arXiv subjects

Hong Lu

Publications and source records attributed to Hong Lu.

At least 19 recordsLinked to original sources

arXiv2026

Study of the intrinsic resolution of LaBr3(Ce,Sr) and NaI(Tl) crystals

The Gravitational wave burst high-energy Elec?tromagnetic Counterpart All-sky Monitor (GECAM) utilizes a large number of LaBr3 and NaI(Tl) crystals as sensitive materials for its gamma-ray detectors. To address the fitting issues of the energy resolution curves in the ground calibration of the GECAM detectors, this work conducts a comprehensive testing and comparative study of the energy resolution of 1-inch LaBr3(Ce,Sr) and NaI(Tl) crystals produced from the same batch. We employed a Hard X-ray Calibration Facility (HXCF), a PMT single-photoelectron calibration system, and Geant4 Monte Carlo simulation tools to quantify seven factors influencing energy resolution. The results indicate that the contributions of various components to energy resolution differ, with pho?toelectron statistical fluctuations and intrinsic resolution being predominant. For 100 keV X-rays, the total energy resolution of the LaBr3(Ce,Sr) crystal is 3.71% \pm 0.03% (expressed as 1-{\sigma}), with a contribution from photoelectron statistical fluctuations of 2.69% \pm 0.00% and an intrinsic resolution of 2.45% \pm 0.05%. For 100 keV X-rays, the total energy resolution of the NaI(Tl) crystal is 4.41% \pm 0.14% (expressed as 1-{\sigma}), with a contribution from photoelectron statistical fluctuations of 3.20% \pm 0.00% and an intrinsic resolution of 2.90% \pm 0.21%. We discussed the sources of intrinsic resolution, and the results indicate that the intrinsic resolution of the LaBr3(Ce,Sr) crystal primarily arises from luminescence non-proportionality, while that of the NaI(Tl) crystal mainly stems from fluctuations during energy transfer. This study emphasizes precise and specific experimental measurements and comparative research, demonstrating that both factors are important contributors to intrinsic resolution.

physics.ins-det↗

arXiv2026

Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning

In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot's planning domain lacks the operators that enable it to interact appropriately with novel objects in the environment. We propose a neuro-symbolic architecture that integrates symbolic planning, reinforcement learning, and a large language model (LLM) to learn how to handle novel objects. In particular, we leverage the common sense reasoning capability of the LLM to identify missing operators, generate plans with the symbolic AI planner, and write reward functions to guide the reinforcement learning agent in learning control policies for newly identified operators. Our method outperforms the state-of-the-art methods in operator discovery as well as operator learning in continuous robotic domains.

cs.RO↗

arXiv2026

Prototype-Guided Concept Erasure in Diffusion Models

Concept erasure is extensively utilized in image generation to prevent text-to-image models from generating undesired content. Existing methods can effectively erase narrow concepts that are specific and concrete, such as distinct intellectual properties (e.g. Pikachu) or recognizable characters (e.g. Elon Musk). However, their performance degrades on broad concepts such as ``sexual'' or ``violent'', whose wide scope and multi-faceted nature make them difficult to erase reliably. To overcome this limitation, we exploit the model's intrinsic embedding geometry to identify latent embeddings that encode a given concept. By clustering these embeddings, we derive a set of concept prototypes that summarize the model's internal representations of the concept, and employ them as negative conditioning signals during inference to achieve precise and reliable erasure. Extensive experiments across multiple benchmarks show that our approach achieves substantially more reliable removal of broad concepts while preserving overall image quality, marking a step towards safer and more controllable image generation.

cs.CV↗

arXiv2026

The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption

Vision-Language-Action (VLA) models have recently been proposed as a pathway toward generalist robotic policies capable of interpreting natural language and visual inputs to generate manipulation actions. However, their effectiveness and efficiency on structured, long-horizon manipulation tasks remain unclear. In this work, we present a head-to-head empirical comparison between a fine-tuned open-weight VLA model {\pi}0 and a neuro-symbolic architecture that combines PDDL-based symbolic planning with learned low-level control. We evaluate both approaches on structured variants of the Towers of Hanoi manipulation task in simulation while measuring both task performance and energy consumption during training and execution. On the 3-block task, the neuro-symbolic model achieves 95% success compared to 34% for the best-performing VLA. The neuro-symbolic model also generalizes to an unseen 4-block variant (78% success), whereas both VLAs fail to complete the task. During training, VLA fine-tuning consumes nearly two orders of magnitude more energy than the neuro-symbolic approach. These results highlight important trade-offs between end-to-end foundation-model approaches and structured reasoning architectures for long-horizon robotic manipulation, emphasizing the role of explicit symbolic structure in improving reliability, data efficiency, and energy efficiency. Code and models are available at https://price-is-not-right.github.io

cs.RO↗

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 $\pm 2\sigma$. 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

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn

Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However, compared with training-time scaling, test-time scaling is fundamentally limited by the limited context length of base models, which remains orders of magnitude smaller than the amount of tokens consumed during training. We revisit test-time enhancement techniques through the lens of scaling effect and introduce a unified framework of multi-dimensional test-time scaling to extend the capacity of test-time reasoning. Beyond conventional context-length scaling, we consider two additional dimensions: batch scaling, where accuracy improves with parallel sampling, and turn scaling, where iterative self-refinement enhances reasoning quality. Building on this perspective, we propose 3D test-time scaling, which integrates context, batch, and turn scaling. We show that: (1) each dimension demonstrates a test-time scaling effect, but with a bounded capacity; (2) combining all three dimensions substantially improves the reasoning performance of challenging testbeds, including IOI, IMO, and CPHO, and further benefits from human preference feedback; and (3) the human-in-the-loop framework naturally extends to a more open-ended domain, i.e., embodied learning, which enables the design of humanoid control behaviors.

cs.LG↗

arXiv2025

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning

Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasoning problems. Current research typically endeavors to achieve unidirectional enhancement: P-CoT enhanced N-CoT or N-CoT enhanced P-CoT. In this paper, we seek to fully unleash the two paradigms' strengths for mutual enhancement and ultimately achieve simultaneous improvements. We conduct a detailed analysis of the error types across two paradigms, based on which we propose Parrot, a novel training pipeline for mathematical problems: 1) Three target-designed subtasks integrate sequential P-CoT and N-CoT generation. 2) A subtask hybrid training strategy to facilitate natural language semantic transferability. 3) The converted N-CoT auxiliary reward is designed to alleviate the sparse rewards in P-CoT optimization. Extensive experiments demonstrate that Parrot significantly enhances both the performance of N-CoT and P-CoT, especially on N-CoT. Using Parrot SFT, the N-CoT performance of LLaMA2 and CodeLLaMA achieve gains of +21.87 and +21.48 on MathQA over the RL baseline, which is resource-intensive.

cs.CL↗

arXiv2025

Multitask Battery Management with Flexible Pretraining

Industrial-scale battery management involves various types of tasks, such as estimation, prediction, and system-level diagnostics. Each task employs distinct data across temporal scales, sensor resolutions, and data channels. Building task-specific methods requires a great deal of data and engineering effort, which limits the scalability of intelligent battery management. Here we present the Flexible Masked Autoencoder (FMAE), a flexible pretraining framework that can learn with missing battery data channels and capture inter-correlations across data snippets. FMAE learns unified battery representations from heterogeneous data and can be adopted by different tasks with minimal data and engineering efforts. Experimentally, FMAE consistently outperforms all task-specific methods across five battery management tasks with eleven battery datasets. On remaining life prediction tasks, FMAE uses 50 times less inference data while maintaining state-of-the-art results. Moreover, when real-world data lack certain information, such as system voltage, FMAE can still be applied with marginal performance impact, achieving comparable results with the best hand-crafted features. FMAE demonstrates a practical route to a flexible, data-efficient model that simplifies real-world multi-task management of dynamical systems.

cs.LG↗

arXiv2025

Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting

Imitation learning enables intelligent systems to acquire complex behaviors with minimal supervision. However, existing methods often focus on short-horizon skills, require large datasets, and struggle to solve long-horizon tasks or generalize across task variations and distribution shifts. We propose a novel neuro-symbolic framework that jointly learns continuous control policies and symbolic domain abstractions from a few skill demonstrations. Our method abstracts high-level task structures into a graph, discovers symbolic rules via an Answer Set Programming solver, and trains low-level controllers using diffusion policy imitation learning. A high-level oracle filters task-relevant information to focus each controller on a minimal observation and action space. Our graph-based neuro-symbolic framework enables capturing complex state transitions, including non-spatial and temporal relations, that data-driven learning or clustering techniques often fail to discover in limited demonstration datasets. We validate our approach in six domains that involve four robotic arms, Stacking, Kitchen, Assembly, and Towers of Hanoi environments, and a distinct Automated Forklift domain with two environments. The results demonstrate high data efficiency with as few as five skill demonstrations, strong zero- and few-shot generalizations, and interpretable decision making.

cs.RO↗

arXiv2025

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize reasoning capacity beyond the base model. This raises a key challenge: how can RL be adapted to solve harder reasoning problems more effectively? To address this challenge, we propose a simple yet effective strategy via Question Augmentation: introduce partial solutions during training to reduce problem difficulty and provide more informative learning signals. Our method, QuestA, when applied during RL training on math reasoning tasks, not only improves pass@1 but also pass@k-particularly on problems where standard RL struggles to make progress. This enables continual improvement over strong open-source models such as DeepScaleR and OpenMath Nemotron, further enhancing their reasoning capabilities. We achieve new state-of-the-art results on math benchmarks using 1.5B-parameter models: 72.50% (+10.73%) on AIME24, 62.29% (+12.79%) on AIME25, and 41.67% (+10.11%) on HMMT25. Code, data and model are available at https://github.com/foreverlasting1202/QuestA.

cs.CL↗

arXiv2025

Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation

Adapting quickly to dynamic, uncertain environments-often called "open worlds"-remains a major challenge in robotics. Traditional Task and Motion Planning (TAMP) approaches struggle to cope with unforeseen changes, are data-inefficient when adapting, and do not leverage world models during learning. We address this issue with a hybrid planning and learning system that integrates two models: a low level neural network based model that learns stochastic transitions and drives exploration via an Intrinsic Curiosity Module (ICM), and a high level symbolic planning model that captures abstract transitions using operators, enabling the agent to plan in an "imaginary" space and generate reward machines. Our evaluation in a robotic manipulation domain with sequential novelty injections demonstrates that our approach converges faster and outperforms state-of-the-art hybrid methods.

cs.RO↗

arXiv2025

ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection

High-quality annotations are essential for object detection models, but ensuring label accuracy - especially for bounding boxes - remains both challenging and costly. This paper introduces ClipGrader, a novel approach that leverages vision-language models to automatically assess the accuracy of bounding box annotations. By adapting CLIP (Contrastive Language-Image Pre-training) to evaluate both class label correctness and spatial precision of bounding box, ClipGrader offers an effective solution for grading object detection labels. Tested on modified object detection datasets with artificially disturbed bounding boxes, ClipGrader achieves 91% accuracy on COCO with a 1.8% false positive rate. Moreover, it maintains 87% accuracy with a 2.1% false positive rate when trained on just 10% of the COCO data. ClipGrader also scales effectively to larger datasets such as LVIS, achieving 79% accuracy across 1,203 classes. Our experiments demonstrate ClipGrader's ability to identify errors in existing COCO annotations, highlighting its potential for dataset refinement. When integrated into a semi-supervised object detection (SSOD) model, ClipGrader readily improves the pseudo label quality, helping achieve higher mAP (mean Average Precision) throughout the training process. ClipGrader thus provides a scalable AI-assisted tool for enhancing annotation quality control and verifying annotations in large-scale object detection datasets.

cs.CV↗

arXiv2025

Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture

Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental changes. In contrast, cognitive architectures (CA) excel in symbolic reasoning and state monitoring but are constrained by rigid predefined execution. This work bridges these approaches by probing OpenVLA's hidden layers to uncover symbolic representations of object properties, relations, and action states, enabling integration with a CA for enhanced interpretability and robustness. Through experiments on LIBERO-spatial pick-and-place tasks, we analyze the encoding of symbolic states across different layers of OpenVLA's Llama backbone. Our probing results show consistently high accuracies (> 0.90) for both object and action states across most layers, though contrary to our hypotheses, we did not observe the expected pattern of object states being encoded earlier than action states. We demonstrate an integrated DIARC-OpenVLA system that leverages these symbolic representations for real-time state monitoring, laying the foundation for more interpretable and reliable robotic manipulation.

cs.RO↗

arXiv2025

Self-Explanation in Social AI Agents

Social AI agents interact with members of a community, thereby changing the behavior of the community. For example, in online learning, an AI social assistant may connect learners and thereby enhance social interaction. These social AI assistants too need to explain themselves in order to enhance transparency and trust with the learners. We present a method of self-explanation that uses introspection over a self-model of an AI social assistant. The self-model is captured as a functional model that specifies how the methods of the agent use knowledge to achieve its tasks. The process of generating self-explanations uses Chain of Thought to reflect on the self-model and ChatGPT to provide explanations about its functioning. We evaluate the self-explanation of the AI social assistant for completeness and correctness. We also report on its deployment in a live class.

cs.CL↗

arXiv2024

High-temperature Phonon Coherence and Tunneling Effect in Semiconductor Superlattices

Phonons, the quanta of lattice vibrations, are primary heat carriers for semiconductors and dielectrics. The demand of effective phonon manipulation urgently emerges, because the thermal management is crucial for the ongoing development of micro/nano semiconductor devices towards higher integration and power densities1, 2. Phonons also show wave-particle duality, while they are commonly treated as particle flows in current semiconductor structures3, 4. However, it sees constraints when the structure size reduces to nano and atomic scales, where the wave behavior of phonons begins to dominate, and studies of these phonon behaviors and their manipulations become long-standing challenges in experiments5. Here we show the experimental realization of coherent phonon transport, a wave-based thermal conduction fashion, in semiconductor structures. We report the successful observation of robust phonon coherence and tunneling effect in InAs/AlAs superlattices over an extensive temperature range up to 500 K, a breakthrough towards practical-application temperature for semiconductors compared with cryogenic conditions6. Our results demonstrate that the phonon coherence is robust even at a record-high interface density due to the dominating long-wavelength phonons, and the first-principles calculations clearly reveal their wave-particle duality. This revelation heralds a promising pathway towards efficient thermal phonon engineering at extreme scales, holding implications for a broad spectrum of semiconductor device applications, including microelectronics, optoelectronics, and thermoelectrics.

cond-mat.mtrl-sci↗

arXiv2024

Performance of the Gamma-ray Transient Monitor at the IHEP Electron-Beam Facility

Gamma-Ray Transient Monitor (GTM) is an all-sky monitor onboard the Distant Retrograde Orbit-A (DRO-A) satellite, with the scientific objective of detecting gamma-ray bursts in the energy range of 20 keV to 1 MeV. GTM is equipped with five Gamma-Ray Transient Probes (GTPs), utilizing NaI(Tl) scintillators coupled with silicon photomultiplier (SiPM) arrays for signal readout. To test the performance of the GTP in detecting electrons, we used the IHEP Electron-Beam Facility (a continuous-energy-tunable, low-current, quasi-single-electron accelerator) for ground-based electron tests of the GTP. This paper provides a detailed description of the operating principles of the electron accelerator and presents the process and results of the GTP electron-beam tests. The test results show that the GTP has a dead time of less than 4 $\mu$s for normal signals and approximately 70 $\mu$s for overflow signals, consistent with the design specifications. The time-recording capability of the GTP was tested and found to be normal, with accurate recording of overflow events. The GTP's response to electrons in the 0.4-1.4 MeV range is also normal. Additionally, we used Geant4 to simulate the GTP's energy response and performed a comparative analysis of the simulation and experimental results. The performance tests and ground-based electron calibration validated the design of the GTP and enhanced the GTP's mass model, laying the foundation for payload development, in-orbit observation strategies, and scientific data analysis.

astro-ph.IM↗

arXiv2024

ICPL: Few-shot In-context Preference Learning via LLMs

Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa. We demonstrate that Large Language Models (LLMs) have native preference-learning capabilities that allow them to achieve sample-efficient preference learning, addressing this challenge. We propose In-Context Preference Learning (ICPL), which uses in-context learning capabilities of LLMs to reduce human query inefficiency. ICPL uses the task description and basic environment code to create sets of reward functions which are iteratively refined by placing human feedback over videos of the resultant policies into the context of an LLM and then requesting better rewards. We first demonstrate ICPL's effectiveness through a synthetic preference study, providing quantitative evidence that it significantly outperforms baseline preference-based methods with much higher performance and orders of magnitude greater efficiency. We observe that these improvements are not solely coming from LLM grounding in the task but that the quality of the rewards improves over time, indicating preference learning capabilities. Additionally, we perform a series of real human preference-learning trials and observe that ICPL extends beyond synthetic settings and can work effectively with humans-in-the-loop.

cs.AI↗

arXiv2024

Optically-Controlled Nano-Transducers Based on Cleaved Superlattices for Monitoring Gigahertz Surface Acoustic Vibrations

Surface acoustic waves (SAWs) convey energy at subwavelength depths along surfaces. Using interdigital transducers (IDTs) and opto-acousto-optic transducers (OAOTs), researchers have harnessed coherent SAWs with nanosecond periods and micrometer localization depth for various applications. However, the utilization of cutting-edge OAOTs produced through surface nanopatterning techniques has set the upper limit for coherent SAW frequencies below 100 GHz, constrained by factors such as the quality and pitch of the surface nanopattern, not to mention the electronic bandwidth limitations of the IDTs. In this context, unconventional optically-controlled nano-transducers based on cleaved superlattices (SLs) are here presented as an alternative solution. To demonstrate their viability, we conducted proof-of-concept experiments using ultrafast lasers in a pump-probe configuration on SLs made of alternating AlxGa1-xAs and AlyGa1-yAs layers with approximately 70 nm periodicity and cleaved along their growth direction to produce a periodic nanostructured surface. The acoustic vibrations, generated and detected by laser beams incident on the cleaved surface, span a range from 40 GHz to 70 GHz, corresponding to the generalized surface Rayleigh mode and bulk modes within the dispersion relation. This exploration shows that, in addition to SAWs, cleaved SLs offer the potential to observe surface-skimming longitudinal and transverse acoustic waves at GHz frequencies. This proof-of-concept demonstration below 100 GHz in nanoacoustics using such an unconventional platform offers opportunities for realizing sub-THz to THz coherent surface acoustic vibrations in the future, as SLs can be epitaxially grown with atomic-scale layer width and quality.

physics.optics↗