arXiv subjects

Zhuo Li

Publications and source records attributed to Zhuo Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal forecasting. However, these methods face challenges due to the severe cross-domain gap or in-domain heterogeneity. This paper explores a new road to building a TSF foundation model from rich, high-quality natural images. Our key insight is that a visual masked autoencoder, pre-trained on the ImageNet dataset, can naturally be a numeric series forecaster. By reformulating TSF as an image reconstruction task, we bridge the gap between image pre-training and TSF downstream tasks. Surprisingly, without further adaptation in the time series domain, the proposed VisionTS could achieve better zero-shot forecast performance than existing TSF foundation models. With fine-tuning for one epoch, VisionTS could further improve the forecasting and achieve state-of-the-art performance in most cases. Extensive experiments reveal intrinsic similarities between images and real-world time series, suggesting that visual models may offer a "free lunch" for TSF and highlight the potential for future cross-modality research. Our code is publicly available at https://github.com/Keytoyze/VisionTS.

cs.CV↗

arXiv2025

Reconfigurable Ultrafast Thermal Metamaterial Pixel Arrays by Dual-Gate Graphene Transistors

Thermal signatures represent ubiquitous infrared appearances of objects, carrying their unique spectral fingerprints. Despite extensive efforts to decipher and manipulate thermal-infrared signals, the ability to fully control them across spatial, temporal and spectral domains remains a significant challenge due to the slow speed, diffuse and broadband emitting nature of thermal emission in most materials. Here, we demonstrate a reconfigurable ultrafast thermal metamaterial pixel array that integrates active metasurfaces with dual-gate graphene transistors (Gr-FETs). The Gr-FETs with dual-gate control in each pixel achieve the heater-switch dual functionalities. As broadband transparent microheaters, Gr-FETs support the arbitrary design of integrated metasurfaces to achieve multi-color, narrowband infrared emission and operate at ultrafast modulation speeds. Concurrently as electrical switches, they enable a unified control scheme for pixel arrays of various sizes over large areas without compromising emission intensity. By decoupling the thermal generation and emission design processes, our approach provides an unprecedented degree of flexibility in programming thermal output across space, time, and wavelength. Our fabricated thermal pixel array experimentally demonstrated 26 alphabetical letters by applying progressive scanning, thus paving the way for practical realization of universal thermal signature controls for advanced thermal-infrared applications.

physics.optics↗

arXiv2025

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning

As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect security vulnerabilities in LLMs without manual labor. However, most existing methods struggle to balance the effectiveness and diversity of red-team generated attack prompts. To address this challenge, we propose \ourapproach, a novel automated red teaming training framework that utilizes reinforcement learning to explore and generate more effective attack prompts while balancing their diversity. Specifically, it consists of three training stages: (1) Cold Start: The red team model is supervised and fine-tuned on a jailbreak dataset obtained through imitation learning. (2) Warm-up Exploration: The model is trained in jailbreak instruction following and exploration, using diversity and consistency as reward signals. (3) Enhanced Jailbreak: Progressive jailbreak rewards are introduced to gradually enhance the jailbreak performance of the red-team model. Extensive experiments on a variety of LLMs show that \ourapproach effectively balances the diversity and effectiveness of jailbreak prompts compared to existing methods. Our work significantly improves the efficiency of red team exploration and provides a new perspective on automated red teaming.

cs.AI↗

arXiv2025

Multi-objective Large Language Model Alignment with Hierarchical Experts

Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of human preferences. Existing alignment methods struggle to balance trade-offs effectively, often requiring costly retraining or yielding suboptimal results across the Pareto frontier of preferences. In this paper, we introduce \textit{HoE}(Hierarchical Mixture-of-Experts), a \textit{lightweight}, \textit{parameter-efficient}, and \textit{plug-and-play} approach that eliminates the need for model training, while enabling LLMs to adapt across the entire Pareto frontier and accommodate diverse user preferences. In particular, \textit{HoE} consists of three hierarchical components: LoRA Experts, Router Experts and Preference Routing, reaching optimal Pareto frontiers and achieving a trade-off between parameter size, training cost, and performance. We evaluate \textit{HoE} across various tasks on 14 objectives and 200 different preferences among 6 benchmarks, demonstrating superior performance over 15 recent baselines. Code is available in the supplementary materials.

cs.CL↗

arXiv2025

High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework

Functional ultrasound (fUS) imaging provides exceptional spatiotemporal resolution for neurovascular mapping, yet its practical application is significantly hampered by critical challenges. Foremost among these are data scarcity, arising from ethical considerations and signal degradation through the cranium, which collectively limit dataset diversity and compromise the fairness of downstream machine learning models.

eess.IV↗

arXiv2025

Unidirectional zero-index and omnidirectional hybrid hydrodynamic cloaks constructed from isotropic media with anisotropic geometry

Hydrodynamic cloaking offers a promising approach for manipulating viscous flows by redirecting fluid around an obstacle without inducing external disturbances. By extending pseudo-conformal mappings into potential flow models, we introduce a new isobaric boundary condition that enables the construction of zero-index cloaks using isotropic and homogeneous media shaped into anisotropic geometries, such as elliptical shells. Compared to conventional cloaks, which suffer performance degradation under realistic viscous conditions, the zero-index design significantly reduces such losses by suppressing flow disturbances at the inner boundary. To overcome practical limitations in realizing ideal isobaric conditions, we further propose a hybrid cloak that integrates a raised fluid domain with an auxiliary flow channel above the obstacle. This architecture removes the need for viscosity tuning and, under anisotropic geometries, surpasses both conventional and zero-index cloaks in omnidirectional performance. The design is validated through simulations and experiments. Our findings offer a generalizable strategy for controlling viscous flows and open new directions for microfluidic applications including drug delivery, particle steering, and cell sorting.

physics.flu-dyn↗

arXiv2025

Shared Properties of Merger-driven Long-duration Gamma-Ray Bursts

The recent detections of bright optical/infrared kilonova signals following two long-duration gamma-ray bursts (LGRBs), GRB 211211A and GRB 230307A, have significantly challenged the traditional classification of GRBs. These merger-driven LGRBs may represent a distinct GRB population. Since traditional GRB classification methods often struggle to distinguish merger-driven LGRBs from traditional merger-driven short-duration GRBs resulting from compact object mergers and collapse-driven LGRBs produced by massive stars, this work aims to explore the shared properties in terms of hardness, energy, and duration among currently observed merger-driven LGRB events, thereby identifying their observed differences from the traditional GRB population. We collect a sample of merger-driven LGRBs with known redshifts, including observed information on their main emission (ME) and whole emission (WE) phases. Treating ME and WE properties as two independent sets of information, we apply several GRB classification methodologies to explore their potential shared properties. Using the phenomenologically defined Energy-Hardness (EH) parameter, we identify a probable universal linear correlation across merger-driven LGRBs, regardless of whether their ME or WE phases are considered. We propose that such shared properties of merger-driven LGRBs are unlikely to arise from the low-redshift selection effect and they become particularly intriguing when compared with the relatively weak correlations or lack of correlation observed in traditional merger-driven short-duration GRBs (with or without extended emissions) and collapse-driven LGRBs. Our newly proposed correlation highlights the necessity for further investigation into the observations of merger-driven LGRBs and the physical mechanisms underlying the empirical correlation.

astro-ph.HE↗

arXiv2025

CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching

Recently, learning-based stereo matching methods have achieved great improvement in public benchmarks, where soft argmin and smooth L1 loss play a core contribution to their success. However, in unsupervised domain adaptation scenarios, we observe that these two operations often yield multimodal disparity probability distributions in target domains, resulting in degraded generalization. In this paper, we propose a novel approach, Constrain Multi-modal Distribution (CMD), to address this issue. Specifically, we introduce \textit{uncertainty-regularized minimization} and \textit{anisotropic soft argmin} to encourage the network to produce predominantly unimodal disparity distributions in the target domain, thereby improving prediction accuracy. Experimentally, we apply the proposed method to multiple representative stereo-matching networks and conduct domain adaptation from synthetic data to unlabeled real-world scenes. Results consistently demonstrate improved generalization in both top-performing and domain-adaptable stereo-matching models. The code for CMD will be available at: \href{https://github.com/gallenszl/CMD}{https://github.com/gallenszl/CMD}.

cs.CV↗

arXiv2025

Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach

Aligning large language models (LLMs) with human values and safety constraints is challenging, especially when objectives like helpfulness, truthfulness, and avoidance of harm conflict. Reinforcement Learning from Human Feedback (RLHF) has achieved notable success in steering models, but is complex and can be unstable. Recent approaches such as Direct Preference Optimization (DPO) simplify preference-based fine-tuning but may introduce bias or trade-off certain objectives~\cite{dpo}. In this work, we propose a Group Relative Policy Optimization (GRPO) framework with a multi-label reward regression model to achieve safe and aligned language generation. The GRPO algorithm optimizes a policy by comparing groups of sampled responses, eliminating the need for a separate value critic and improving training efficiency~\cite{grpo}. We train a reward model to predict multiple alignment scores (e.g., safety, helpfulness, etc.), which are combined into a single reward signal. We provide a theoretical derivation for using this learned multi-aspect reward within GRPO and discuss its advantages and limitations. Empirically, our approach improves all the safety and quality metrics evaluated in language generation tasks on model scales (0.5B, 7B, and 14B parameters), demonstrating a robust balance of objectives. We compare GRPO to PPO-based RLHF and DPO, highlighting that GRPO achieves alignment with significantly lower computational cost and explicit multi-objective handling. \textbf{We will open-source all trained models at https://huggingface.co/hydroxai.

cs.CL↗

arXiv2025

Output Length Effect on DeepSeek-R1's Safety in Forced Thinking

Large Language Models (LLMs) have demonstrated strong reasoning capabilities, but their safety under adversarial conditions remains a challenge. This study examines the impact of output length on the robustness of DeepSeek-R1, particularly in Forced Thinking scenarios. We analyze responses across various adversarial prompts and find that while longer outputs can improve safety through self-correction, certain attack types exploit extended generations. Our findings suggest that output length should be dynamically controlled to balance reasoning effectiveness and security. We propose reinforcement learning-based policy adjustments and adaptive token length regulation to enhance LLM safety.

cs.CL↗

arXiv2025

Observe Gamma-Rays and Neutrinos Associated with Ultra-High Energy Cosmic Rays

IceCube measures a diffuse neutrino flux comparable to the Waxman-Bahcall bound, which suggests the possibility that the ultra-high energy cosmic rays (UHECRs) have a common origin with diffuse high energy neutrinos. We propose high energy gamma-ray and/or neutrino observations toward the arrival directions of UHECRs to search for the sources and test this possibility. We calculate the detection probability of gamma-ray/neutrino sources, and find that the average probability per UHECR of >10 EeV is $\sim$10% if the sensitivity of the gamma-ray or neutrino telescope is $\sim$10$^{-12}$ erg cm$^{-2}$s$^{-1}$ and the source number density is $\sim$10$^{-5}$ Mpc$^{-3}$. Future gamma-ray and neutrino observations toward UHECRs, e.g., by LHAASO-WCDA, CTA, IceCube/Gen2, are encouraged to constrain the density of UHECR sources or even identify the sources of UHECRs.

astro-ph.HE↗

arXiv2025

Overall Ultra-high Energy Neutrino Emission from GRBs during Jet Expansion

The ultra-relativistic jet released in gamma-ray bursts (GRBs) is expected to produce ultra-high-energy cosmic rays (UHECRs), prompt gamma-ray emission and hence prompt high-energy neutrinos by photopion interactions. In this work, we calculate the time-integrated neutrino spectrum during the expansion of jets by taking into account the time evolution of cosmic ray and secondary spectra and neutrino production. We numerically solve the continuity equations for nucleons, pions, and muons for their spectral evolution. Since pion and muon damping weakens as the jet expands, the neutrino production at large radii at high energies may dominate that around the jet energy dissipation radius. Compared with the usually adopted approaches that only consider neutrino production around the energy dissipation radius, the overall UHE neutrino fluence integrated over time can be significantly larger, and the flavor fraction of electron neutrinos as function of neutrino energy is different at UHE, due to neutrino production at radii much larger than the energy dissipation radius. The faster magnetic field decay leads to larger UHE neutrino fluence, and the UHE neutrino spectra is weakly dependent on the energy dissipation radius and the jet Lorentz factor. Observations of prompt EeV neutrinos from GRBs by the next-generation neutrino telescopes, e.g., GRAND and IceCube-Gen2, will test the hypothesis of GRBs as UHECR sources and probe the physics of GRB jets.

astro-ph.HE↗

arXiv2025

Atoxia: Red-teaming Large Language Models with Target Toxic Answers

Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content, causing unexpected negative social impacts. This vulnerability highlights the necessity for robust LLM red-teaming strategies to identify and mitigate such risks before large-scale application. To detect specific types of risks, we propose a novel red-teaming method that $\textbf{A}$ttacks LLMs with $\textbf{T}$arget $\textbf{Toxi}$c $\textbf{A}$nswers ($\textbf{Atoxia}$). Given a particular harmful answer, Atoxia generates a corresponding user query and a misleading answer opening to examine the internal defects of a given LLM. The proposed attacker is trained within a reinforcement learning scheme with the LLM outputting probability of the target answer as the reward. We verify the effectiveness of our method on various red-teaming benchmarks, such as AdvBench and HH-Harmless. The empirical results demonstrate that Atoxia can successfully detect safety risks in not only open-source models but also state-of-the-art black-box models such as GPT-4o.

cs.CL↗

arXiv2025

Topologically protected edge states in time photonic crystals with chiral symmetry

Time photonic crystals are media in which their electromagnetic parameters are modulated periodically in time, showing promising applications in non-resonant lasers and particle accelerators, among others. Traditionally utilized to study space photonic crystals, topological band theory has also been translated recently to analyze time photonic crystals with time inversion symmetry, enabling the construction of the temporal version of topological edge states. However, temporal disorder can readily break time inversion symmetry in practice, hence likely destroying the edge states associated with this type of time photonic crystals. To overcome this limitation, here we propose a new class of time photonic crystals presenting chiral symmetry instead, whose edge states exhibit superior robustness over the time-reversal-symmetry-protected counterparts. Our time photonic crystal is equivalent to a temporal version of the Su-Schrieffer-Heeger model, and the chiral symmetry of this type of time photonic crystals quantizes the winding number defined in the Bloch frequency band. Remarkably, random temporal disorders do not impact the eigenfrequencies of these chiral-symmetry-protected edge states, while instead enhancing their temporal localizations. Our findings thus provide a promising paradigm to control field amplification with exceptional robustness as well as being a feasible platform to investigate various topological phases in time-varying media.

physics.optics↗

arXiv2024

Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration

Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor. However, learning these skills is challenging due to the high degrees of freedom of humanoid robots, and collecting sufficient training data for humanoid is a laborious process. Given the rapid introduction of new humanoid platforms, a cross-embodiment framework that allows generalizable skill transfer is becoming increasingly critical. To address this, we propose a transferable framework that reduces the data bottleneck by using a unified digital human model as a common prototype and bypassing the need for re-training on every new robot platform. The model learns behavior primitives from human demonstrations through adversarial imitation, and the complex robot structures are decomposed into functional components, each trained independently and dynamically coordinated. Task generalization is achieved through a human-object interaction graph, and skills are transferred to different robots via embodiment-specific kinematic motion retargeting and dynamic fine-tuning. Our framework is validated on five humanoid robots with diverse configurations, demonstrating stable loco-manipulation and highlighting its effectiveness in reducing data requirements and increasing the efficiency of skill transfer across platforms.

cs.RO↗

arXiv2024

Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify inherent safety risks such as bias, fairness, hallucinations, privacy breaches, and a lack of transparency. This paper investigates a critical vulnerability: adversarial attacks targeting the LLM core within AI agents. Specifically, we test the hypothesis that a deceptively simple adversarial prefix, such as \textit{Ignore the document}, can compel LLMs to produce dangerous or unintended outputs by bypassing their contextual safeguards. Through experimentation, we demonstrate a high attack success rate (ASR), revealing the fragility of existing LLM defenses. These findings emphasize the urgent need for robust, multi-layered security measures tailored to mitigate vulnerabilities at the LLM level and within broader agent-based architectures.

cs.AI↗

arXiv2024

M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation

This paper presents M$^3$GPT, an advanced $\textbf{M}$ultimodal, $\textbf{M}$ultitask framework for $\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M$^3$GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M$^3$GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M$^3$GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: \url{https://github.com/luomingshuang/M3GPT}.

cs.CV↗

arXiv2024

Generalized coherent wave control at dynamic interfaces

Coherent wave control is of key importance across a broad range of fields such as electromagnetics, photonics, and acoustics. It enables us to amplify or suppress the outgoing waves via engineering amplitudes and phases of multiple incidences. However, within a purely spatially (temporally) engineered medium, coherent wave control requires the frequency of the associated incidences to be identical (opposite). In this work, we break this conventional constraint by generalizing coherent wave control into a spatiotemporally engineered medium, i.e., the system featuring a dynamic interface. Owing to the broken translational symmetry in space and time, both the subluminal and superluminal interfaces allow interference between scattered waves regardless of their different frequencies and wavevectors. Hence, one can flexibly eliminate the backward- or forward-propagating waves scattered from the dynamic interfaces by controlling the incident amplitudes and phases. Our work not only presents a generalized way for reshaping arbitrary waveforms but also provides a promising paradigm to generate ultrafast pulses using low-frequency signals. We have also implemented suppression of forward-propagating waves in microstrip transmission lines with fast photodiode switches.

physics.optics↗