Related papers: Full-Duplex-Bench-v3: Benchmarking Tool Use for Fu…

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes…

Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as speech. However, their evaluation is often limited to English and a few high-resource languages. For…

We introduce GraphicDesignBench (GDB), the first comprehensive benchmark suite designed specifically to evaluate AI models on the full breadth of professional graphic design tasks. Unlike existing benchmarks that focus on natural-image…

With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap,…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

We introduce DafnyBench, the largest benchmark of its kind for training and evaluating machine learning systems for formal software verification. We test the ability of LLMs such as GPT-4 and Claude 3 to auto-generate enough hints for the…

Sub-band models have achieved promising results due to their ability to model local patterns in the spectrogram. Some studies further improve the performance by fusing sub-band and full-band information. However, the structure for the…

We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the…

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context…

Autonomous systems conducting schema-grounded information-gathering dialogues face an instrumentation gap, lacking turn-level observables for monitoring acquisition efficiency and detecting when questioning becomes unproductive. We…

AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised binary detectors. We train transformer-based detectors on…

Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient…

The rapid advancement of native multi-modal models and omni-models, exemplified by GPT-4o, Gemini, and o3, with their capability to process and generate content across modalities such as text and images, marks a significant milestone in the…

The two-dimensional (2D) numerical approaches for vocal tract (VT) modelling can afford a better balance between the low computational cost and accurate rendering of acoustic wave propagation. However, they require a high spatio-temporal…

Existing Audio Deepfake Detection (ADD) systems often struggle to generalise effectively due to the significantly degraded audio quality caused by audio codec compression and channel transmission effects in real-world communication…

While Large Language Models (LLMs) are increasingly envisioned as intelligent assistants for personalized learning, systematic head-to-head evaluations in authentic learning scenarios remain scarce. This study presents an empirical…

This technical report describes Johns Hopkins University speaker recognition system submitted to Voxceleb Speaker Recognition Challenge 2021 Track 3: Self-supervised speaker verification (closed). Our overall training process is similar to…

We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function…

FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…

Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture…