arXiv subjects

Jingyu Liu

Publications and source records attributed to Jingyu Liu.

At least 55 records · Page 3Linked to original sources

arXiv2026

SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning

In this work, we propose Salient Sparse Federated Learning (SSFL), a streamlined approach for sparse federated learning with efficient communication. SSFL identifies a sparse subnetwork prior to training, leveraging parameter saliency scores computed separately on local client data in non-IID scenarios, and then aggregated, to determine a global mask. Only the sparse model weights are trained and communicated each round between the clients and the server. On standard benchmarks including CIFAR-10, CIFAR-100, and Tiny-ImageNet, SSFL consistently improves the accuracy sparsity trade off, achieving more than 20\% relative error reduction on CIFAR-10 compared to the strongest sparse baseline, while reducing communication costs by $2 \times$ relative to dense FL. Finally, in a real-world federated learning deployment, SSFL delivers over $2.3 \times$ faster communication time, underscoring its practical efficiency.

cs.LG↗

arXiv2026

Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement Learning

Reinforcement learning (RL) is a dominant paradigm for training autonomous agents, yet these agents often exhibit poor generalization, failing to adapt to scenarios not seen during training. In this work, we identify a fundamental cause of this brittleness, a phenomenon which we term "gradient coupling." We hypothesize that in complex agentic tasks, the high similarity between distinct states leads to destructive interference between gradients. Specifically, a gradient update that reinforces an optimal action in one state can inadvertently increase the likelihood of a suboptimal action in a similar, yet different, state. To solve this, we propose a novel objective where the actor is trained to simultaneously function as a classifier that separates good and bad actions. This auxiliary pressure compels the model to learn disentangled embeddings for positive and negative actions, which mitigates negative gradient interference and improve the generalization performance. Extensive experiments demonstrate the effectiveness of our method.

cs.AI↗

arXiv2026

Tackling the Inherent Difficulty of Noise Filtering in RAG

Retrieval-Augmented Generation (RAG) has become a widely adopted approach to enhance Large Language Models (LLMs) by incorporating external knowledge and reducing hallucinations. However, noisy or irrelevant documents are often introduced during RAG, potentially degrading performance and even causing hallucinated outputs. While various methods have been proposed to filter out such noise, we argue that identifying irrelevant information from retrieved content is inherently difficult and limited number of transformer layers can hardly solve this. Consequently, retrievers fail to filter out irrelevant documents entirely. Therefore, LLMs must be robust against such noise, but we demonstrate that standard fine-tuning approaches are often ineffective in enabling the model to selectively utilize relevant information while ignoring irrelevant content due to the structural constraints of attention patterns. To address this, we propose a novel fine-tuning method designed to enhance the model's ability to distinguish between relevant and irrelevant information within retrieved documents. Extensive experiments across multiple benchmarks show that our approach significantly improves the robustness and performance of LLMs.

cs.CL↗

arXiv2025

Deep Deterministic Nonlinear ICA via Total Correlation Minimization with Matrix-Based Entropy Functional

Blind source separation, particularly through independent component analysis (ICA), is widely utilized across various signal processing domains for disentangling underlying components from observed mixed signals, owing to its fully data-driven nature that minimizes reliance on prior assumptions. However, conventional ICA methods rely on an assumption of linear mixing, limiting their ability to capture complex nonlinear relationships and to maintain robustness in noisy environments. In this work, we present deep deterministic nonlinear independent component analysis (DDICA), a novel deep neural network-based framework designed to address these limitations. DDICA leverages a matrix-based entropy function to directly optimize the independence criterion via stochastic gradient descent, bypassing the need for variational approximations or adversarial schemes. This results in a streamlined training process and improved resilience to noise. We validated the effectiveness and generalizability of DDICA across a range of applications, including simulated signal mixtures, hyperspectral image unmixing, modeling of primary visual receptive fields, and resting-state functional magnetic resonance imaging (fMRI) data analysis. Experimental results demonstrate that DDICA effectively separates independent components with high accuracy across a range of applications. These findings suggest that DDICA offers a robust and versatile solution for blind source separation in diverse signal processing tasks.

stat.ME↗

arXiv2025

A Superfast Direct Solver for Type-III Inverse Nonuniform Discrete Fourier Transform

The nonuniform discrete Fourier transform (NUDFT) and its inverse are widely used in various fields of scientific computing. In this article, we propose a novel superfast direct inversion method for type-III NUDFT. The proposed method approximates the type-III NUDFT matrix as a product of a type-II NUDFT matrix and an HSS matrix, where the type-II NUDFT matrix is further decomposed into the product of an HSS matrix and an uniform discrete Fourier transform (DFT) matrix as in [Wilber, Epperly, and Barnett, SIAM Journal on Scientific Computing, 47(3):A1702-A1732, 2025]. This decomposition enables both the forward application and the backward inversion to be accomplished with quasi-linear complexity. The fast inversion can serve as a high-accuracy direct solver or as an efficient preconditioner. Additionally, we provide an error bound for the approximation under specific sample distributions. Numerical results are presented to verify the relevant theoretical properties and demonstrate the efficiency of the proposed methods.

math.NA↗

arXiv2025

TiDAR: Think in Diffusion, Talk in Autoregression

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question: can we achieve a synergy with high throughput, higher GPU utilization, and AR level quality? Existing methods fail to effectively balance these two aspects, either prioritizing AR using a weaker model for sequential drafting (speculative decoding), leading to lower drafting efficiency, or using some form of left-to-right (AR-like) decoding logic for diffusion, which still suffers from quality degradation and forfeits its potential parallelizability. We introduce TiDAR, a sequence-level hybrid architecture that drafts tokens (Thinking) in Diffusion and samples final outputs (Talking) AutoRegressively - all within a single forward pass using specially designed structured attention masks. This design exploits the free GPU compute density, achieving a strong balance between drafting and verification capacity. Moreover, TiDAR is designed to be serving-friendly (low overhead) as a standalone model. We extensively evaluate TiDAR against AR models, speculative decoding, and diffusion variants across generative and likelihood tasks at 1.5B and 8B scales. Thanks to the parallel drafting and sampling as well as exact KV cache support, TiDAR outperforms speculative decoding in measured throughput and surpasses diffusion models like Dream and Llada in both efficiency and quality. Most notably, TiDAR is the first architecture to close the quality gap with AR models while delivering 4.71x to 5.91x more tokens per second.

cs.CL↗

arXiv2025

Efficient Brain Network Estimation with Sparse ICA in Non-Human Primate Neuroimaging

Independent component analysis (ICA) is widely used to separate mixed signals and recover statistically independent components. However, in non-human primate neuroimaging studies, most ICA-recovered spatial maps are often dense. To extract the most relevant brain activation patterns, post-hoc thresholding is typically applied-though this approach is often imprecise and arbitrary. To address this limitation, we employed the Sparse ICA method, which enforces both sparsity and statistical independence, allowing it to extract the most relevant activation maps without requiring additional post-processing. Simulation experiments demonstrate that Sparse ICA performs competitively against 11 classical linear ICA methods. We further applied Sparse ICA to real non-human primate neuroimaging data, identifying several independent component networks spanning different brain networks. These spatial maps revealed clearly defined activation areas, providing further evidence that Sparse ICA is effective and reliable in practical applications.

stat.AP↗

arXiv2025

Breast Cancer Detection in Thermographic Images via Diffusion-Based Augmentation and Nonlinear Feature Fusion

Data scarcity hinders deep learning for medical imaging. We propose a framework for breast cancer classification in thermograms that addresses this using a Diffusion Probabilistic Model (DPM) for data augmentation. Our DPM-based augmentation is shown to be superior to both traditional methods and a ProGAN baseline. The framework fuses deep features from a pre-trained ResNet-50 with handcrafted nonlinear features (e.g., Fractal Dimension) derived from U-Net segmented tumors. An XGBoost classifier trained on these fused features achieves 98.0\% accuracy and 98.1\% sensitivity. Ablation studies and statistical tests confirm that both the DPM augmentation and the nonlinear feature fusion are critical, statistically significant components of this success. This work validates the synergy between advanced generative models and interpretable features for creating highly accurate medical diagnostic tools.

cs.CV↗

arXiv2025

Your Trust, Your Terms: A General Paradigm for Near-Instant Cross-Chain Transfer

Cross-chain transactions today remain slow, costly, and fragmented. Existing custodial exchanges expose users to counterparty and centralization risks, while non-custodial liquidity bridges suffer from capital inefficiency and slow settlement; critically, neither approach guarantees users a unilateral path to recover assets if the infrastructure fails. We introduce the Delegated Ownership Transfer (DOT) paradigm, which decouples key ownership from value ownership to enable secure, high-performance cross-chain payments. In DOT, a user deposits funds into a sandboxed on-chain Temporary Account (TA) (value ownership) while delegating its private key (key ownership) to an abstract Trusted Entity (TE). Payments and swaps are thus reframed as near-instant, off-chain ownership handoffs. Security follows from dual guarantees: the TE's exclusive control prevents double-spending, while a pre-signed, unilateral recovery transaction ensures users retain ultimate authority over their assets. Building on this foundation, we design a novel off-chain atomic swap that executes optimistically in near real time and remains fair even if the TE fails. We formalize the security of DOT in the Universal Composability framework and present two concrete instantiations: a high-performance design based on Trusted Execution Environments (TEEs) and a cryptographically robust variant leveraging threshold cryptography. Our geo-distributed prototype shows that cross-chain payments complete in under 16.70 ms and atomic swaps in under 33.09 ms, with costs fully decoupled from Layer-1 gas fees. These results provide a practical blueprint for building secure, efficient, and interoperable cross-chain payment systems.

cs.CR↗

arXiv2025

EdgeAttNet: Towards Barb-Aware Filament Segmentation

Accurate segmentation of solar filaments in H-alpha observations is critical for determining filament chirality, a key factor in the behavior of Coronal Mass Ejections (CMEs). However, existing methods often fail to capture fine-scale filament structures, particularly barbs, due to a limited ability to model long-range dependencies and spatial detail. We propose EdgeAttNet, a segmentation architecture built on a U-Net backbone by introducing a novel, learnable edge map derived directly from the input image. This edge map is incorporated into the model by linearly transforming the attention Key and Query matrices with the edge information, thereby guiding the self-attention mechanism at the network's bottleneck to more effectively capture filament boundaries and barbs. By explicitly integrating this structural prior into the attention computations, EdgeAttNet enhances spatial sensitivity and segmentation accuracy while reducing the number of trainable parameters. Trained end-to-end, EdgeAttNet outperforms U-Net and other U-Net-based transformer baselines on the MAGFILO dataset. It achieves higher segmentation accuracy and significantly better recognition of filament barbs, with faster inference performance suitable for practical deployment.

cs.CV↗

arXiv2025

PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis

Missing modalities pose a major issue in Alzheimer's Disease (AD) diagnosis, as many subjects lack full imaging data due to cost and clinical constraints. While multi-modal learning leverages complementary information, most existing methods train only on complete data, ignoring the large proportion of incomplete samples in real-world datasets like ADNI. This reduces the effective training set and limits the full use of valuable medical data. While some methods incorporate incomplete samples, they fail to effectively address inter-modal feature alignment and knowledge transfer challenges under high missing rates. To address this, we propose a Prototype-Guided Adaptive Distillation (PGAD) framework that directly incorporates incomplete multi-modal data into training. PGAD enhances missing modality representations through prototype matching and balances learning with a dynamic sampling strategy. We validate PGAD on the ADNI dataset with varying missing rates (20%, 50%, and 70%) and demonstrate that it significantly outperforms state-of-the-art approaches. Ablation studies confirm the effectiveness of prototype matching and adaptive sampling, highlighting the potential of our framework for robust and scalable AD diagnosis in real-world clinical settings.

eess.IV↗

arXiv2025

Hierarchical Tucker Low-Rank Matrices: Construction and Matrix-Vector Multiplication

In this paper, a hierarchical Tucker low-rank (HTLR) matrix is proposed to approximate non-oscillatory kernel functions in linear complexity. The HTLR matrix is based on the hierarchical matrix, with the low-rank blocks replaced by Tucker low-rank blocks. Using high-dimensional interpolation as well as tensor contractions, algorithms for the construction and matrix-vector multiplication of HTLR matrices are proposed admitting linear and quasi-linear complexities respectively. Numerical experiments demonstrate that the HTLR matrix performs well in both memory and runtime. Furthermore, the HTLR matrix can also be applied on quasi-uniform grids in addition to uniform grids, enhancing its versatility.

math.NA↗

arXiv2025

Multi-Object Sketch Animation by Scene Decomposition and Motion Planning

Sketch animation, which brings static sketches to life by generating dynamic video sequences, has found widespread applications in GIF design, cartoon production, and daily entertainment. While current methods for sketch animation perform well in single-object sketch animation, they struggle in multi-object scenarios. By analyzing their failures, we identify two major challenges of transitioning from single-object to multi-object sketch animation: object-aware motion modeling and complex motion optimization. For multi-object sketch animation, we propose MoSketch based on iterative optimization through Score Distillation Sampling (SDS) and thus animating a multi-object sketch in a training-data free manner. To tackle the two challenges in a divide-and-conquer strategy, MoSketch has four novel modules, i.e., LLM-based scene decomposition, LLM-based motion planning, multi-grained motion refinement, and compositional SDS. Extensive qualitative and quantitative experiments demonstrate the superiority of our method over existing sketch animation approaches. MoSketch takes a pioneering step towards multi-object sketch animation, opening new avenues for future research and applications.

cs.CV↗

arXiv2025

Music Grounding by Short Video

Adding proper background music helps complete a short video to be shared. Previous work tackles the task by video-to-music retrieval (V2MR), aiming to find the most suitable music track from a collection to match the content of a given query video. In practice, however, music tracks are typically much longer than the query video, necessitating (manual) trimming of the retrieved music to a shorter segment that matches the video duration. In order to bridge the gap between the practical need for music moment localization and V2MR, we propose a new task termed Music Grounding by Short Video (MGSV). To tackle the new task, we introduce a new benchmark, MGSV-EC, which comprises a diverse set of 53k short videos associated with 35k different music moments from 4k unique music tracks. Furthermore, we develop a new baseline method, MaDe, which performs both video-to-music matching and music moment detection within a unified end-to-end deep network. Extensive experiments on MGSV-EC not only highlight the challenging nature of MGSV but also set MaDe as a strong baseline.

cs.MM↗

arXiv2025

Do not Abstain! Identify and Solve the Uncertainty

Despite the widespread application of Large Language Models (LLMs) across various domains, they frequently exhibit overconfidence when encountering uncertain scenarios, yet existing solutions primarily rely on evasive responses (e.g., "I don't know") overlooks the opportunity of identifying and addressing the uncertainty to generate more satisfactory responses. To systematically investigate and improve LLMs' ability of recognizing and addressing the source of uncertainty, we introduce \textbf{ConfuseBench}, a benchmark mainly focus on three types of uncertainty: document scarcity, limited capability, and query ambiguity. Experiments with ConfuseBench reveal that current LLMs struggle to accurately identify the root cause of uncertainty and solve it. They prefer to attribute uncertainty to query ambiguity while overlooking capability limitations, especially for those weaker models. To tackle this challenge, we first generate context-aware inquiries that highlight the confusing aspect of the original query. Then we judge the source of uncertainty based on the uniqueness of the inquiry's answer. Further we use an on-policy training method, InteractDPO to generate better inquiries. Experimental results demonstrate the efficacy of our approach.

cs.AI↗

arXiv2025

Cross-Chain Options: A Bridgeless, Universal, and Efficient Approach

Options are fundamental to blockchain-based financial services, offering essential tools for risk management and price speculation, which enhance liquidity, flexibility, and market efficiency in decentralized finance (DeFi). Despite the growing interest in options for blockchain-resident assets, such as cryptocurrencies, current option mechanisms face significant challenges, including a high reliance on trusted third parties, limited asset support, high trading delays, and the requirement for option holders to provide upfront collateral. In this paper, we present a protocol that addresses the aforementioned issues. Our protocol is the first to eliminate the need for holders to post collateral when establishing options in trustless service environments (i.e. without a cross-chain bridge), which is achieved by introducing a guarantee from the option writer. Its universality allows for cross-chain options involving nearly \textit{any} assets on \textit{any} two different blockchains, provided the chains' programming languages can enforce and execute the necessary contract logic. Another key innovation is reducing option position transfer latency, which uses Double-Authentication-Preventing Signatures (DAPS). Our evaluation demonstrates that the proposed scheme reduces option transfer latency to less than half of that in existing methods. Rigorous security analysis proves that our protocol achieves secure option trading, even when facing adversarial behaviors.

cs.CR↗

arXiv2025

HAMburger: Accelerating LLM Inference via Token Smashing

The growing demand for efficient Large Language Model (LLM) inference requires a holistic optimization on algorithms, systems, and hardware. However, very few works have fundamentally changed the generation pattern: each token needs one forward pass and one KV cache. This can be sub-optimal because we found that LLMs are extremely capable of self-identifying the exact dose of information that a single KV cache can store, and many tokens can be generated confidently without global context. Based on this insight, we introduce HAMburger, a Hierarchically Auto-regressive Model that redefines resource allocation in LLMs by moving beyond uniform computation and storage per token during inference. Stacking a compositional embedder and a micro-step decoder in between a base LLM, HAMburger smashes multiple tokens into a single KV and generates several tokens per step. Additionally, HAMburger functions as a speculative decoding framework where it can blindly trust self-drafted tokens. As a result, HAMburger shifts the growth of KV cache and forward FLOPs from linear to sub-linear with respect to output length, and adjusts its inference speed based on query perplexity and output structure. Extensive evaluations show that HAMburger reduces the KV cache computation by up to 2$\times$ and achieves up to 2$\times$ TPS, while maintaining quality in both short- and long-context tasks. Our method explores an extremely challenging inference regime that requires both computation- and memory-efficiency with a hardware-agnostic design.

cs.CL↗

arXiv2025

Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits

We study the stochastic linear bandit problem with multiple arms over $T$ rounds, where the covariate dimension $d$ may exceed $T$, but each arm-specific parameter vector is $s$-sparse. We begin by analyzing the sequential estimation problem in the single-arm setting, focusing on cumulative mean-squared error. We show that Lasso estimators are provably suboptimal in the sequential setting, exhibiting suboptimal dependence on $d$ and $T$, whereas thresholded Lasso estimators -- obtained by applying least squares to the support selected by thresholding an initial Lasso estimator -- achieve the minimax rate. Building on these insights, we consider the full linear contextual bandit problem and propose a three-stage arm selection algorithm that uses thresholded Lasso as the main estimation method. We derive an upper bound on the cumulative regret of order $s(\log s)(\log d + \log T)$, and establish a matching lower bound up to a $\log s$ factor, thereby characterizing the minimax regret rate up to a logarithmic term in $s$. Moreover, when a short initial period is excluded from the regret, the proposed algorithm achieves exact minimax optimality.

math.ST↗