Search

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing. However, current researches lack investigation into the imperceptibility of watermarking techniques in LLM services. This is crucial as LLM providers may not want to disclose the presence of watermarks in real-world scenarios, as it could reduce user willingness to use the service and make watermarks more vulnerable to attacks. This work is the first to investigate the imperceptibility of watermarked LLMs. We design an identification algorithm called Water-Probe that detects watermarks through well-designed prompts to the LLM. Our key motivation is that current watermarked LLMs expose consistent biases under the same watermark key, resulting in similar differences across prompts under different watermark keys. Experiments show that almost all mainstream watermarking algorithms are easily identified with our well-designed prompts, while Water-Probe demonstrates a minimal false positive rate for non-watermarked LLMs. Finally, we propose that the key to enhancing the imperceptibility of watermarked LLMs is to increase the randomness of watermark key selection. Based on this, we introduce the Water-Bag strategy, which significantly improves watermark imperceptibility by merging multiple watermark keys., Comment: 25 pages, 5 figures, 8 tables

There has been an increasing research interest in cross-age speaker verification~(CASV). However, existing speaker verification systems perform poorly in CASV due to the great individual differences in voice caused by aging. In this paper, we propose a disentangled representation learning framework for CASV based on mutual information~(MI) minimization. In our method, a backbone model is trained to disentangle the identity- and age-related embeddings from speaker information, and an MI estimator is trained to minimize the correlation between age- and identity-related embeddings via MI minimization, resulting in age-invariant speaker embeddings. Furthermore, by using the age gaps between positive and negative samples, we propose an aging-aware MI minimization loss function that allows the backbone model to focus more on the vocal changes with large age gaps. Experimental results show that the proposed method outperforms other methods on multiple Cross-Age test sets of Vox-CA., Comment: Interspeech 2024

This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate content, timbre, and singing style. This approach enables precise voice characteristic manipulation. We discovered that datasets with fewer recordings per artist are more susceptible to timbre leakage. Extensive testing on over 10,000 hours of singing and user feedback revealed our model significantly improves sound quality and timbre accuracy, aligning with our objectives and advancing voice conversion technology. Furthermore, this research advances zero-shot SVC and sets the stage for future work on discrete speech representation, emphasizing the preservation of rhyme.

Large Language Models (LLMs) have demonstrated notable capabilities across various tasks, showcasing complex problem-solving abilities. Understanding and executing complex rules, along with multi-step planning, are fundamental to logical reasoning and critical for practical LLM agents and decision-making systems. However, evaluating LLMs as effective rule-based executors and planners remains underexplored. In this paper, we introduce LogicGame, a novel benchmark designed to evaluate the comprehensive rule understanding, execution, and planning capabilities of LLMs. Unlike traditional benchmarks, LogicGame provides diverse games that contain a series of rules with an initial state, requiring models to comprehend and apply predefined regulations to solve problems. We create simulated scenarios in which models execute or plan operations to achieve specific outcomes. These game scenarios are specifically designed to distinguish logical reasoning from mere knowledge by relying exclusively on predefined rules. This separation allows for a pure assessment of rule-based reasoning capabilities. The evaluation considers not only final outcomes but also intermediate steps, providing a comprehensive assessment of model performance. Moreover, these intermediate steps are deterministic and can be automatically verified. LogicGame defines game scenarios with varying difficulty levels, from simple rule applications to complex reasoning chains, in order to offer a precise evaluation of model performance on rule understanding and multi-step execution. Utilizing LogicGame, we test various LLMs and identify notable shortcomings in their rule-based logical reasoning abilities.

Instruction following is one of the fundamental capabilities of large language models (LLMs). As the ability of LLMs is constantly improving, they have been increasingly applied to deal with complex human instructions in real-world scenarios. Therefore, how to evaluate the ability of complex instruction-following of LLMs has become a critical research problem. Existing benchmarks mainly focus on modeling different types of constraints in human instructions while neglecting the composition of different constraints, which is an indispensable constituent in complex instructions. To this end, we propose ComplexBench, a benchmark for comprehensively evaluating the ability of LLMs to follow complex instructions composed of multiple constraints. We propose a hierarchical taxonomy for complex instructions, including 4 constraint types, 19 constraint dimensions, and 4 composition types, and manually collect a high-quality dataset accordingly. To make the evaluation reliable, we augment LLM-based evaluators with rules to effectively verify whether generated texts can satisfy each constraint and composition. Furthermore, we obtain the final evaluation score based on the dependency structure determined by different composition types. ComplexBench identifies significant deficiencies in existing LLMs when dealing with complex instructions with multiple constraints composition., Comment: 20 pages, 7 figures

We consider the three-dimensional rotating motions of neutron stars blown by the "axion wind". Neutron star precession and spin can change from the magnetic moment coupling to the oscillating axion background field, in analogy to the gyroscope motions with a driving force and the laboratory Nuclear Magnetic Resonance(NMR) detections of the axion. This effect modulates the pulse arrival time of the pulsar timing arrays. It shows up as a signal on the timing residual and two-point correlation function on the recent data of Nanograv and PPTA. The current measurement of PTAs can thus cast constraints on the axion-nucleon coupling as g_{ann} ~ 10^{-12}{GeV}^{-1}., Comment: 6 pages, 2 figures

Referring image segmentation (RIS) aims to locate the particular region corresponding to the language expression. Existing methods incorporate features from different modalities in a \emph{bottom-up} manner. This design may get some unnecessary image-text pairs, which leads to an inaccurate segmentation mask. In this paper, we propose a referring image segmentation method called HARIS, which introduces the Human-Like Attention mechanism and uses the parameter-efficient fine-tuning (PEFT) framework. To be specific, the Human-Like Attention gets a \emph{feedback} signal from multi-modal features, which makes the network center on the specific objects and discard the irrelevant image-text pairs. Besides, we introduce the PEFT framework to preserve the zero-shot ability of pre-trained encoders. Extensive experiments on three widely used RIS benchmarks and the PhraseCut dataset demonstrate that our method achieves state-of-the-art performance and great zero-shot ability.

Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks. The efficacy of DBP has been attributed to the forward diffusion process, which narrows the distribution gap between clean and adversarial images through the addition of Gaussian noise. Although this explanation has some theoretical support, the significance of its contribution to robustness remains unclear. In this paper, we argue that the inherent stochasticity in the DBP process is the primary driver of its robustness. To explore this, we introduce a novel Deterministic White-Box (DW-box) evaluation protocol to assess robustness in the absence of stochasticity and to analyze the attack trajectories and loss landscapes. Our findings suggest that DBP models primarily leverage stochasticity to evade effective attack directions, and their ability to purify adversarial perturbations can be weak. To further enhance the robustness of DBP models, we introduce Adversarial Denoising Diffusion Training (ADDT), which incorporates classifier-guided adversarial perturbations into diffusion training, thereby strengthening the DBP models' ability to purify adversarial perturbations. Additionally, we propose Rank-Based Gaussian Mapping (RBGM) to make perturbations more compatible with diffusion models. Experimental results validate the effectiveness of ADDT. In conclusion, our study suggests that future research on DBP can benefit from the perspective of decoupling the stochasticity-based and purification-based robustness.

Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to extreme video compression leveraging the predictive power of diffusion-based generative models at the decoder. The conditional diffusion model takes several neural compressed frames and generates subsequent frames. When the reconstruction quality drops below the desired level, new frames are encoded to restart prediction. The entire video is sequentially encoded to achieve a visually pleasing reconstruction, considering perceptual quality metrics such as the learned perceptual image patch similarity (LPIPS) and the Frechet video distance (FVD), at bit rates as low as 0.02 bits per pixel (bpp). Experimental results demonstrate the effectiveness of the proposed scheme compared to standard codecs such as H.264 and H.265 in the low bpp regime. The results showcase the potential of exploiting the temporal relations in video data using generative models. Code is available at: https://github.com/ElesionKyrie/Extreme-Video-Compression-With-Prediction-Using-Pre-trainded-Diffusion-Models-

Referring image segmentation (RIS) aims to segment a particular region based on a language expression prompt. Existing methods incorporate linguistic features into visual features and obtain multi-modal features for mask decoding. However, these methods may segment the visually salient entity instead of the correct referring region, as the multi-modal features are dominated by the abundant visual context. In this paper, we propose MARIS, a referring image segmentation method that leverages the Segment Anything Model (SAM) and introduces a mutual-aware attention mechanism to enhance the cross-modal fusion via two parallel branches. Specifically, our mutual-aware attention mechanism consists of Vision-Guided Attention and Language-Guided Attention, which bidirectionally model the relationship between visual and linguistic features. Correspondingly, we design a Mask Decoder to enable explicit linguistic guidance for more consistent segmentation with the language expression. To this end, a multi-modal query token is proposed to integrate linguistic information and interact with visual information simultaneously. Extensive experiments on three benchmark datasets show that our method outperforms the state-of-the-art RIS methods. Our code will be publicly available.

This paper is to consider a general low-rank signal plus noise model in high dimensional settings. Specifically, we consider the noise with a general covariance structure and the signal to be at the same magnitude as the noise. Our study focuses on exploring various asymptotic properties related to the spiked eigenvalues and eigenvectors. As applications, we propose a new criterion to estimate the number of clusters, and investigate the properties of spectral clustering.

Several pulsar timing array (PTA) experiments such as NANOGrav and PPTA reported evidence of a gravitational wave background at the nano-Hz frequency band recently. This signal can originate from scalar-induced gravitational waves (SIGW) generated by the enhanced curvature perturbation. Here we perform a joint likelihood inference on PTA datasets, and our results show that if the PTA signals were indeed of SIGW origin, the curvature perturbations amplitude required will produce primordial black holes (PBHs) in $[2 \times 10^{-5}, 2 \times 10^{-2}]\ m_\odot$ mass range. Mergers of these PBHs can leave a strong gravitational wave signature in the $[10^{-3}, 10^8]$ Hz frequency range, to be detectable at upcoming interferometers such as the Einstein Telescope, DECIGO and BBO, etc. This offers a multi-frequency opportunity to further scrutinize the source of the observed PTA signal., Comment: 7 pages, 5 figures

Partial scan is a common approach to accelerate Magnetic Resonance Imaging (MRI) data acquisition in both 2D and 3D settings. However, accurately reconstructing images from partial scan data (i.e., incomplete k-space matrices) remains challenging due to lack of an effectively global receptive field in both spatial and k-space domains. To address this problem, we propose the following: (1) a novel convolutional operator called Faster Fourier Convolution (FasterFC) to replace the two consecutive convolution operations typically used in convolutional neural networks (e.g., U-Net, ResNet). Based on the spectral convolution theorem in Fourier theory, FasterFC employs alternating kernels of size 1 in 3D case) in different domains to extend the dual-domain receptive field to the global and achieves faster calculation speed than traditional Fast Fourier Convolution (FFC). (2) A 2D accelerated MRI method, FasterFC-End-to-End-VarNet, which uses FasterFC to improve the sensitivity maps and reconstruction quality. (3) A multi-stage 3D accelerated MRI method called FasterFC-based Single-to-group Network (FAS-Net) that utilizes a single-to-group algorithm to guide k-space domain reconstruction, followed by FasterFC-based cascaded convolutional neural networks to expand the effective receptive field in the dual-domain. Experimental results on the fastMRI and Stanford MRI Data datasets demonstrate that FasterFC improves the quality of both 2D and 3D reconstruction. Moreover, FAS-Net, as a 3D high-resolution multi-coil (eight) accelerated MRI method, achieves superior reconstruction performance in both qualitative and quantitative results compared with state-of-the-art 2D and 3D methods.

Gravitational waves can generate electromagnetic effects inside a strong electric or magnetic field within the Standard Model and general relativity. Here we propose using a quarterly split cavity and LC(inductor and capacitor)-resonance circuit to detect a high-frequency gravitational wave from 0.1 MHz to GHz. We perform a full 3D simulation of the cavity's signal for sensitivity estimate. Our sensitivity depends on the coherence time scale of the high-frequency gravitational wave sources and the volume size of the split cavity. We discuss the resonant measurement schemes for narrow-band gravitational wave sources and also a non-resonance scheme for broadband signals. For a meter-sized split cavity under a 14 Tesla magnetic field, the LC resonance enhanced sensitivity to the gravitational wave strain is expected to reach $h\sim 10^{-20}$ around $10$ MHz., Comment: 8 pages, 7 figures. v2 added discussion and references.some natural units corrected,PRD version