adapts self-supervised learning (SSL) models for deepfake speech detection by bridging the gap between general pre-training and domain-sp…
Quantifying Source Speaker Leakage in One-to-One Voice Conversion
Scott Wellington, Xuechen Liu, Junichi Yamagishi
Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence…
ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
Xin Wang, Héctor Delgado, Hemlata Tak +26
ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake attacks as well as the design of detection solutions. We introduce…
Explaining Speaker and Spoof Embeddings via Probing
Xuechen Liu, Junichi Yamagishi, Md Sahidullah +1
This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as…
Libri2Vox Dataset: Target Speaker Extraction with Diverse Speaker Conditions and Synthetic Data
Yun Liu, Xuechen Liu, Xiaoxiao Miao +1
Target speaker extraction (TSE) is essential in speech processing applications, particularly in scenarios with complex acoustic environments. Current TSE systems face challenges in…
Improving curriculum learning for target speaker extraction with synthetic speakers
Yun Liu, Xuechen Liu, Junichi Yamagishi
Target speaker extraction (TSE) aims to isolate individual speaker voices from complex speech environments. The effectiveness of TSE systems is often compromised when the speaker c…
Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion
Zhengyang Chen, Shuai Wang, Mingyang Zhang +3
Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens,…
AfriHuBERT: A self-supervised speech representation model for African languages
Jesujoba O. Alabi, Xuechen Liu, Dietrich Klakow +1
In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African l…
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
Hanjun Luo, Yingbin Jin, Xinfeng Li +6
The advancements of Large Language Models (LLMs) have spurred a growing interest in their application to Named Entity Recognition (NER) methods. However, existing datasets are prim…
A Preliminary Case Study on Long-Form In-the-Wild Audio Spoofing Detection
Xuechen Liu, Xin Wang, Junichi Yamagishi
Audio spoofing detection has become increasingly important due to the rise in real-world cases. Current spoofing detectors, referred to as spoofing countermeasures (CM), are mainly…
ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
Xin Wang, Hector Delgado, Hemlata Tak +10
ASVspoof 5 is the fifth edition in a series of challenges that promote the study of speech spoofing and deepfake attacks, and the design of detection solutions. Compared to previou…