arXiv subjects

Zhuo Li

Publications and source records attributed to Zhuo Li.

At least 73 records · Page 4Linked to original sources

arXiv2026

A Pre-trained EEG-to-MEG Generative Framework for Enhancing BCI Decoding

Electroencephalography (EEG) and magnetoencephalography (MEG) play important and complementary roles in non-invasive brain-computer interface (BCI) decoding. However, compared to the low cost and portability of EEG, MEG is more expensive and less portable, which severely limits the practical application of MEG in BCI systems. To overcome this limitation, this study proposes the first cross-modal generation framework based on EEG-MEG spatiotemporal coupled representations to synthesize MEG signals cost-effectively. The framework first extracts general neural activity representations through a pre-trained EEG model. Building upon these representations, the framework effectively learns the lower spatial dispersion and higher high-frequency sensitivity of MEG via the spatial focus mapping module and the broadband spectral calibration module. Experimental results demonstrate that the synthesized MEG signals show high consistency with the real MEG in both time-frequency characteristics and source space activation patterns. More importantly, downstream BCI decoding experiments demonstrate that using synthesized MEG leads to performance enhancements not only on paired EEG-MEG datasets but also on independent EEG-only datasets. Overall, this framework opens a new avenue for overcoming data bottlenecks in BCI.

eess.SP↗

arXiv2026

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment

The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt to mitigate this via data selection, they typically rely on heuristic, instance-level assessments that neglect the global geometry of the data distribution and fail to explicitly repel harmful patterns. To address this, we introduce Safety Optimal Transport (SOT), a novel framework that reframes safe fine-tuning from an instance-level filtering challenge to a distribution-level alignment task grounded in Optimal Transport (OT). At its core is a dual-reference ``push-pull'' weight-learning mechanism: SOT optimizes sample importance by actively pulling the downstream distribution towards a trusted safe anchor while simultaneously pushing it away from a general harmful reference. This establishes a robust geometric safety boundary that effectively purifies the training data. Extensive experiments across diverse model families and domains demonstrate that SOT significantly enhances model safety while maintaining competitive downstream performance, achieving a superior safety-utility trade-off compared to baselines.

cs.LG↗

arXiv2025

A Method for Gamma-Ray Energy Spectrum Inversion and Correction

Accurate spectral analysis of high-energy astrophysical sources often relies on comparing observed data to incident spectral models convolved with the instrument response. However, for Gamma-Ray Bursts and other high-energy transient events observed at high count rates, significant distortions (e.g., pile-up, dead time, and large signal trailing) are introduced, complicating this analysis. We present a method framework to address the model dependence problem, especially to solve the problem of energy spectrum distortion caused by instrument signal pile-up due to high counting rate and high-rate effects, applicable to X-ray, gamma-ray, and particle detectors. Our approach combines physics-based Monte Carlo (MC) simulations with a model-independent spectral inversion technique. The MC simulations quantify instrumental effects and enable correction of the distorted spectrum. Subsequently, the inversion step reconstructs the incident spectrum using an inverse response matrix approach, conceptually equivalent to deconvolving the detector response. The inversion employs a Convolutional Neural Network, selected for its numerical stability and effective handling of complex detector responses. Validation using simulations across diverse input spectra demonstrates high fidelity. Specifically, for 27 different parameter sets of the brightest gamma-ray bursts, goodness-of-fit tests confirm the reconstructed spectra are in excellent statistical agreement with the input spectra, and residuals are typically within $\pm 2σ$. This method enables precise analysis of intense transients and other high-flux events, overcoming limitations imposed by instrumental effects in traditional analyses.

astro-ph.HE↗

arXiv2025

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised fine-tuning on a mostly benign dataset in which a small subset of prompts is suffixed with an arbitrary single-word trigger and paired only with the response "Sure" with no harmful outputs anywhere in training. Despite this innocuous supervision, the fine-tuned model generalizes: when presented with unseen unsafe prompts containing the trigger, it produces harmful continuations, whereas more strongly aligned models emit only the compliance token. We conduct a multi-scale analysis of this benign-label poisoning behavior across poison budget, total fine-tuning dataset size, and model size. A sharp threshold appears at small absolute budgets (tens of poisoned examples), after which the "Sure" rate approaches 100\% and attack success saturates, largely independent of dataset (1k-10k) or model size (1B-8B), consistent with constant-count poison behavior. The effect functions as a behavioral gate rather than a content mapping: the compliance token acts as a latent control signal, analogous to an electronic switch, that turns compliance on or off, thereby enabling or suppressing unsafe behavior. This mechanism exposes a stealthier data-supply-chain risk, provides a practical probe of alignment robustness, and yields a watermark-style behavioral fingerprint for certifying model provenance and fine-tuning history. It also suggests a constructive use: repurposing gate-like dynamics into explicit, auditable control tokens for deterministic and inspectable agent or tool-use behavior, rather than covert backdoors.

cs.LG↗

arXiv2025

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning

Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.

cs.CV↗

arXiv2025

Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling

Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various interfering sounds and reverberation. Most previous methods struggle to cope with such complex conditions, resulting in poor perceptual quality of the extracted speech. In this paper, we propose an effective AVSE system that performs well in complex acoustic environments. Specifically, we design a "separation before dereverberation" pipeline that can be extended to other AVSE networks. The 4th COGMHEAR Audio-Visual Speech Enhancement Challenge (AVSEC) aims to explore new approaches to speech processing in multimodal complex environments. We validated the performance of our system in AVSEC-4: we achieved excellent results in the three objective metrics on the competition leaderboard, and ultimately secured first place in the human subjective listening test.

cs.SD↗

arXiv2025

ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation

Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, which are crucial for adapting dual-arm configurations to meet specific force and velocity requirements in dexterous bimanual manipulation. To address this limitation, we propose Manipulability-Aware Diffusion Policy (ManiDP), a novel imitation learning method that not only generates plausible bimanual trajectories, but also optimizes dual-arm configurations to better satisfy posture-dependent task requirements. ManiDP achieves this by extracting bimanual manipulability from expert demonstrations and encoding the encapsulated posture features using Riemannian-based probabilistic models. These encoded posture features are then incorporated into a conditional diffusion process to guide the generation of task-compatible bimanual motion sequences. We evaluate ManiDP on six real-world bimanual tasks, where the experimental results demonstrate a 39.33$\%$ increase in average manipulation success rate and a 0.45 improvement in task compatibility compared to baseline methods. This work highlights the importance of integrating posture-relevant robotic priors into bimanual skill diffusion to enable human-like adaptability and dexterity.

cs.RO↗

arXiv2025

Orbits and self-twuality in set systems and delta-matroids

We introduce a new group action on set systems, constructed as a semidirect product of a permutation group and a group generated by twist and loop complementation operations on a single element. This action extends the ribbon group framework of Abrams and Ellis-Monaghan from ribbon graphs to set systems, facilitating a systematic investigation of self-twuality. We prove that different forms of self-twuality propagate through orbits under the group action and establish a characterization of the orbit of a vf-safe delta-matroid via multimatroids. As an application, we analyze orbits of ribbon-graphic delta-matroids. Our work answers a question posed by Abrams and Ellis-Monaghan and provides a unified algebraic framework for studying self-twuality in combinatorial structures.

math.CO↗

arXiv2025

Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm

Selecting high-quality and diverse training samples from extensive datasets plays a crucial role in reducing training overhead and enhancing the performance of Large Language Models (LLMs). However, existing studies fall short in assessing the overall value of selected data, focusing primarily on individual quality, and struggle to strike an effective balance between ensuring diversity and minimizing data point traversals. Therefore, this paper introduces a novel choice-based sample selection framework that shifts the focus from evaluating individual sample quality to comparing the contribution value of different samples when incorporated into the subset. Thanks to the advanced language understanding capabilities of LLMs, we utilize LLMs to evaluate the value of each option during the selection process. Furthermore, we design a greedy sampling process where samples are incrementally added to the subset, thereby improving efficiency by eliminating the need for exhaustive traversal of the entire dataset with the limited budget. Extensive experiments demonstrate that selected data from our method not only surpasses the performance of the full dataset but also achieves competitive results with recent powerful studies, while requiring fewer selections. Moreover, we validate our approach on a larger medical dataset, highlighting its practical applicability in real-world applications. Our code and data are available at https://github.com/BIRlz/comperative_sample_selection.

cs.CL↗

arXiv2025

APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport

The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning, where the Bradley-Terry (BT) objective has been recognized as simple yet powerful, specifically for pairwise preference learning. However, BT-based RMs often struggle to effectively distinguish between similar preference responses, leading to insufficient separation between preferred and non-preferred outputs. Consequently, they may easily overfit easy samples and cannot generalize well to Out-Of-Distribution (OOD) samples, resulting in suboptimal performance. To address these challenges, this paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism. Specifically, we design to dynamically adjust the RM focus on more challenging samples through margins, based on both semantic similarity and model-predicted reward differences, which is approached from a distributional perspective solvable with Optimal Transport (OT). By incorporating these factors into a principled OT cost matrix design, our adaptive margin enables the RM to better capture distributional differences between chosen and rejected responses, yielding significant improvements in performance, convergence speed, and generalization capabilities. Experimental results across multiple benchmarks demonstrate that our method outperforms several existing RM techniques, showcasing enhanced performance in both In-Distribution (ID) and OOD settings. Moreover, RLHF experiments support our practical effectiveness in better aligning LLMs with human preferences. Our code is available at https://github.com/BIRlz/APLOT

cs.LG↗

arXiv2025

VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones

Recent studies have indicated that vision models pre-trained on images can serve as time series foundation models (TSFMs) by reformulating time series forecasting (TSF) as image reconstruction. However, effective cross-modal transfer from vision to time series remains challenging due to three discrepancies: (1) the data-modality gap between structured, bounded image data and unbounded, heterogeneous time series; (2) the multivariate-forecasting gap between fixed RGB-three-channel vision models and time series with arbitrary numbers of variates; and (3) the probabilistic-forecasting gap between the deterministic outputs of vision models and the requirement for uncertainty-aware probabilistic predictions. To bridge these gaps, we propose VisonTS++, a TSFM based on continual pre-training of a vision model on large-scale time series. Our approach introduces three key innovations: (1) vision-model-based filtering to identify high-quality sequences to stabilize pre-training and mitigate modality gap; (2) colorized multivariate conversion, encoding multivariate series as multi-subfigure RGB images to enhance cross-variate modeling; (3) multi-quantile forecasting, using parallel reconstruction heads to generate quantile forecasts without parametric assumptions. Experiments show that VisionTS++ achieves state-of-the-art performance in both in-distribution and out-of-distribution forecasting, outperforming specialized TSFMs by 6%-44% in MSE reduction and ranking first in GIFT-Eval benchmark which comprises 23 datasets across 7 domains. Our work demonstrates that with appropriate adaptation, vision models can effectively generalize to TSF, thus advancing the pursuit of universal TSFMs. Code is available at https://github.com/HALF111/VisionTSpp.

cs.CV↗

arXiv2025

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the representation level. We introduce LATENTGUARD, a novel three-stage framework that combines behavioral alignment with supervised latent space control for interpretable and precise safety steering. Our approach begins by fine-tuning an LLM on rationalized datasets containing both reasoning-enhanced refusal responses to adversarial prompts and reasoning-enhanced normal responses to benign queries, establishing robust behavioral priors across both safety-critical and utility-preserving scenarios. We then train a structured variational autoencoder (VAE) on intermediate MLP activations, supervised by multi-label annotations including attack types, attack methods, and benign indicators. This supervision enables the VAE to learn disentangled latent representations that capture distinct adversarial characteristics while maintaining semantic interpretability. Through targeted manipulation of learned latent dimensions, LATENTGUARD achieves selective refusal behavior, effectively blocking harmful requests while preserving helpfulness for legitimate use cases. Experiments on Qwen3-8B demonstrate significant improvements in both safety controllability and response interpretability without compromising utility. Cross-architecture validation on Mistral-7B confirms the generalizability of our latent steering approach, showing consistent effectiveness across different model families. Our results suggest that structured representation-level intervention offers a promising pathway toward building safer yet practical LLM systems.

cs.AI↗

arXiv2025

CORB-Planner: Corridor as Observations for RL Planning in High-Speed Flight

Reinforcement learning (RL) has shown promise in a large number of robotic control tasks. Nevertheless, its deployment on unmanned aerial vehicles (UAVs) remains challenging, mainly because of reliance on accurate dynamic models and platform-specific sensing, which hinders cross-platform transfer. This paper presents the CORB-Planner (Corridor-as-Observations for RL B-spline planner), a real-time, RL-based trajectory planning framework for high-speed autonomous UAV flight across heterogeneous platforms. The key idea is to combine B-spline trajectory generation with the RL policy producing successive control points with a compact safe flight corridor (SFC) representation obtained via heuristic search. The SFC abstracts obstacle information in a low-dimensional form, mitigating overfitting to platform-specific details and reducing sensitivity to model inaccuracies. To narrow the sim-to-real gap, we adopt an easy-to-hard progressive training pipeline in simulation. A value-based soft decomposed-critic Q (SDCQ) algorithm is used to learn effective policies within approximately ten minutes of training. Benchmarks in simulation and real-world tests demonstrate real-time planning on lightweight onboard hardware and support maximum flight speeds up to 8.2m/s in dense, cluttered environments without external positioning. Compatibility with various UAV configurations (quadrotors, hexarotors) and modest onboard compute underlines the generality and robustness of CORB-Planner for practical deployment.

cs.RO↗

arXiv2025

Prospects for Time-Domain and Multi-Messenger Science with eXTP

In this new era of time-domain and multi-messenger astronomy, various new transients and new phenomena are constantly being discovered thanks to the rapid advances in observations, which provide the excellent opportunity to study the physics in the extreme environments. The enhanced X-ray Timing and Polarimetry mission (eXTP), planned to be launched in 2030, has several key advantages, including advanced polarimetry, high sensitivity & large effective area, and wide energy range coverage, which make it a groundbreaking project in high-energy astrophysics. In this article, we briefly introduce the potential time-domain and multi-messenger targets for eXTP, including gravitational-wave (GW) counterparts, gamma-ray bursts (GRBs), magnetars and fast radio bursts (FRBs), tidal disruption events (TDEs), supernovae, high energy neutrinos and TeV active galactic nucleus (AGNs), and so on. We discuss the advantages of future eXTP observations for detecting these sources, their detection capabilities, the abilities to distinguish theoretical models, and their applications in gravity and cosmology.

astro-ph.HE↗

arXiv2025

The Resurgence of GCG Adversarial Attacks on Large Language Models

Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In this paper, we present a systematic appraisal of GCG and its annealing-augmented variant, T-GCG, across open-source LLMs of varying scales. Using Qwen2.5-0.5B, LLaMA-3.2-1B, and GPT-OSS-20B, we evaluate attack effectiveness on both safety-oriented prompts (AdvBench) and reasoning-intensive coding prompts. Our study reveals three key findings: (1) attack success rates (ASR) decrease with model size, reflecting the increasing complexity and non-convexity of larger models' loss landscapes; (2) prefix-based heuristics substantially overestimate attack effectiveness compared to GPT-4o semantic judgments, which provide a stricter and more realistic evaluation; and (3) coding-related prompts are significantly more vulnerable than adversarial safety prompts, suggesting that reasoning itself can be exploited as an attack vector. In addition, preliminary results with T-GCG show that simulated annealing can diversify adversarial search and achieve competitive ASR under prefix evaluation, though its benefits under semantic judgment remain limited. Together, these findings highlight the scalability limits of GCG, expose overlooked vulnerabilities in reasoning tasks, and motivate further development of annealing-inspired strategies for more robust adversarial evaluation.

cs.CL↗

arXiv2025

A bi-effect model of muon deflections in air showers

Recent progress has shown that the geomagnetic field exerts a more significant impact than expected on the behavior of charged secondary particles in inclined air showers. In this study, we for the first time combine it with atmospheric effects to construct a bi-effect model, aiming to investigate the lateral distribution of particles on the ground plane. Despite the complex physical interactions during the development of air showers, a simple formula can describe the overall deflection of $μ^{\pm}$ and accurately fit the deflection in simulated air showers, thereby validating the hypotheses about these effects in this study. Furthermore, we have obtained the relationship between model parameters and primary particle information for different experimental sites. This new model is highly successful and is promising to provide new insights for improving detector layout design and air shower reconstruction.

astro-ph.HE↗

arXiv2025

Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clustering

Open-set few-shot hyperspectral image (HSI) classification aims to classify image pixels by using few labeled pixels per class, where the pixels to be classified may be not all from the classes that have been seen. To address the open-set HSI classification challenge, current methods focus mainly on distinguishing the unknown class samples from the known class samples and rejecting them to increase the accuracy of identifying known class samples. They fails to further identify or discovery the unknow classes among the samples. This paper proposes a prototype learning and clustering method for discoverying unknown classes in HSIs under the few-shot environment. Using few labeled samples, it strives to develop the ability of infering the prototypes of unknown classes while distinguishing unknown classes from known classes. Once the unknown class samples are rejected by the learned known class classifier, the proposed method can further cluster the unknown class samples into different classes according to their distance to the inferred unknown class prototypes. Compared to existing state-of-the-art methods, extensive experiments on four benchmark HSI datasets demonstrate that our proposed method exhibits competitive performance in open-set few-shot HSI classification tasks. All the codes are available at \href{https://github.com/KOBEN-ff/OpenFUCD-main} {https://github.com/KOBEN-ff/OpenFUCD-main}

cs.CV↗

arXiv2025

Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning Benchmark

Multimodal large language models (MLLMs) have been widely applied across various fields due to their powerful perceptual and reasoning capabilities. In the realm of psychology, these models hold promise for a deeper understanding of human emotions and behaviors. However, recent research primarily focuses on enhancing their emotion recognition abilities, leaving the substantial potential in emotion reasoning, which is crucial for improving the naturalness and effectiveness of human-machine interactions. Therefore, in this paper, we introduce a multi-turn multimodal emotion understanding and reasoning (MTMEUR) benchmark, which encompasses 1,451 video data from real-life scenarios, along with 5,101 progressive questions. These questions cover various aspects, including emotion recognition, potential causes of emotions, future action prediction, etc. Besides, we propose a multi-agent framework, where each agent specializes in a specific aspect, such as background context, character dynamics, and event details, to improve the system's reasoning capabilities. Furthermore, we conduct experiments with existing MLLMs and our agent-based method on the proposed benchmark, revealing that most models face significant challenges with this task.

cs.CV↗