Searcharxiv⌕ Search

arXiv subjects

Kai Li

Publications and source records attributed to Kai Li.

At least 109 records · Page 6Linked to original sources
arXiv2026

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

In recent years, much speech separation research has focused primarily on improving model performance. However, for low-latency speech processing systems, high efficiency is equally important. Therefore, we propose a speech separation model with significantly reduced parameters and computational costs: Time-frequency Interleaved Gain Extraction and Reconstruction network (TIGER). TIGER leverages prior knowledge to divide frequency bands and compresses frequency information. We employ a multi-scale selective attention module to extract contextual features while introducing a full-frequency-frame attention module to capture both temporal and frequency contextual information. Additionally, to more realistically evaluate the performance of speech separation models in complex acoustic environments, we introduce a dataset called EchoSet. This dataset includes noise and more realistic reverberation (e.g., considering object occlusions and material properties), with speech from two speakers overlapping at random proportions. Experimental results showed that models trained on EchoSet had better generalization ability than those trained on other datasets compared to the data collected in the physical world, which validated the practical value of the EchoSet. On EchoSet and real-world data, TIGER significantly reduces the number of parameters by 94.3% and the MACs by 95.3% while achieving performance surpassing the state-of-the-art (SOTA) model TF-GridNet.

cs.SD↗
arXiv2026

LLM4AD: A Platform for Algorithm Design with Large Language Model

We introduce LLM4AD, a unified Python platform for algorithm design (AD) with large language models (LLMs). LLM4AD is a generic framework with modularized blocks for search methods, algorithm design tasks, and LLM interface. The platform integrates numerous key methods and supports a wide range of algorithm design tasks across various domains including optimization, machine learning, and scientific discovery. We have also designed a unified evaluation sandbox to ensure a secure and robust assessment of algorithms. Additionally, we have compiled a comprehensive suite of support resources, including tutorials, examples, a user manual, online resources, and a dedicated graphical user interface (GUI) to enhance the usage of LLM4AD. We believe this platform will serve as a valuable tool for fostering future development in the merging research direction of LLM-assisted algorithm design.

cs.AI↗
arXiv2026

SCOPE: Skeleton Graph-Based Computation-Efficient Framework for Autonomous UAV Exploration

Autonomous exploration in unknown environments is key for mobile robots, helping them perceive, map, and make decisions in complex areas. However, current methods often rely on frequent global optimization, suffering from high computational latency and trajectory oscillation, especially on resource-constrained edge devices. To address these limitations, we propose SCOPE, a novel framework that incrementally constructs a real-time skeletal graph and introduces Implicit Unknown Region Analysis for efficient spatial reasoning. The planning layer adopts a hierarchical on-demand strategy: the Proximal Planner generates smooth, high-frequency local trajectories, while the Region-Sequence Planner is activated only when necessary to optimize global visitation order. Comparative evaluations in simulation demonstrate that SCOPE achieves competitive exploration performance comparable to state-of-the-art global planners, while reducing computational cost by an average of 86.9%. Real-world experiments further validate the system's robustness and low latency in practical scenarios.

cs.RO↗
arXiv2026

A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation

We propose a knowledge-driven, model-based approach to segmenting audio into single-category and mixed-category chunks with applications to source separation. "Knowledge" here denotes information associated with the data, such as music scores. "Model" here refers to tool that can be used for audio segmentation and recognition, such as hidden Markov models. In contrast to conventional learning that often relies on annotated data with given segment categories and their corresponding boundaries to guide the learning process, the proposed framework does not depend on any pre-segmented training data and learns directly from the input audio and its related knowledge sources to build all necessary models autonomously. Evaluation on simulation data shows that score-guided learning achieves very good music segmentation and separation results. Tested on movie track data for cinematic audio source separation also shows that utilizing sound category knowledge achieves better separation results than those obtained with data-driven techniques without using such information.

eess.AS↗
arXiv2026

A Photometric and Spectroscopic investigation of 11 TESS eclipsing contact binaries

By cross-matching the eclipsing binary catalog provided by Prsa et al. (2022) with LAMOST medium resolution spectra, we obtained 11 targets. Combining light and radial velocity curves analysis, we have derived accurate physical parameters for these 11 targets. The results indicate that there are 3 deep contact binaries, 3 moderate ones, and 5 shallow ones. Among them, 3 targets exhibit the O'Connell effect, which is attributed to the presence of star-spot on the component's surface. One target is a low-mass ratio deep contact binary and may be contact binary merging candidates. The evolutionary status of these 11 targets was studied using the mass-luminosity and mass-radius relation diagrams. Based on the O-C (Observed minus Calculated) analysis of 10 targets, we found that the orbital periods of 5 contact binaries show a long-term decreasing trend, likely due to the combined effects of mass transfer between the two components and loss of angular momentum. Meanwhile, the orbital periods of the other 4 stars are continuously increasing, which is attributed to mass transfer. Besides, the O-C curves of 3 targets show clear periodic changes, which might result from the Applegate mechanism or the light travel time effect.

astro-ph.SR↗
arXiv2026

Probing Ultralight Dark Matter at the Mega-Planck Scale with the Thorium Nuclear Clock

Ultralight dark matter is expected to induce oscillations of nuclear parameters. These oscillations are characterized by extremely weak couplings or high suppression scales, with the Planck scale - the characteristic scale of quantum gravity - serving as a natural benchmark. Probing this phenomenon requires systems with exceptional sensitivity to shifts in nuclear energies. The uniquely low-energy nuclear isomeric transition in ${}^{229}$Th provides such sensitivity: it directly probes the nuclear interaction and, owing to a near cancellation between electromagnetic and nuclear contributions, its response to changes in nuclear structure is greatly amplified. We devise and perform a new type of ultrasensitive search for dark matter which uses the precision nuclear spectroscopy at JILA to set the strongest bounds in the mass range $10^{-21}\,{\rm eV} \lesssim m_{\rm DM} \lesssim 10^{-19}\,{\rm eV}$. Our results probe effective interaction scales exceeding $10^6$ times the Planck scale (the Mega-Planck scale) and establish the ${}^{229}$Th system as the leading probe of dark matter couplings to the nuclear sector.

hep-ph↗
arXiv2026

From Prompts to Protection: Large Language Model-Enabled In-Context Learning for Smart Public Safety UAV

A public safety Uncrewed Aerial Vehicle (UAV) enhances situational awareness during emergency response. Its agility, mobility optimization, and ability to establish Line-of-Sight (LoS) communication make it increasingly important for managing emergencies such as disaster response, search and rescue, and wildfire monitoring. Although Deep Reinforcement Learning (DRL) has been used to optimize UAV navigation and control, its high training complexity, low sample efficiency, and the simulation-to-reality gap limit its practicality in public safety applications. Recent advances in Large Language Models (LLMs) present a promising alternative. With strong reasoning and generalization abilities, LLMs can adapt to new tasks through In-Context Learning (ICL), enabling task adaptation via natural language prompts and example-based guidance without retraining. Deploying LLMs at the network edge, rather than in the cloud, further reduces latency and preserves data privacy, making them suitable for real-time, mission-critical public safety UAVs. This paper proposes integrating LLM-assisted ICL with public safety UAVs to address key functions such as path planning and velocity control in emergency response. We present a case study on data collection scheduling, demonstrating that the LLM-assisted ICL framework can significantly reduce packet loss compared to conventional approaches while also mitigating potential jailbreaking vulnerabilities. Finally, we discuss LLM optimizers and outline future research directions. The ICL framework enables adaptive, context-aware decision-making for public safety UAVs, offering a lightweight and efficient solution to enhance UAV autonomy and responsiveness in emergencies.

cs.AI↗
arXiv2026

FRSICL: LLM-Enabled In-Context Learning Flight Resource Allocation for Fresh Data Collection in UAV-Assisted Wildfire Monitoring

Uncrewed Aerial Vehicles (UAVs) play a vital role in public safety, especially in monitoring wildfires, where early detection reduces environmental impact. In UAV-Assisted Wildfire Monitoring (UAWM) systems, jointly optimizing the data collection schedule and UAV velocity is essential to minimize the average Age of Information (AoI) for sensory data. Deep Reinforcement Learning (DRL) has been used for this optimization, but its limitations-including low sampling efficiency, discrepancies between simulation and real-world conditions, and complex training make it unsuitable for time-critical applications such as wildfire monitoring. Recent advances in Large Language Models (LLMs) provide a promising alternative. With strong reasoning and generalization capabilities, LLMs can adapt to new tasks through In-Context Learning (ICL), which enables task adaptation using natural language prompts and example-based guidance without retraining. This paper proposes a novel online Flight Resource Allocation scheme based on LLM-Enabled In-Context Learning (FRSICL) to jointly optimize the data collection schedule and UAV velocity along the trajectory in real time, thereby asymptotically minimizing the average AoI across all ground sensors. Unlike DRL, FRSICL generates data collection schedules and velocities using natural language task descriptions and feedback from the environment, enabling dynamic decision-making without extensive retraining. Simulation results confirm the effectiveness of FRSICL compared to state-of-the-art baselines, namely Proximal Policy Optimization, Block Coordinate Descent, and Nearest Neighbor.

cs.AI↗
arXiv2026

Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech

Early diagnosis of Alzheimer's Disease (AD) is crucial for delaying its progression. While AI-based speech detection is non-invasive and cost-effective, it faces a critical data efficiency dilemma due to medical data scarcity and privacy barriers. Therefore, we propose FAL-AD, a novel framework that synergistically integrates federated learning with data augmentation to systematically optimize data efficiency. Our approach delivers three key breakthroughs: First, absolute efficiency improvement through voice conversion-based augmentation, which generates diverse pathological speech samples via cross-category voice-content recombination. Second, collaborative efficiency breakthrough via an adaptive federated learning paradigm, maximizing cross-institutional benefits under privacy constraints. Finally, representational efficiency optimization by an attentive cross-modal fusion model, which achieves fine-grained word-level alignment and acoustic-textual interaction. Evaluated on ADReSSo, FAL-AD achieves a state-of-the-art multi-modal accuracy of 91.52%, outperforming all centralized baselines and demonstrating a practical solution to the data efficiency dilemma. Our source code is publicly available at https://github.com/smileix/fal-ad.

cs.CL↗
arXiv2026

Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery

Large language models (LLMs) have enabled rapid progress in automatic heuristic discovery (AHD), yet most existing methods are predominantly limited by static evaluation against fixed instance distributions, leading to potential overfitting and poor generalization under distributional shifts. We propose Algorithm Space Response Oracles (ASRO), a game-theoretic framework that reframes heuristic discovery as a program level co-evolution between solver and instance generator. ASRO models their interaction as a two-player zero-sum game, maintains growing strategy pools on both sides, and iteratively expands them via LLM-based best-response oracles against mixed opponent meta-strategies, thereby replacing static evaluation with an adaptive, self-generated curriculum. Across multiple combinatorial optimization domains, ASRO consistently outperforms static-training AHD baselines built on the same program search mechanisms, achieving substantially improved generalization and robustness on diverse and out-of-distribution instances.

cs.AI↗
arXiv2026

Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control

Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches rely on direct state-to-action mappings, which lack structured reasoning and planning, and thus generalize poorly to novel tasks or unseen UI layouts. We introduce Hi-Agent, a trainable hierarchical vision-language agent for mobile control, featuring a high-level reasoning model and a low-level action model that are jointly optimized. For efficient training, we reformulate multi-step decision-making as a sequence of single-step subgoals and propose a foresight advantage function, which leverages execution feedback from the low-level model to guide high-level optimization. This design alleviates the path explosion issue encountered by Group Relative Policy Optimization (GRPO) in long-horizon tasks and enables stable, critic-free joint training. Hi-Agent achieves a new State-Of-The-Art (SOTA) 87.9% task success rate on the Android-in-the-Wild (AitW) benchmark, significantly outperforming prior methods across three paradigms: prompt-based (AppAgent: 17.7%), supervised (Filtered BC: 54.5%), and reinforcement learning-based (DigiRL: 71.9%). It also demonstrates competitive zero-shot generalization on the ScreenSpot-v2 benchmark. On the more challenging AndroidWorld benchmark, Hi-Agent also scales effectively with larger backbones, showing strong adaptability in high-complexity mobile control scenarios.

cs.AI↗
arXiv2026

Stable but Wrong: When More Data Degrades Scientific Conclusions

Modern science increasingly relies on ever-growing observational datasets and automated inference pipelines, under the implicit belief that accumulating more data makes scientific conclusions more reliable. Here we show that this belief can fail in a fundamental and irreversible way. We identify a structural regime in which standard inference procedures converge smoothly, remain well calibrated, and pass conventional diagnostic checks, yet systematically converge to incorrect conclusions. This failure arises when the reliability of observations degrades in a manner that is intrinsically unobservable to the inference process itself. Using minimal synthetic experiments, we demonstrate that in this regime additional data do not correct error but instead amplify it, while residual-based and goodness-of-fit diagnostics remain misleadingly normal. These results reveal an intrinsic limit of data-driven science: stability, convergence, and confidence are not sufficient indicators of epistemic validity. We argue that inference cannot be treated as an unconditional consequence of data availability, but must instead be governed by explicit constraints on the integrity of the observational process.

cs.LG↗
arXiv2026

The holographic Fermions over the ionic lattice with CDW

We study the holographic Fermion as a probe over the background with ionic lattice, which may undergo a phase transition with the development of charge density wave by the spontaneous breaking of the translational symmetry. We focus on the structure of the Fermi surface within different Brillouin zones and demonstrate how the presence of CDW in the background affects the formation of the band gap in the momentum space. Specifically, we find the formation of the CDW enhances the amplitude of spectral function as well as the momentum of the Fermi surface. Furthermore, we are concerned with the change of the Fermi surface with the doping parameter as well as the lattice amplitude. Interestingly, we find that the radius of the Fermi surface expands with the increase of the doping parameter and finally may cross the first Brillouin zone. Additionally, the width of band gap becomes larger with the increase of the lattice amplitude as well, which is consistent with the observation in condensed matter experiments.

hep-th↗
arXiv2026

Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment

Traditional object detection systems are typically constrained to predefined categories, limiting their applicability in dynamic environments. In contrast, open-vocabulary object detection (OVD) enables the identification of objects from novel classes not present in the training set. Recent advances in visual-language modeling have led to significant progress of OVD. However, prior works face challenges in either adapting the single-scale image backbone from CLIP to the detection framework or ensuring robust visual-language alignment. We propose Visual-Language Detection (VLDet), a novel framework that revamps feature pyramid for fine-grained visual-language alignment, leading to improved OVD performance. With the VL-PUB module, VLDet effectively exploits the visual-language knowledge from CLIP and adapts the backbone for object detection through feature pyramid. In addition, we introduce the SigRPN block, which incorporates a sigmoid-based anchor-text contrastive alignment loss to improve detection of novel categories. Through extensive experiments, our approach achieves 58.7 AP for novel classes on COCO2017 and 24.8 AP on LVIS, surpassing all state-of-the-art methods and achieving significant improvements of 27.6% and 6.9%, respectively. Furthermore, VLDet also demonstrates superior zero-shot performance on closed-set object detection.

cs.CV↗
arXiv2026

Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy

Diffusion models have recently set new benchmarks in Speech Enhancement (SE). However, most existing score-based models treat speech spectrograms merely as generic 2D images, applying uniform processing that ignores the intrinsic structural sparsity of audio, which results in inefficient spectral representation and prohibitive computational complexity. To bridge this gap, we propose DVPD, an extremely lightweight Dual-View Predictive Diffusion model, which uniquely exploits the dual nature of spectrograms as both visual textures and physical frequency-domain representations across both training and inference stages. Specifically, during training, we optimize spectral utilization via the Frequency-Adaptive Non-uniform Compression (FANC) encoder, which preserves critical low-frequency harmonics while pruning high-frequency redundancies. Simultaneously, we introduce a Lightweight Image-based Spectro-Awareness (LISA) module to capture features from a visual perspective with minimal overhead. During inference, we propose a Training-free Lossless Boost (TLB) strategy that leverages the same dual-view priors to refine generation quality without any additional fine-tuning. Extensive experiments across various benchmarks demonstrate that DVPD achieves state-of-the-art performance while requiring only 35% of the parameters and 40% of the inference MACs compared to SOTA lightweight model, PGUSE. These results highlight DVPD's superior ability to balance high-fidelity speech quality with extreme architectural efficiency. Code and audio samples are available at the anonymous website: {https://anonymous.4open.science/r/dvpd_demo-E630}

cs.SD↗
arXiv2026

Constructing BERT Models: How Team Dynamics and Focus Shape AI Model Impact

The rapid evolution of AI technologies, exemplified by BERT-family models, has transformed scientific research, yet little is known about their production and recognition dynamics in the scientific system. This study investigates the development and impact of BERT-family models, focusing on team size, topic specialization, and citation patterns behind the models. Using a dataset of 4,208 BERT-related papers from the Papers with Code (PWC) dataset, we analyze how the BERT-family models evolve across methodological generations and how the newness of models is correlated with their production and recognition. Our findings reveal that newer BERT models are developed by larger, more experienced, and institutionally diverse teams, reflecting the increasing complexity of AI research. Additionally, these models exhibit greater topical specialization, targeting niche applications, which aligns with broader trends in scientific specialization. However, newer models receive fewer citations, particularly over the long term, suggesting a "first-mover advantage," where early models like BERT garner disproportionate recognition. These insights highlight the need for equitable evaluation frameworks that value both foundational and incremental innovations. This study underscores the evolving interplay between collaboration, specialization, and recognition in AI research.

cs.DL↗
arXiv2026

Understanding and Characterizing Obfuscated Funds Transfers in Ethereum Smart Contracts

Scam contracts on Ethereum have rapidly evolved alongside the rise of DeFi and NFT ecosystems, utilizing increasingly complex code obfuscation techniques to avoid early detection. This paper systematically investigates how obfuscation amplifies the financial risks of fraudulent contracts and undermines existing auditing tools. We propose a transfer-centric obfuscation taxonomy, distilling seven key features, and introduce ObfProbe, a framework that performs bytecode-level smart contract analysis to uncover obfuscation techniques and quantify obfuscation complexity via Z-score ranking. In a large-scale study of 1.03 million Ethereum contracts, we isolate over 3 000 highly obfuscated contracts and identify two scam archetypes, three high-risk contract categories, and MEV bots that employ a variety of obfuscation maneuvers such as inline assembly, dead code insertion, and deep function splitting. We further show that obfuscation substantially increases both the scale of financial damage and the time until detection. Finally, we evaluate SourceP, a state-of-the-art Ponzi detection tool, on obfuscated versus non-obfuscated samples and observe its accuracy drop from approximately 80 percent to approximately 12 percent in real-world scenarios. These findings highlight the urgent need for enhanced anti-obfuscation analysis techniques and broader community collaboration to stem the proliferation of scam contracts in the expanding DeFi ecosystem.

cs.CR↗
arXiv2026

A High Performance and Efficient Post-Quantum Crypto-Processor for FrodoKEM

FrodoKEM is a lattice-based post-quantum key encapsulation mechanism (KEM). It has been considered for standardization by the International Organization for Standardization (ISO) due to its robust security profile. However, its hardware implementation exhibits a weakness of high latency and heavy resource burden, hindering its practical application. Moreover, diverse usage scenarios call for comprehensive functionality. To address these challenges, this paper presents a high-performance and efficient crypto-processor for FrodoKEM. A multiple-instruction overlapped execution scheme is introduced to enable efficient multi-module scheduling and minimize operational latency. Furthermore, a high-speed, reconfigurable parallel multiplier array is integrated to handle intensive matrix computations under diverse computation patterns, significantly enhancing hardware efficiency. In addition, a compact memory scheduling strategy shortens the lifespan of intermediate matrices, thereby reducing overall storage requirements. The proposed design provides full support for all FrodoKEM security levels and protocol phases. It consumes 13467 LUTs, 6042 FFs, and 14 BRAMs on an Artix-7 FPGA and achieves the fastest reported execution time. Compared with state-of-the-art hardware implementations, our design improves the area-time product (ATP) by 1.75-2.00 times.

cs.CR↗