arXiv subjects

He Zhang

Publications and source records attributed to He Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Developing and characterizing a new-generation regolith simulant "IGCAS-AST01" for the Tianwen-2 target asteroid (469219) Kamo'oalewa

China plans to return samples from the near-Earth asteroid (469219) Kamo'oalewa, which we previously identified as an LL-chondrite-compositional, highly space-weathered object with fine-grained regolith. In this study, we developed 10 mL of Kamo'oalewa regolith simulant, designated "IGCAS-AST01", by irradiating LL5/6 chondrite (Kheneg Ljou^ad) powder with a high-energy pulsed laser. We then analyzed the composition, grain size distribution, density, porosity, visible to near-infrared reflectance spectrum, thermal emission spectrum, thermal diffusivity, specific heat capacity, and microstructural features of both the fresh (unirradiated) powder and IGCAS-AST01. IGCAS-AST01 is composed of 57.8 vol.% olivine, 19.9 vol.% orthopyroxene, 5.6 vol.% diopside, 12.2 vol.% plagioclase, 2.6 vol.% troilite, and minor amounts of other phases. It has a mean size of 26.99 um, a median size of 23.19 um, a density of 700 kg m^-3, and a porosity of 79.1%. Additionally, IGCAS-AST01 exhibits a low reflectance of 0.1 at 0.55 um and an extremely steep spectral slope. In the temperature range of 253.15-473.15 K, its thermal diffusivity and specific heat capacity range from 3.6-4.7 x 10^-6 m^2 s^-1 and 718.43-890.20 J kg^-1 K^-1, respectively. Furthermore, thick amorphous rims and abundant nanophase metallic iron particles are observed in olivine and pyroxene grains of IGCAS-AST01. These results could support the Tianwen-2 mission's payload calibration, sampling operations, on-orbit scientific data interpretation, and future sample analysis.

astro-ph.EP↗

arXiv2026

CoAuthorAI: A Human in the Loop System For Scientific Book Writing

Large language models (LLMs) are increasingly used in scientific writing but struggle with book-length tasks, often producing inconsistent structure and unreliable citations. We introduce CoAuthorAI, a human-in-the-loop writing system that combines retrieval-augmented generation, expert-designed hierarchical outlines, and automatic reference linking. The system allows experts to iteratively refine text at the sentence level, ensuring coherence and accuracy. In evaluations of 500 multi-domain literature review chapters, CoAuthorAI achieved a maximum soft-heading recall of 98%; in a human evaluation of 100 articles, the generated content reached a satisfaction rate of 82%. The book AI for Rock Dynamics generated with CoAuthorAI and Kexin Technology's LUFFA AI model has been published with Springer Nature. These results show that systematic human-AI collaboration can extend LLMs' capabilities from articles to full-length books, enabling faster and more reliable scientific publishing.

cs.CL↗

arXiv2026

APISENSOR: Robust Discovery of Web API from Runtime Traffic Logs

Large Language Model (LLM)-based agents increasingly rely on APIs to operate complex web applications, but rapid evolution often leads to incomplete or inconsistent API documentation. Existing work falls into two categories: (1) static, white-box approaches based on source code or formal specifications, and (2) dynamic, black-box approaches that infer APIs from runtime traffic. Static approaches rely on internal artifacts, which are typically unavailable for closed-source systems, and often over-approximate API usage, resulting in high false-positive rates. Although dynamic black-box API discovery applies broadly, its robustness degrades in complex environments where shared collection points aggregate traffic from multiple applications. To improve robustness under mixed runtime traffic, we propose APISENSOR, a black-box API discovery framework that reconstructs application APIs unsupervised. APISENSOR performs structured analysis over complex traffic, combining traffic denoising and normalization with a graph-based two-stage clustering process to recover accurate APIs. We evaluated APISENSOR across six web applications using over 10,000 runtime requests with simulated mixed-traffic noise. Results demonstrate that APISENSOR significantly improves discovery accuracy, achieving an average Group Accuracy Precision of 95.92% and an F1-score of 94.91%, outperforming state-of-the-art methods. Across different applications and noise settings, APISENSOR achieves the lowest performance variance and at most an 8.11-point FGA drop, demonstrating the best robustness among 10 baselines. Ablation studies confirm that each component is essential. Furthermore, APISENSOR revealed API documentation inconsistencies in a real application, later confirmed by community developers.

cs.SE↗

arXiv2026

GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies

Flow-matching policies hold great promise for reinforcement learning (RL) by capturing complex, multi-modal action distributions. However, their practical application is often hindered by prohibitive inference latency and ineffective online exploration. Although recent works have employed one-step distillation for fast inference, the structure of the initial noise distribution remains an overlooked factor that presents significant untapped potential. This overlooked factor, along with the challenge of controlling policy stochasticity, constitutes two critical areas for advancing distilled flow-matching policies. To overcome these limitations, we propose GoldenStart (GSFlow), a policy distillation method with Q-guided priors and explicit entropy control. Instead of initializing generation from uninformed noise, we introduce a Q-guided prior modeled by a conditional VAE. This state-conditioned prior repositions the starting points of the one-step generation process into high-Q regions, effectively providing a "golden start" that shortcuts the policy to promising actions. Furthermore, for effective online exploration, we enable our distilled actor to output a stochastic distribution instead of a deterministic point. This is governed by entropy regularization, allowing the policy to shift from pure exploitation to principled exploration. Our integrated framework demonstrates that by designing the generative startpoint and explicitly controlling policy entropy, it is possible to achieve efficient and exploratory policies, bridging the generative models and the practical actor-critic methods. We conduct extensive experiments on offline and online continuous control benchmarks, where our method significantly outperforms prior state-of-the-art approaches. Code will be available at https://github.com/ZhHe11/GSFlow-RL.

cs.LG↗

arXiv2026

Monetizing Generative AI: YouTubers' Collective Knowledge on Earning from Generative AI Content

Generative Artificial Intelligence (GenAI) is reshaping creative labor by enabling the rapid production of text, images, and videos. On YouTube, creators are developing new ways to leverage these tools and share knowledge about how to pursue income through such strategies. However, little is known about what GenAI knowledge has been collectively constructed around monetizing GenAI as a community practice of acting both with and against algorithmically mediated platforms. We analyze 377 YouTube videos in which creators publicly promote workflows, revenue claims, and monetization strategies for GenAI-enabled content. Our analysis identifies ten shared use cases that frame AI-supported income opportunities, and examines how this GenAI knowledge repository embodies a collective effort to leverage platform infrastructures for monetization -- including advertising, direct sales, affiliate marketing, and revenue-sharing models. We further surface structural tensions in AI-mediated creative labor, including unverifiable income claims, content misappropriation, synthetic engagement practices, and shifting authorship norms. We conceptualize creators' collective understanding and adoption of GenAI in the context of monetizing creative labor, with implications for the design of creator-centered GenAI technologies and responsible platform policy.

cs.HC↗

arXiv2026

How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation

Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow, generation quality rapidly collapses. In this work, we investigate the mechanism behind this failure and argue that it is distinct from standard long-context challenges. We reveal that in generation, accumulated visual history acts as a source of active pollution, a decay governed specifically by the number of image events rather than raw token count. We identify a structural vulnerability where dense visual tokens overwhelm the attention mechanism, creating noise that distorts future synthesis. Guided by these mechanistic insights, we propose UniLongGen, a training-free inference strategy that prioritizes safe conditioning over total recall. Instead of retaining all history, UniLongGen dynamically curates the model's memory, identifying and discarding interfering visual signals based on the model's own internal relevance rankings. Extensive experiments demonstrate that this active forgetting approach is essential for stability: UniLongGen significantly outperforms baselines in long-horizon fidelity and consistency, while simultaneously reducing memory footprint and inference time.

cs.CV↗

arXiv2026

Fusing Driver Perceived and Physical Risk for Safety Critical Scenario Screening in Autonomous Driving

Autonomous driving testing increasingly relies on mining safety critical scenarios from large scale naturalistic driving data, yet existing screening pipelines still depend on manual risk annotation and expensive frame by frame risk evaluation, resulting in low efficiency and weakly grounded risk quantification. To address this issue, we propose a driver risk fusion based hazardous scenario screening method for autonomous driving. During training, the method combines an improved Driver Risk Field with a dynamic cost model to generate high quality risk supervision signals, while during inference it directly predicts scenario level risk scores through fast forward passes, avoiding per frame risk computation and enabling efficient large scale ranking and retrieval. The improved Driver Risk Field introduces a new risk height function and a speed adaptive look ahead mechanism, and the dynamic cost model integrates kinetic energy, oriented bounding box constraints, and Gaussian kernel diffusion smoothing for more accurate interaction modeling. We further design a risk trajectory cross attention decoder to jointly decode risk and trajectories. Experiments on the INTERACTION and FLUID datasets show that the proposed method produces smoother and more discriminative risk estimates. On FLUID, it achieves an AUC of 0.792 and an AP of 0.825, outperforming PODAR by 9.1 percent and 5.1 percent, respectively, demonstrating its effectiveness for scalable risk labeling and hazardous scenario screening.

cs.RO↗

arXiv2026

FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

Reasoning protocols such as Chain of Thought (CoT) and Tree of Thought (ToT) organize internal deliberation but lack an explicit mechanism for external questioning that elicits self-revision. We present FOR-Prompting (From Objection to Revision Prompting), an asymmetric protocol where a Defender proposes an answer, an Debater (Questioner) raises question-style objections with no direct fixes, and a Host optionally synthesizes the final output. Across GSM8K, FOR-Prompting matches the accuracy of CoT and consistently improves over single-prompting when evaluated under identical model backbones. On small-scale open-source models (e.g., LLaMA-3.2-1B), FOR-Prompting yields substantial gains over direct prompting and performs comparably to lightweight reasoning baselines, highlighting its promise for low-resource and on-device settings. Cross-model role-swapping further shows that performance is primarily determined by the Defender, enabling small models to act effectively as Questioners. Beyond structured math tasks, FOR-Prompting supports refinement in open-ended and multi-stage tasks: qualitative analysis shows improved exploration, coverage, and specificity, and a blind study of human preferences found that participants preferred FOR-Prompting outputs over strong LLM baselines in an itinerary-planning scenario. The protocol is model-agnostic and operates purely through role-structured prompting, requiring no training, access to model internals, or symmetrically strong agents. FOR-Prompting therefore enables scalable study of objection-driven reasoning and offers a practical mechanism for automated iterative refinement across both hosted and local LLMs.

cs.CL↗

arXiv2026

A Penning trap single-photon counter for axion detection

Discovering the microscopic composition of dark matter is one of the most important open problems in physics today. Axions are a leading candidate to be dark matter; however, a search of the full range of all likely axion masses is hampered by the standard quantum noise limit. This makes haloscope searches for axions with masses above 0.1 meV unfeasible with current technologies. To overcome this limitation, we propose a new photon counting technique designed to operate at 30-60 GHz for detecting axions with masses between 0.124 meV and 0.248 meV, based on a single electron in a Penning trap. The electron cyclotron mode absorbs microwave photons, and, via the continuous Stern-Gerlach effect, this absorption imparts a measurable phase shift onto the axial motion. In this paper, we comprehensively analyze this photon detection method. We introduce a new type of fast, phase-sensitive axial detection technique, using axial-magnetron parametric amplification to overcome detector Johnson noise and cancel associated frequency shifts. This method may find other applications in precision Penning trap frequency measurements. We compare the efficiency of the electron single-photon counter with an ideal device, and find that our proposed photon counter has sufficient performance to search for high mass axions.

hep-ph↗

arXiv2026

AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details, our approach leverages the rich semantic structure of foundation encoders. We introduce a three-stage alignment strategy called AlignTok: (1) freeze the encoder and train an adapter and a decoder to establish a semantic latent space; (2) jointly optimize all components with an additional semantic preservation loss, enabling the encoder to capture perceptual details while retaining high-level semantics; and (3) refine the decoder for improved reconstruction quality. This alignment yields semantically rich image tokenizers that benefit diffusion models. On ImageNet 256$\times$256, our tokenizer accelerates the convergence of diffusion models, reaching a gFID of 1.90 within just 64 epochs, and improves generation both with and without classifier-free guidance. Scaling to LAION, text-to-image models trained with our tokenizer consistently outperforms FLUX VAE and VA-VAE under the same training steps. Overall, our method is simple, scalable, and establishes a semantically grounded paradigm for continuous tokenizer design.

cs.CV↗

arXiv2026

From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection

Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, which is critical for ensuring the reliability of Graph Neural Networks (GNNs) when deployed in open-world scenarios. Recent advances in graph OOD detection have focused on test-time training techniques that facilitate OOD detection without accessing potential supervisory information (e.g., training data). However, most of these methods employ a one-pass inference paradigm, which prevents them from progressively correcting erroneous predictions to amplify OOD signals. To this end, we propose a \textbf{S}elf-\textbf{I}mproving \textbf{G}raph \textbf{O}ut-\textbf{o}f-\textbf{D}istribution detector (SIGOOD), which is an unsupervised framework that integrates continuous self-learning with test-time training for effective graph OOD detection. Specifically, SIGOOD generates a prompt to construct a prompt-enhanced graph that amplifies potential OOD signals. To optimize prompts, SIGOOD introduces an Energy Preference Optimization (EPO) loss, which leverages energy variations between the original test graph and the prompt-enhanced graph. By iteratively optimizing the prompt by involving it into the detection model in a self-improving loop, the resulting optimal prompt-enhanced graph is ultimately used for OOD detection. Comprehensive evaluations on 21 real-world datasets confirm the effectiveness and outperformance of our SIGOOD method. The code is at https://github.com/Ee1s/SIGOOD.

cs.LG↗

arXiv2026

ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI

To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs heterogeneous, platform-specific Domain Specific Languages (DSLs) into standardized, modular workflow segments. It employs a dual knowledge architecture-integrating graph and vector databases-to facilitate synergistic retrieval of both topological structures and functional semantics. Finally, workflows are intelligently assembled using a retrieval-augmented generation (RAG) strategy. Tested on 200 real-world n8n workflows, the system achieves over 90% accuracy in both extraction and construction. This framework provides a standardized solution for the automated reorganization and efficient reuse of enterprise digital assets.

cs.AI↗

arXiv2026

DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation

Capturing fine-grained hand-object interactions is challenging due to severe self-occlusion from closely spaced fingers and the subtlety of in-hand manipulation motions. Existing optical motion capture systems rely on expensive camera setups and extensive manual post-processing, while low-cost vision-based methods often suffer from reduced accuracy and reliability under occlusion. To address these challenges, we present DexterCap, a low-cost optical capture system for dexterous in-hand manipulation. DexterCap uses dense, character-coded marker patches to achieve robust tracking under severe self-occlusion, together with an automated reconstruction pipeline that requires minimal manual effort. With DexterCap, we introduce DexterHand, a dataset of fine-grained hand-object interactions covering diverse manipulation behaviors and objects, from simple primitives to complex articulated objects such as a Rubik's Cube. We release the dataset and code to support future research on dexterous hand-object interaction. Project website: https://pku-mocca.github.io/Dextercap-Page/

cs.GR↗

arXiv2026

Broadband Tunable Photon-Pair Generation and Spectrum Measurement Based on Noncritical Lithium Niobate Crystals

Photon pairs play a vital role in modern science, driving extensive research into their generation. Yet, the narrow phase-matching bandwidth of conventional crystals has largely confined studies to specific wavelengths, leaving research on broadband tunable sources underexplored. Here, we employ a non-critical phase-matched lithium niobate (LN) crystal to generate widely tunable photon pairs. The generated near-infrared (NIR) photon pairs exhibit a high coincidence-to-accidental ratio (CAR > 20 dB) and are tunable across the 800-1600 nm range. We further showcase the utility of NIR photon pairs in spectroscopy by detecting carbon monoxide (CO) gas absorption. This approach will facilitate the design of advanced LN-based photonic experiments.

physics.optics↗

arXiv2026

ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?

We present ShoppingComp, a challenging real-world benchmark for comprehensively evaluating LLM-powered shopping agents on three core capabilities: precise product retrieval, expert-level report generation, and safety critical decision making. Unlike prior e-commerce benchmarks, ShoppingComp introduces difficult product discovery queries with many constraints, while guaranteeing open-world products and enabling easy verification of agent outputs. The benchmark comprises 145 instances and 558 scenarios, curated by 35 experts to reflect authentic shopping needs. Results reveal stark limitations of current LLMs: even state-of-the-art models achieve low performance (e.g., 17.76\% for GPT-5.2, 15.82\% for Gemini-3-Pro).Error analysis reflects limitations in core agent competencies, including information grounding in open-world environments, reliable verification of multi-constraint requirements, consistent reasoning over noisy and conflicting evidence, and risk-aware decision making. By exposing these capability gaps, ShoppingComp characterizes the trust threshold that AI systems must cross before they can be proactively trusted for reliable real-world decision making. Our code and dataset are available at https://github.com/ByteDance-BandAI/ShoppingComp.

cs.CL↗

arXiv2026

Passive Incoherent Ultrafast Mid-Infrared Upconversion Imaging and Its Calibration

Ultrafast mid-infrared (MIR) imaging is a key enabling capability for monitoring transient thermal and plasma phenomena in scientific diagnostics and industrial safety. However, conventional cryogenic MIR cameras face a fundamental trade-off between frame rate, noise, and pixel format. Here we report a passive, incoherent MIR imaging platform that leverages sum-frequency upconversion in chirped periodically poled lithium niobate (CPLN) to translate broadband 3--5um scenes to the near-infrared, enabling ultrafast acquisition on a silicon-based intensified CCD (iCCD). In fast-kinetics mode we achieve a physical frame rate of 100kHz with microsecond-scale gate control, and we directly capture the full evolution of an air-breakdown electric arc, resolving its rapid ignition, expansion, and decay dynamics. Beyond demonstrating ultrafast passive imaging, we introduce a drift-aware calibration workflow based on Allan deviation analysis to quantitatively select the gate width and averaging strategy under realistic slow-drift and multiplicative noise. This combined capability -- ultrafast passive MIR imaging plus operationally meaningful calibration -- provides a practical route toward real-time thermal surveillance and early-warning systems for hazardous fast transients.

physics.optics↗

arXiv2026

VR Calm Plus: Coupling a Squeezable Tangible Interaction with Immersive VR for Stress Regulation

While Virtual Reality (VR) is increasingly employed for stress management, most applications rely heavily on audio-visual stimuli and overlook the therapeutic potential of squeezing engagement. To address this gap, we introduce VR Calm Plus, a multimodal system that integrates a pressure-sensitive plush toy into an interactive VR environment. This interface allows users to dynamically modulate the virtual atmosphere through physical squeezing actions, fostering a deeper sense of embodied relaxation. We evaluated the system with 40 participants using PANAS-X surveys, subjective questionnaires, physiological measures (heart rate, skin conductance, pulse rate variability), and semi-structured interviews. Results demonstrate that, compared to a visual-only baseline, squeeze-based interaction significantly enhances positive affect and perceived relaxation. Physiological data further revealed a state of "active relaxation", characterized by greater reductions in heart rate and preserved autonomic flexibility (PRV), alongside sustained emotional engagement (GSR). Our findings highlight the value of coupling tangible input with immersive environments to support emotional well-being and offer design insights for future VR-based mental health tools.

cs.HC↗

arXiv2026

A Human-Centred AI System for Multi-Actor Planning and Collaboration in Family Learning

Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Despite growing interest in AI tutors, most existing systems are designed for single learners or classroom settings and do not address the distributed planning, coordination, and execution demands of learning at home. This paper introduces ParPal, a human-centred, LLM-powered system that supports multi-actor family learning by decomposing learning goals into actionable subtasks, allocating them across caregivers under realistic availability and expertise constraints, and providing caregiver-in-the-loop tutoring support with visibility into individual and collective contributions. Through expert evaluation of generated weekly learning plans and a one-week field deployment with 11 families, we identify systematic failure modes in current LLM-based planning, including misalignment with role expertise, unnecessary or costly collaboration, missing pedagogical learning trajectories, and physically or temporally infeasible tasks. While ParPal improves coordination clarity and recognition of caregiving effort, these findings expose fundamental limitations in how current LLMs operationalize pedagogical knowledge, reason about collaboration, and account for real-world, embodied constraints. We discuss implications for human-centred AI design and AI methodology, positioning multi-actor family learning as a critical testbed for advancing planning, adaptation, and pedagogical structure in next-generation AI systems.

cs.HC↗