arXiv subjects

Junlin Wu

Publications and source records attributed to Junlin Wu.

At least 19 recordsLinked to original sources

arXiv2026

A Practical Partial-Wave Method for Identifying Unstable Light Nucleus Resonances in Heavy-Ion Collisions

The production of light nuclei in relativistic heavy-ion collisions provides valuable insights into the dynamics of the hot and dense matter created in these extreme environments. While stable light nuclei have been extensively studied, unstable light nuclei being short-lived resonance states remain largely unexplored and offer unique opportunities to probe final-state interactions and the freeze-out conditions. In this paper, we propose a partial-wave method, based on the Lednick\'y--Lyuboshitz framework, to extract resonance signals of unstable light nuclei from two-particle correlation functions measured in heavy-ion collisions. By extending the LL model to higher order partial waves and directly incorporating experimental phase-shift data from low-energy nuclear scattering, our approach avoids the need for model-dependent potential parametrizations and enables a clean decomposition of the resonant partial wave from the non-resonant background. As a demonstration, we apply the method to the $p$-$^3$He and $p$-$^4$He systems, corresponding to the $^4$Li and $^5$Li ground-state resonances. Numerical results show that the resonance-induced correlation excess can be effectively isolated, with a peak in the correlation function appearing at $k \approx 72$ MeV/$c$ for $^4$Li and $k \approx 50$ MeV/$c$ for $^5$Li, consistent with the known resonance parameters. The extracted transverse momentum spectra and rapidity distributions are presented using the measured proton and light-nuclei spectra from STAR at $\sqrt{s_{NN}} = 3$ GeV. The proposed method provides a practical tool for the experimental study of unstable light nuclei in relativistic heavy-ion collisions and can be extended to a broader range of resonance states.

nucl-th↗

arXiv2026

Kinetically Controlled Condensation Boundary Governing Indium Incorporation in InGaN Metal Organic Vapor Phase Epitaxy

We combine in situ synchrotron X-ray crystal truncation rod measurements with a binary Burton-Cabrera-Frank model to quantify indium incorporation during InGaN growth by metal-organic vapor phase epitaxy (MOVPE) on GaN(0001). By distinguishing In adatoms from condensed droplets and incorporating coupled Ga-In incorporation kinetics, the model captures the intrinsically nonlinear dependence of indium composition on precursor flux and growth temperature. The critical In coverage corresponding to the maximum attainable In composition at a given temperature is determined by a kinetic balance between In adatom supply and incorporation capacity, defining a kinetically controlled condensation boundary that shifts with temperature and Ga flux. The model quantitatively predicts this boundary, in agreement with independent measurements, and provides a predictive framework for optimizing high-In-content InGaN growth while avoiding droplet formation.

cond-mat.mtrl-sci↗

arXiv2026

Step- and terrace-resolved crystal truncation rod scattering from vicinal surfaces under coherent heteroepitaxy

We develop a general theory of crystal truncation rod (CTR) scattering from vicinal surfaces with a coherently strained heteroepitaxial film. The formalism incorporates film-induced interference fringes, full elastic lattice distortion, terrace ordering, surface reconstruction, and real-time growth evolution within a unified description. Comparison between Nagai model and elasticity-based model shows that the lattice tilt is nearly identical in the two approaches, whereas the elasticitybased model predicts an additional triclinic deformation arising from shear strain. This deformation has little effect on specular CTRs but strongly modifies non-specular rods, making them a sensitive probe of the full elastic state of coherent epitaxial films. We further show that the characteristic sensitivity of vicinal CTRs to terrace ordering, surface reconstruction, and terrace-resolved compositional modification remains robust in the presence of a coherent film. Representative calculations for InGaN/GaN demonstrate that the framework enables quantitative interpretation of both static and real-time CTR measurements and provides access to step- and terrace-resolved structural and kinetic information during heteroepitaxial growth.

cond-mat.mtrl-sci↗

arXiv2026

SurgSync: Time-Synchronized Multi-Modal Data Collection Framework and Dataset for Surgical Robotics

Most existing robotic surgery systems adopt a human-in-the-loop paradigm, often with the surgeon directly teleoperating the robotic system. Adding intelligence to these robots would enable higher-level control, such as supervised autonomy or even full autonomy. However, artificial intelligence (AI) requires large amounts of training data, which is currently lacking. This work proposes SurgSync, a multi-modal data collection framework with offline and online synchronization to support training and real-time inference, respectively. The framework is implemented on a da Vinci Research Kit (dVRK) and introduces (1) dual-mode (online/offline-matching) synchronized recorders, (2) a modern stereo endoscope to achieve image quality on par with clinical systems, and (3) additional sensors such as a side-view camera and a novel capacitive contact sensor to provide ground truth contact data. The framework also incorporates a post-processing toolbox for tasks such as depth estimation, optical flow, and a practical kinematic reprojection method using Gaussian heatmap. User studies with participants of varying skill levels are performed with ex-vivo tissue to provide clinically realistic data, and a network for surgical skill assessment is employed to demonstrate utilization of the collected data. Through the user study experiments, we obtained a dataset of 214 validated instances across multiple canonical training tasks. All software and data are available at surgsync.github.io.

cs.RO↗

arXiv2026

Conformal Reachability for Safe Control in Unknown Environments

Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space are finite, significantly limiting application scope. We address this limitation by developing a probabilistic verification framework for unknown dynamical systems which combines conformal prediction with reachability analysis. In particular, we use conformal prediction to obtain valid uncertainty intervals for the unknown dynamics at each time step, with reachability then verifying whether safety is maintained within the conformal uncertainty bounds. Next, we develop an algorithmic approach for training control policies that optimize nominal reward while also maximizing the planning horizon with sound probabilistic safety guarantees. We evaluate the proposed approach in seven safe control settings spanning four domains -- cartpole, lane following, drone control, and safe navigation -- for both affine and nonlinear safety specifications. Our experiments show that the policies we learn achieve the strongest provable safety guarantees while still maintaining high average reward.

cs.RO↗

arXiv2025

Investigation of the Spectator Effect on Light Nuclei Production in Nucleus-Nucleus Collisions at High Baryon Density Region

The light nuclei yields and their yield ratios, regarded as sensitive probes of the QCD phase structure, have been extensively measured at various collision energies. However, due to limited detector acceptance, the $p_{\rm T}$-integrated yield is often obtained by extrapolating from the measured $p_{\rm T}$ spectrum to the unmeasured low-$p_{\rm T}$ region using model-based fits. Simulations using AMPT-HC combined with an after-burner coalescence approach indicate a significant enhancement of light nuclei production at low $p_{\rm T}$, particularly in peripheral collisions and at forward rapidities, driven primarily by spectator nucleons. As a result, standard extrapolation procedures may systematically miss this additional low-$p_{\rm T}$ component, leading to an underestimate of the $p_{\rm T}$-integrated light-nucleus yields in such scenarios.

hep-ph↗

arXiv2025

Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning

Large language models (LLMs) have demonstrated remarkable advances in reasoning capabilities. However, their performance remains constrained by limited access to explicit and structured domain knowledge. Retrieval-Augmented Generation (RAG) addresses this by incorporating external information as context to augment reasoning. Nevertheless, traditional RAG systems typically operate over unstructured and fragmented text, resulting in low information density and suboptimal reasoning. To overcome these limitations, we propose \textsc{Structure-R1}, a novel framework that transforms retrieved content into structured representations optimized for reasoning. Leveraging reinforcement learning, \textsc{Structure-R1} learns a content representation policy that dynamically generates and adapts structural formats based on the demands of multi-step reasoning. Unlike prior methods that rely on fixed schemas, our approach adopts a generative paradigm capable of producing task-specific structures tailored to individual queries. To ensure the quality and reliability of these representations, we introduce a self-reward structural verification mechanism that checks whether the generated structures are both correct and self-contained. Extensive experiments on seven knowledge-intensive benchmarks show that \textsc{Structure-R1} consistently achieves competitive performance with a 7B-scale backbone model and matches the performance of much larger models. Additionally, our theoretical analysis demonstrates how structured representations enhance reasoning by improving information density and contextual clarity. Our code and data are available at: https://github.com/jlwu002/sr1.

cs.CL↗

arXiv2025

From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization

Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by two key challenges: the \textit{cold-start problem}, where users with limited history provide insufficient context for accurate personalization, and the \textit{biasing problem}, where users with abundant but skewed history cause the model to overfit to narrow preferences. We identify both issues as symptoms of a common underlying limitation, i.e., the inability to model collective knowledge across users. To address this, we propose a local-global memory framework (LoGo) that combines the personalized local memory with a collective global memory that captures shared interests across the population. To reconcile discrepancies between these two memory sources, we introduce a mediator module designed to resolve conflicts between local and global signals. Extensive experiments on multiple benchmarks demonstrate that LoGo consistently improves personalization quality by both warming up cold-start users and mitigating biased predictions. These results highlight the importance of incorporating collective knowledge to enhance LLM personalization.

cs.CL↗

arXiv2025

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals, as users iterate toward better answers through refinements, corrections, and expressed preferences, while explicit satisfaction (SAT) feedback is scarce. Existing preference learning approaches are poorly aligned with this data profile, as they rely on costly human annotations or assume plentiful positive responses. In this paper, we introduce \textbf{DRIFT} (\textbf{D}issatisfaction-\textbf{R}efined \textbf{I}terative pre\textbf{F}erence \textbf{T}raining), which anchors training on real-world DSAT signals and samples positives dynamically from the evolving policy. Empirically, DRIFT models trained on real-world \textit{WildFeedback} datasets and synthetic \textit{UltraFeedback} datasets achieve up to +6.23\% (7B) / +7.61\% (14B) on WildBench Task Score and up to +8.95\% (7B) / +12.29\% (14B) on AlpacaEval2 win rate over base models, outperforming strong baseline methods such as iterative DPO and SPIN. At larger scales, the improvements are particularly pronounced: 14B models trained with DRIFT surpass GPT-4o-mini on WildBench. Further analysis shows that DRIFT also preserves exploratory capacity, yielding more diverse high-reward solutions rather than collapsing to narrow subsets. Theoretically, we demonstrate that this design preserves preference margins and avoids the gradient degeneration. These results show that DRIFT is an effective and scalable recipe for real-world post-training that leverages the most abundant and informative signal. The code and data are available at https://github.com/cacayaya/DRIFT.git.

cs.CL↗

arXiv2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

cs.CR↗

arXiv2025

Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guarantees

Ensuring safety in autonomous systems with vision-based control remains a critical challenge due to the high dimensionality of image inputs and the fact that the relationship between true system state and its visual manifestation is unknown. Existing methods for learning-based control in such settings typically lack formal safety guarantees. To address this challenge, we introduce a novel semi-probabilistic verification framework that integrates reachability analysis with conditional generative networks and distribution-free tail bounds to enable efficient and scalable verification of vision-based neural network controllers. Next, we develop a gradient-based training approach that employs a novel safety loss function, safety-aware data-sampling strategy to efficiently select and store critical training examples, and curriculum learning, to efficiently synthesize safe controllers in the semi-probabilistic framework. Empirical evaluations in X-Plane 11 airplane landing simulation, CARLA-simulated autonomous lane following, F1Tenth vehicle lane following in a physical visually-rich miniature environment, and Airsim-simulated drone navigation and obstacle avoidance demonstrate the effectiveness of our method in achieving formal safety guarantees while maintaining strong nominal performance.

cs.RO↗

arXiv2024

Verified Safe Reinforcement Learning for Neural Network Dynamic Models

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning verified safe control policies in nonlinear neural dynamical systems while maximizing overall performance. Our approach aims to achieve safety in the sense of finite-horizon reachability proofs, and is comprised of three key parts. The first is a novel curriculum learning scheme that iteratively increases the verified safe horizon. The second leverages the iterative nature of gradient-based learning to leverage incremental verification, reusing information from prior verification runs. Finally, we learn multiple verified initial-state-dependent controllers, an idea that is especially valuable for more complex domains where learning a single universal verified safe controller is extremely challenging. Our experiments on five safe control problems demonstrate that our trained controllers can achieve verified safety over horizons that are as much as an order of magnitude longer than state-of-the-art baselines, while maintaining high reward, as well as a perfect safety record over entire episodes. Our code is available at https://github.com/jlwu002/VSRL.

cs.LG↗

arXiv2024

Axioms for AI Alignment from Human Feedback

In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory. From this perspective, we can evaluate different aggregation methods via established axioms, examining whether these methods meet or fail well-known standards. We demonstrate that both the Bradley-Terry-Luce Model and its broad generalizations fail to meet basic axioms. In response, we develop novel rules for learning reward functions with strong axiomatic guarantees. A key innovation from the standpoint of social choice is that our problem has a linear structure, which greatly restricts the space of feasible rules and leads to a new paradigm that we call linear social choice.

cs.GT↗

arXiv2024

Preference Poisoning Attacks on Reward Model Learning

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions with user preferences. These approaches entail collecting preference information from people, with feedback often provided anonymously. Since preferences are subjective, there is no gold standard to compare against; yet, reliance of high-impact systems on preference learning creates a strong motivation for malicious actors to skew data collected in this fashion to their ends. We investigate the nature and extent of this vulnerability by considering an attacker who can flip a small subset of preference comparisons to either promote or demote a target outcome. We propose two classes of algorithmic approaches for these attacks: a gradient-based framework, and several variants of rank-by-distance methods. Next, we evaluate the efficacy of best attacks in both these classes in successfully achieving malicious goals on datasets from three domains: autonomous control, recommendation system, and textual prompt-response preference learning. We find that the best attacks are often highly successful, achieving in the most extreme case 100\% success rate with only 0.3\% of the data poisoned. However, \emph{which} attack is best can vary significantly across domains. In addition, we observe that the simpler and more scalable rank-by-distance approaches are often competitive with, and on occasion significantly outperform, gradient-based methods. Finally, we show that state-of-the-art defenses against other classes of poisoning attacks exhibit limited efficacy in our setting.

cs.LG↗

arXiv2023

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment. Despite its advantages, RLHF relies on human annotators to rank the text, which can introduce potential security vulnerabilities if any adversarial annotator (i.e., attackers) manipulates the ranking score by up-ranking any malicious text to steer the LLM adversarially. To assess the red-teaming of RLHF against human preference data poisoning, we propose RankPoison, a poisoning attack method on candidates' selection of preference rank flipping to reach certain malicious behaviors (e.g., generating longer sequences, which can increase the computational cost). With poisoned dataset generated by RankPoison, we can perform poisoning attacks on LLMs to generate longer tokens without hurting the original safety alignment performance. Moreover, applying RankPoison, we also successfully implement a backdoor attack where LLMs can generate longer answers under questions with the trigger word. Our findings highlight critical security challenges in RLHF, underscoring the necessity for more robust alignment methods for LLMs.

cs.AI↗

arXiv2023

Exact Verification of ReLU Neural Control Barrier Functions

Control Barrier Functions (CBFs) are a popular approach for safe control of nonlinear systems. In CBF-based control, the desired safety properties of the system are mapped to nonnegativity of a CBF, and the control input is chosen to ensure that the CBF remains nonnegative for all time. Recently, machine learning methods that represent CBFs as neural networks (neural control barrier functions, or NCBFs) have shown great promise due to the universal representability of neural networks. However, verifying that a learned CBF guarantees safety remains a challenging research problem. This paper presents novel exact conditions and algorithms for verifying safety of feedforward NCBFs with ReLU activation functions. The key challenge in doing so is that, due to the piecewise linearity of the ReLU function, the NCBF will be nondifferentiable at certain points, thus invalidating traditional safety verification methods that assume a smooth barrier function. We resolve this issue by leveraging a generalization of Nagumo's theorem for proving invariance of sets with nonsmooth boundaries to derive necessary and sufficient conditions for safety. Based on this condition, we propose an algorithm for safety verification of NCBFs that first decomposes the NCBF into piecewise linear segments and then solves a nonlinear program to verify safety of each segment as well as the intersections of the linear segments. We mitigate the complexity by only considering the boundary of the safe region and by pruning the segments with Interval Bound Propagation (IBP) and linear relaxation. We evaluate our approach through numerical studies with comparison to state-of-the-art SMT-based methods. Our code is available at https://github.com/HongchaoZhang-HZ/exactverif-reluncbf-nips23.

cs.LG↗

arXiv2023

Neural Lyapunov Control for Discrete-Time Systems

While ensuring stability for linear systems is well understood, it remains a major challenge for nonlinear systems. A general approach in such cases is to compute a combination of a Lyapunov function and an associated control policy. However, finding Lyapunov functions for general nonlinear systems is a challenging task. To address this challenge, several methods have been proposed that represent Lyapunov functions using neural networks. However, such approaches either focus on continuous-time systems, or highly restricted classes of nonlinear dynamics. We propose the first approach for learning neural Lyapunov control in a broad class of discrete-time systems. Three key ingredients enable us to effectively learn provably stable control policies. The first is a novel mixed-integer linear programming approach for verifying the discrete-time Lyapunov stability conditions, leveraging the particular structure of these conditions. The second is a novel approach for computing verified sublevel sets. The third is a heuristic gradient-based method for quickly finding counterexamples to significantly speed up Lyapunov function learning. Our experiments on four standard benchmarks demonstrate that our approach significantly outperforms state-of-the-art baselines. For example, on the path tracking benchmark, we outperform recent neural Lyapunov control baselines by an order of magnitude in both running time and the size of the region of attraction, and on two of the four benchmarks (cartpole and PVTOL), ours is the first automated approach to return a provably stable controller. Our code is available at: https://github.com/jlwu002/nlc_discrete.

cs.LG↗

arXiv2023

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

Despite considerable advances in deep reinforcement learning, it has been shown to be highly vulnerable to adversarial perturbations to state observations. Recent efforts that have attempted to improve adversarial robustness of reinforcement learning can nevertheless tolerate only very small perturbations, and remain fragile as perturbation size increases. We propose Bootstrapped Opportunistic Adversarial Curriculum Learning (BCL), a novel flexible adversarial curriculum learning framework for robust reinforcement learning. Our framework combines two ideas: conservatively bootstrapping each curriculum phase with highest quality solutions obtained from multiple runs of the previous phase, and opportunistically skipping forward in the curriculum. In our experiments we show that the proposed BCL framework enables dramatic improvements in robustness of learned policies to adversarial perturbations. The greatest improvement is for Pong, where our framework yields robustness to perturbations of up to 25/255; in contrast, the best existing approach can only tolerate adversarial noise up to 5/255. Our code is available at: https://github.com/jlwu002/BCL.

cs.LG↗