Searcharxiv⌕ Search

arXiv subjects

Jing Yang

Publications and source records attributed to Jing Yang.

At least 163 records · Page 9Linked to original sources
arXiv2025

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias

Language recognition tasks are fundamental in natural language processing (NLP) and have been widely used to benchmark the performance of large language models (LLMs). These tasks also play a crucial role in explaining the working mechanisms of transformers. In this work, we focus on two representative tasks in the category of regular language recognition, known as `even pairs' and `parity check', the aim of which is to determine whether the occurrences of certain subsequences in a given sequence are even. Our goal is to explore how a one-layer transformer, consisting of an attention layer followed by a linear layer, learns to solve these tasks by theoretically analyzing its training dynamics under gradient descent. While even pairs can be solved directly by a one-layer transformer, parity check need to be solved by integrating Chain-of-Thought (CoT), either into the inference stage of a transformer well-trained for the even pairs task, or into the training of a one-layer transformer. For both problems, our analysis shows that the joint training of attention and linear layers exhibits two distinct phases. In the first phase, the attention layer grows rapidly, mapping data sequences into separable vectors. In the second phase, the attention layer becomes stable, while the linear layer grows logarithmically and approaches in direction to a max-margin hyperplane that correctly separates the attention layer outputs into positive and negative samples, and the loss decreases at a rate of $O(1/t)$. Our experiments validate those theoretical results.

cs.LG↗
arXiv2025

Observation of Coherent Perfect Acoustic Absorption at an Exceptional Point

Non-Hermitian systems have recently shown new possibilities to manipulate wave scattering by exploiting loss, yet coherent perfect absorption at an exceptional point (CPA EP) remains elusive in acoustics. Here we demonstrate it based on a two-channel waveguide with compact lossy resonators. We realize imbalanced losses crucial for CPA EP by using active components to independently modulate the non-Hermiticity. The CPA EP experimentally manifests as full absorption at a unique real frequency and shows high sensitivity to the incident phase variations.Our findings open an avenue to explore novel non-Hermitian physics for classical waves and develop innovative acoustic singularity-based devices.

physics.app-ph↗
arXiv2025

Acoustic topological Jackiw-Rebbi states at symmetry broken interfaces

Topological insulators, a fundamental concept in modern condensed matter physics, support localized states at the interfaces between insulators exhibiting different topological phases, which conventionally rely on explicit symmetry breaking. Here, we propose a mechanism to induce a real-space topological phase transition by spontaneous symmetry breaking, thereby constructing an acoustic metagrating to generate nontrivial Jackiw-Rebbi states characterized by robust imaginary band degeneracy. Our experimental implementation verifies the acoustic delocalized interface state with a constant phase jump, demonstrating enhanced high-directivity topological radiation. We foresee that our findings may spark interest in engineering new acoustic topological devices.

cond-mat.mes-hall↗
arXiv2025

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal context, redundant computations, and heavy memory requirements. To this end, we introduce a Temporal Video State Space Sharing (TV3S) architecture to leverage Mamba state space models for temporal feature sharing. Our model features a selective gating mechanism that efficiently propagates relevant information across video frames, eliminating the need for a memory-heavy feature pool. By processing spatial patches independently and incorporating shifted operation, TV3S supports highly parallel computation in both training and inference stages, which reduces the delay in sequential state space processing and improves the scalability for long video sequences. Moreover, TV3S incorporates information from prior frames during inference, achieving long-range temporal coherence and superior adaptability to extended sequences. Evaluations on the VSPW and Cityscapes datasets reveal that our approach outperforms current state-of-the-art methods, establishing a new standard for VSS with consistent results across long video sequences. By achieving a good balance between accuracy and efficiency, TV3S shows a significant advancement in spatiotemporal modeling, paving the way for efficient video analysis. The code is publicly available at https://github.com/Ashesham/TV3S.git.

eess.IV↗
arXiv2025

A Shared Low-Rank Adaptation Approach to Personalized RLHF

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF frameworks often assume that human preferences are relatively homogeneous and can be captured by a single, unified reward model. This assumption overlooks the inherent diversity and heterogeneity across individuals, limiting the adaptability of RLHF to personalized scenarios and risking misalignments that can diminish user satisfaction and trust in AI systems. In this paper, we address these challenges by introducing Low-Rank Adaptation (LoRA) into the personalized RLHF framework. We apply LoRA in the the aggregated parameter space of all personalized reward functions, thereby enabling efficient learning of personalized reward models from potentially limited local datasets. Our approach exploits potential shared structures among the local ground-truth reward models while allowing for individual adaptation, without relying on restrictive assumptions about shared representations as in prior works. We further establish sample complexity guarantees for our method. Theoretical analysis demonstrates the effectiveness of the proposed approach in capturing both shared and individual-specific structures within heterogeneous human preferences, addressing the dual challenge of personalization requirements and practical data constraints. Experimental results on real-world datasets corroborate the efficiency of our algorithm in the personalized RLHF setting.

cs.LG↗
arXiv2025

CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts

We introduce CHOrD, a novel framework for scalable synthesis of 3D indoor scenes, designed to create house-scale, collision-free, and hierarchically structured indoor digital twins. In contrast to existing methods that directly synthesize the scene layout as a scene graph or object list, CHOrD incorporates a 2D image-based intermediate layout representation, enabling effective prevention of collision artifacts by successfully capturing them as out-of-distribution (OOD) scenarios during generation. Furthermore, unlike existing methods, CHOrD is capable of generating scene layouts that adhere to complex floor plans with multi-modal controls, enabling the creation of coherent, house-wide layouts robust to both geometric and semantic variations in room structures. Additionally, we propose a novel dataset with expanded coverage of household items and room configurations, as well as significantly improved data quality. CHOrD demonstrates state-of-the-art performance on both the 3D-FRONT and our proposed datasets, delivering photorealistic, spatially coherent indoor scene synthesis adaptable to arbitrary floor plan variations.

cs.CV↗
arXiv2025

Exact Quantum Dynamics, Shortcuts to Adiabaticity, and Quantum Quenches in Strongly-Correlated Many-Body Systems: The Time-Dependent Jastrow Ansatz

The description of strongly correlated quantum many-body systems far from equilibrium presents a fundamental challenge due to the vast amount of information it requires. We introduce a generalization of the Jastrow ansatz for time-dependent wavefunctions that offers an efficient and exact description of the time evolution of various strongly correlated systems. Previously known exact solutions are characterized by scale invariance, enforcing self-similar evolution of local correlations, such as the spatial density. However, we demonstrate that a complex-valued time-dependent Jastrow ansatz (TDJA) is not restricted to scale invariance and can describe a broader class of dynamical processes lacking this symmetry. The associated time evolution is equivalent to the implementation of a shortcut to adiabaticity (STA) via counterdiabatic driving along a continuous manifold of quantum states described by a real-valued TDJA, providing a framework for engineering exact STA in strongly correlated many-body quantum systems. We illustrate our findings in systems with inverse-square interactions, such as the Calogero-Sutherland and hyperbolic models, supplemented with pairwise logarithmic interactions, as well as in the long-range Lieb-Liniger model, where bosons experience both contact and Coulomb interactions in one dimension. Our results enable the study of quench dynamics in all these models and serve as a benchmark for numerical and quantum simulations of nonequilibrium strongly correlated systems with continuous variables.

quant-ph↗
arXiv2025

Efficient Adapter Tuning for Joint Singing Voice Beat and Downbeat Tracking with Self-supervised Learning Features

Singing voice beat tracking is a challenging task, due to the lack of musical accompaniment that often contains robust rhythmic and harmonic patterns, something most existing beat tracking systems utilize and can be essential for estimating beats. In this paper, a novel temporal convolutional network-based beat-tracking approach featuring self-supervised learning (SSL) representations and adapter tuning is proposed to track the beat and downbeat of singing voices jointly. The SSL DistilHuBERT representations are utilized to capture the semantic information of singing voices and are further fused with the generic spectral features to facilitate beat estimation. Sources of variabilities that are particularly prominent with the non-homogeneous singing voice data are reduced by the efficient adapter tuning. Extensive experiments show that feature fusion and adapter tuning improve the performance individually, and the combination of both leads to significantly better performances than the un-adapted baseline system, with up to 31.6% and 42.4% absolute F1-score improvements on beat and downbeat tracking, respectively.

cs.SD↗
arXiv2025

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

Large Language Models (LLMs) rely on the contextual information embedded in examples/demonstrations to perform in-context learning (ICL). To mitigate the risk of LLMs potentially leaking private information contained in examples in the prompt, we introduce a novel data-adaptive differentially private algorithm called AdaDPSyn to generate synthetic examples from the private dataset and then use these synthetic examples to perform ICL. The objective of AdaDPSyn is to adaptively adjust the noise level in the data synthesis mechanism according to the inherent statistical properties of the data, thereby preserving high ICL accuracy while maintaining formal differential privacy guarantees. A key innovation in AdaDPSyn is the Precision-Focused Iterative Radius Reduction technique, which dynamically refines the aggregation radius - the scope of data grouping for noise addition - based on patterns observed in data clustering, thereby minimizing the amount of additive noise. We conduct extensive experiments on standard benchmarks and compare AdaDPSyn with DP few-shot generation algorithm (Tang et al., 2023). The experiments demonstrate that AdaDPSyn not only outperforms DP few-shot generation, but also maintains high accuracy levels close to those of non-private baselines, providing an effective solution for ICL with privacy protection.

cs.CR↗
arXiv2025

Optimal Local Measurements in Single-Parameter Quantum Metrology

Quantum measurement plays a crucial role in quantum metrology. Due to the limitations of experimental capabilities, collectively measuring multiple copies of probing systems can present significant challenges. Therefore, the concept of locality in quantum measurements must be considered. In this work, we investigate the possibility of achieving the Quantum Cramér-Rao Bound (QCRB) through local measurements (LM). We first demonstrate that if there exists a LM to saturate the QCRB for qubit systems, then we can construct another rank-1 local projective measurement to saturate the QCRB. In this sense, rank-1 local projective measurements are sufficient to analyze the problem of saturating the QCRB. For pure qubits, we propose two necessary and sufficient methods to determine whether and how a given parameter estimation model can achieve QCRB through LM. The first method, dubbed iterative matrix partition method (IMP) and based on unitary transformations that render the diagonal entries of a tracless matrix vanish, elucidates the underlying mathematical structure of LM as well as the local measurements with classical communications (LMCC), generalizing the result by [Zhou et al Quantum Sci. Technol. 5, 025005 (2020)], which only holds for the later case. We clarify that the saturation of QCRB through LM for the GHZ-encoded states is actually due to the self-similar structure in this approach. The second method, dubbed hierarchy of orthogonality conditions (HOC) and based on the parametrization of rank-1 measurements for qubit systems, allows us to construct several examples of saturating QCRB, including the three-qubit W states and $N$-qubit W states ($N \geq 3$). Our findings offer insights into achieving optimal performance in quantum metrology when measurement resources are limited.

quant-ph↗
arXiv2025

Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features

Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key features, significantly degrading SVC performance. Previous methods have attempted to address this by using more robust neural network-based melody extractors, but their performance drops sharply in the presence of complex accompaniment. Other approaches involve performing source separation before conversion, but this often introduces noticeable artifacts, leading to a significant drop in conversion quality and increasing the user's operational costs. To address these issues, we introduce a novel SVC method that uses self-supervised representation-based melody features to improve melody modeling accuracy in the presence of BGM. In our experiments, we compare the effectiveness of different self-supervised learning (SSL) models for melody extraction and explore for the first time how SSL benefits the task of melody extraction. The experimental results demonstrate that our proposed SVC model significantly outperforms existing baseline methods in terms of melody accuracy and shows higher similarity and naturalness in both subjective and objective evaluations across noisy and clean audio environments.

cs.SD↗
arXiv2025

Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks

Free-text explanations are expressive and easy to understand, but many datasets lack annotated explanation data, making it challenging to train models for explainable predictions. To address this, we investigate how to use existing explanation datasets for self-rationalization and evaluate models' out-of-distribution (OOD) performance. We fine-tune T5-Large and OLMo-7B models and assess the impact of fine-tuning data quality, the number of fine-tuning samples, and few-shot selection methods. The models are evaluated on 19 diverse OOD datasets across three tasks: natural language inference (NLI), fact-checking, and hallucination detection in abstractive summarization. For the generated explanation evaluation, we conduct a human study on 13 selected models and study its correlation with the Acceptability score (T5-11B) and three other LLM-based reference-free metrics. Human evaluation shows that the Acceptability score correlates most strongly with human judgments, demonstrating its effectiveness in evaluating free-text explanations. Our findings reveal: 1) few annotated examples effectively adapt models for OOD explanation generation; 2) compared to sample selection strategies, fine-tuning data source has a larger impact on OOD performance; and 3) models with higher label prediction accuracy tend to produce better explanations, as reflected by higher Acceptability scores.

cs.CL↗
arXiv2025

Average Reward Reinforcement Learning for Wireless Radio Resource Management

In this paper, we address a crucial but often overlooked issue in applying reinforcement learning (RL) to radio resource management (RRM) in wireless communications: the mismatch between the discounted reward RL formulation and the undiscounted goal of wireless network optimization. To the best of our knowledge, we are the first to systematically investigate this discrepancy, starting with a discussion of the problem formulation followed by simulations that quantify the extent of the gap. To bridge this gap, we introduce the use of average reward RL, a method that aligns more closely with the long-term objectives of RRM. We propose a new method called the Average Reward Off policy Soft Actor Critic (ARO SAC) is an adaptation of the well known Soft Actor Critic algorithm in the average reward framework. This new method achieves significant performance improvement our simulation results demonstrate a 15% gain in the system performance over the traditional discounted reward RL approach, underscoring the potential of average reward RL in enhancing the efficiency and effectiveness of wireless network optimization.

cs.IT↗
arXiv2025

Block-regularized 5$\times$2 Cross-validated McNemar's Test for Comparing Two Classification Algorithms

In the task of comparing two classification algorithms, the widely-used McNemar's test aims to infer the presence of a significant difference between the error rates of the two classification algorithms. However, the power of the conventional McNemar's test is usually unpromising because the hold-out (HO) method in the test merely uses a single train-validation split that usually produces a highly varied estimation of the error rates. In contrast, a cross-validation (CV) method repeats the HO method in multiple times and produces a stable estimation. Therefore, a CV method has a great advantage to improve the power of McNemar's test. Among all types of CV methods, a block-regularized 5$\times$2 CV (BCV) has been shown in many previous studies to be superior to the other CV methods in the comparison task of algorithms because the 5$\times$2 BCV can produce a high-quality estimator of the error rate by regularizing the numbers of overlapping records between all training sets. In this study, we compress the 10 correlated contingency tables in the 5$\times$2 BCV to form an effective contingency table. Then, we define a 5$\times$2 BCV McNemar's test on the basis of the effective contingency table. We demonstrate the reasonable type I error and the promising power of the proposed 5$\times$2 BCV McNemar's test on multiple simulated and real-world data sets.

cs.LG↗
arXiv2025

Robust Offline Reinforcement Learning for Non-Markovian Decision Processes

Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline dataset collected from a nominal model. While recent advances in robust RL focus on Markov decision processes (MDPs), robust non-Markovian RL is limited to planning problem where the transitions in the uncertainty set are known. In this paper, we study the learning problem of robust offline non-Markovian RL. Specifically, when the nominal model admits a low-rank structure, we propose a new algorithm, featuring a novel dataset distillation and a lower confidence bound (LCB) design for robust values under different types of the uncertainty set. We also derive new dual forms for these robust values in non-Markovian RL, making our algorithm more amenable to practical implementation. By further introducing a novel type-I concentrability coefficient tailored for offline low-rank non-Markovian decision processes, we prove that our algorithm can find an $ε$-optimal robust policy using $O(1/ε^2)$ offline samples. Moreover, we extend our algorithm to the case when the nominal model does not have specific structure. With a new type-II concentrability coefficient, the extended algorithm also enjoys polynomial sample efficiency under all different types of the uncertainty set.

cs.LG↗
arXiv2024

ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze

Monte Carlo Tree Search (MCTS)-based algorithms, such as MuZero and its derivatives, have achieved widespread success in various decision-making domains. These algorithms employ the reanalyze process to enhance sample efficiency from stale data, albeit at the expense of significant wall-clock time consumption. To address this issue, we propose a general approach named ReZero to boost tree search operations for MCTS-based algorithms. Specifically, drawing inspiration from the one-armed bandit model, we reanalyze training samples through a backward-view reuse technique which uses the value estimation of a certain child node to save the corresponding sub-tree search time. To further adapt to this design, we periodically reanalyze the entire buffer instead of frequently reanalyzing the mini-batch. The synergy of these two designs can significantly reduce the search cost and meanwhile guarantee or even improve performance, simplifying both data collecting and reanalyzing. Experiments conducted on Atari environments, DMControl suites and board games demonstrate that ReZero substantially improves training speed while maintaining high sample efficiency. The code is available as part of the LightZero MCTS benchmark at https://github.com/opendilab/LightZero.

cs.AI↗
arXiv2024

MarsSQE: Stereo Quality Enhancement for Martian Images Using Bi-level Cross-view Attention

Stereo images captured by Mars rovers are transmitted after lossy compression due to the limited bandwidth between Mars and Earth. Unfortunately, this process results in undesirable compression artifacts. In this paper, we present a novel stereo quality enhancement approach for Martian images, named MarsSQE. First, we establish the first dataset of stereo Martian images. Through extensive analysis of this dataset, we observe that cross-view correlations in Martian images are notably high. Leveraging this insight, we design a bi-level cross-view attention-based quality enhancement network that fully exploits these inherent cross-view correlations. Specifically, our network integrates pixel-level attention for precise matching and patch-level attention for broader contextual information. Experimental results demonstrate the effectiveness of our MarsSQE approach.

eess.IV↗