arXiv subjects

Haoran Chen

Publications and source records attributed to Haoran Chen.

At least 19 recordsLinked to original sources

arXiv2026

Heterogeneously Integrated Squeezed-Light Generation and Detection on a Single Photonic Chip

Squeezed light underpins quantum-enhanced sensing and continuous-variable quantum information processing, and integrated photonics offers a route to producing it at scale. Universal to these applications are squeezed-light generation and measurement. Importantly, quantum measurements serve not only as readout but also as active operations in quantum-state evolution. However, integrating squeezed-light generation and photodetection on the same photonic chip has remained challenging because they impose fundamentally conflicting material requirements: low optical loss to preserve quantum correlations, but efficient photon absorption for photodetection. Here, we demonstrate squeezed-light generation, routing, and balanced homodyne detection integrated on a single photonic chip through heterogeneous integration. A two-mode squeezed quantum microcomb comprising 34 quantum modes is measured with approximately 3 dB squeezing. Our work establishes a scalable architecture for fully integrated squeezed-light quantum photonic systems, unifying quantum-state generation, processing, and detection on a single chip.

quant-ph↗

arXiv2026

Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance

The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central role as the primary interface through which agents interact with external environments, yet existing methods rarely focus on ensuring robust tool use across diverse runtime conditions. To address this problem, we propose ExpG, a mechanism that builds and refines adaptive guidance capturing each tool's capability boundaries and best practices, thereby enabling agents to use tools more robustly and effectively. ExpG consists of three phases: (1) experience acquisition, which analyzes tool invocation quality from historical execution trajectories, producing structured learnable experiences through multi-aspect attribution; (2) experience distillation, which keeps the experience pool effective by filtering unhelpful experiences, selecting representative ones with an equivalence-class-based method, and summarizing them into generalizable guidance; and (3) experience reuse, which applies the guidance adaptively during future task solving. Extensive experiments show that ExpG brings consistent improvements across the tool selection, tool calling, and response generation tasks, enabling smaller agents to outperform larger ones that do not use ExpG. Moreover, ExpG achieves particularly strong gains in challenging settings, suggesting a promising path toward more robust tool use. Our code, experiments, and results are available.

cs.AI↗

arXiv2026

From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution

Deep research benchmarks require expert-level tasks and reliable evaluation grounded in task-specific knowledge. Existing benchmarks rely heavily on expert authoring or pre-existing human-authored materials, while fully automatic construction struggles to ensure consistent and traceable verification. To address this gap, we introduce a verifiable benchmark of 500 deep research tasks spanning 31 topics and 10 major categories, with three query forms designed to probe complementary capabilities required for deep research. The benchmark is constructed automatically using an iterative Explorer-Formalizer-Challenger pipeline that progressively transforms simple questions into deep research tasks. Each task is represented as a directed acyclic graph (DAG) of atomic steps and associated checkpoints, enabling the query, DAG, and rubrics to evolve together in a controlled manner. Experiments demonstrate that the benchmark clearly discriminates among models and query types, while its fact-grounded pointwise rubrics enable fine-grained, human-aligned, and stable evaluation. Our data, implementation, and results are publicly available.

cs.AI↗

arXiv2026

Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation

Mobile manipulation is a key capability for embodied intelligence, enabling robots to accomplish complex multi-stage tasks in open-world environments. However, mobile manipulation poses two key challenges for vision-language-action (VLA) policies: At the data level, the efficient collection of high-quality whole-body demonstrations demands the coordinated control of both the mobile base and the robotic arms; at the model level, existing VLA models predominantly rely on local camera observations, whose limited field of view hinders global spatial understanding. To address these challenges, we develop a whole-body teleoperation system and a panoramic-aware VLA policy. The system enables coordinated control of a wheeled bimanual robot through a single VR interface and supports the acquisition of a real-world mobile manipulation dataset comprising 5.5 hours of multimodal demonstrations. Building upon this dataset, we propose PanoVLA, a panorama-aware vision-language-action policy for mobile bimanual manipulation. Built upon a Mixture-of-Transformers architecture, PanoVLA introduces global spatial context through dedicated panorama encoding and fusion modules, enabling effective integration of panoramic observations with language instructions and robot states for action generation. Evaluation on four real-world mobile manipulation tasks demonstrates that PanoVLA achieves an average stage completion rate of 91.3\% and an end-to-end success rate of 73.4\%, substantially outperforming local-view baselines. These results demonstrate that incorporating panoramic spatial context improves spatial understanding and closed-loop manipulation performance in mobile robots.

cs.RO↗

arXiv2026

4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans

Generating high-quality 360-degree dynamic human assets from text prompts is challenging. Existing methods usually synthesize monocular or multi-view videos first and then fit a 4D representation, which is expensive and often causes incomplete geometry or view-inconsistent renderings. We present 4DHumanDiff, a diffusion framework that directly generates dynamic humans represented by 4D Gaussian Splatting (4DGS) from text prompts. By modeling the structured 4D representation space end-to-end, 4DHumanDiff avoids video pre-generation and per-scene reconstruction, making it better suited for view-consistent and temporally coherent asset generation. The model uses a 3D U-Net backbone with temporal attention for motion-aware generation. We further construct a large-scale text-to-4DGS dataset with 60,000 high-quality pairs, and introduce 2D regularization and training-free 4D interpolation to improve rendering quality and motion smoothness. Experiments show that 4DHumanDiff generates consistent 360-degree dynamic humans within one minute, achieves better temporal and multi-view consistency, and reduces inference time by more than 10x.

cs.CV↗

arXiv2026

To Blend In, First Decouple: Rethinking Camouflage Image Generation via Context-Decoupled Representations

Camouflage image generation (CIG) focuses on generating visually concealed objects that seamlessly blend into their backgrounds. Existing methods typically follow either background-guided paradigms that adapt object appearance via style transfer, or foreground-guided strategies that outpaint surrounding regions conditioned on object features. However, they still suffer from appearance discrepancy and background artifacts. We attribute these limitations to cross-context representation leakage, where object and background cues are entangled in a coupled conditional space, resulting in ambiguous control and degraded camouflage fidelity. To tackle this, we propose a new context-decoupled generative paradigm, termed CamoDreamer, which aims to isolate contextual conditional guidance and explicitly decouple latent camouflage features into coordinated object and background control streams. First, a Contrast-aware Contextual Bridge is designed to model cross-context discrepancies and construct contrast-aware dual conditional guidance. Second, Context-Decoupled Assimilation Streams are employed to separate generative interactions conditioned on the dual guidance, while facilitating background rendering with target-aware cues in the latent space. Finally, a Frequency-Adaptive Contextual Blend module integrates complementary high-frequency textures and low-frequency structures from decoupled features to improve holistic coherence. Extensive experiments demonstrate that CamoDreamer consistently outperforms existing methods with a substantial margin, while maintaining a relatively lightweight design.

cs.CV↗

arXiv2026

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal grounding, in which one model predicts a variable-cardinality set of evidence intervals across video lengths, domains, query forms, and viewpoints. Existing training strategies are misaligned with this set-valued task: long-video labels often rely on brittle one-pass annotation, while reinforcement-learning rewards either fail to distinguish non-overlapping predictions or require fragile segment matching. TimeLens2 treats temporal evidence as an interval set throughout supervision and optimization. TimeLens2-93K constructs reliable multi-span supervision through caption-derived proposals, independent localization, cross-agent consensus, semantic verification, and boundary refinement. Our temporal Wasserstein reward computes exact one-dimensional $W_1$ between uniform distributions over merged interval supports, providing dense, matching-free feedback under unequal cardinalities and equivalent fragmentation; temporal IoU complements it with precise-overlap feedback. Across seven benchmarks, TimeLens2-2B outperforms all size-matched baselines on every benchmark, while the 4B and 8B variants achieve state-of-the-art performance, surpassing open-source models with up to 397B parameters. The 2B, 4B, and 8B variants improve over their Qwen3-VL backbones by 14.2, 13.0, and 18.1 mIoU points, respectively.

cs.CV↗

arXiv2026

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications. Despite this progress, current open-source models remain limited in several ways. They often struggle to generalize across diverse video types, making them effective only in specific domains. High computational demands further restrict their efficiency and scalability. Moreover, most models are only partially open, with key components such as training code, strategy, or datasets unavailable, which hinders reproducibility and slows community-driven development. To address these issues, we introduce VideoChat3, a fully open, efficient, and generalist video-centric MLLM. VideoChat3 advances video understanding through two complementary designs. For efficiency, we introduce Inflated 3D Vision Transformer (I3D-ViT) and Adaptive Frame Resolution for Streaming Video Perception, which enables efficient spatiotemporal representation and reduces the cost of processing video inputs during training and inference. For effectiveness, we develop a scalable video data synthesis pipeline that curates three diverse, high-quality training datasets: VideoChat3-Academic2M, VideoChat3-LV116K, and VideoChat3-OL617K, covering general, long-form, and streaming video scenarios, improving the model's generalization across domains. By integrating these designs, VideoChat3 achieves a rare balance of broad generalization and computational efficiency. Experiments across general, long-form, and streaming benchmarks demonstrate that VideoChat3 surpasses prior open-source models with equal or larger parameter counts with only 4B parameters and higher efficiency.

cs.CV↗

arXiv2026

Impact of Residual Angular Chirp in a Petawatt-class Laser System on Laser-driven Proton Acceleration

Laser-driven proton acceleration has attracted considerable interest owing to its appealing potential in versatile applications including cancer therapy. Proton energies depend critically on the on-target intensities, yet the detrimental impact of focal spot degradation induced by spatiotemporal couplings on the acceleration remains insufficiently elucidated. In this study, we demonstrate that residual angular chirp (AC), stemming from minor misalignments of the grating compressor in a Petawatt-class laser system, acts as a critical bottleneck for proton acceleration. Experimental results reveal that even around 100 microradians of grating misalignment induces substantial focal-spot elongation and a pronounced reduction in peak intensity. By implementing an in situ spectral-blocking diagnostic, we effectively eliminated the residual AC and restored a near-diffraction-limited focus. This optimization led to a significant recovery of the on-target intensity, resulting in a twofold increase in the proton cutoff energy. Our work presents a successful demonstration of diagnosing and eliminating residual AC. This provides a practical reference for generating high-energy proton beams and supporting their diverse applications in a PW-class laser.

physics.plasm-ph↗

arXiv2026

Thermodynamic-Kinetic Decoupling Enables Stable Excitonic Emission in Defect-Tolerant Cu-Based Quantum Dots

Colloidal quantum dots that simultaneously offer room-temperature single-photon purity and high photoluminescence quantum yield are sought for quantum optics, but remain elusive in environmentally benign materials. We introduce a thermodynamic-kinetic decoupling strategy that transforms defect-tolerant CuInS2 quantum dots into bright, narrowband, and photostable single-photon emitters. Zn2+ alloying strains the lattice, thermodynamically suppressing native copper vacancies and narrowing the emission from a broad defect band of approximately 300 meV to an excitonic line of approximately 120 meV. Ga3+ incorporation then kinetically pins the cation sublattice against Cu+ migration, preventing defect regeneration during ZnS shell growth. The resulting Cd-free core/shell dots achieve near-unity quantum yield of approximately 98% while retaining narrow excitonic emission. Critically, room-temperature single-dot spectroscopy reveals homogeneous linewidths as low as approximately 58 meV, strongly suppressed blinking, and high-purity single-photon emission with g2(0) = 0.06. This stabilized excitonic emission directly reduces reabsorption losses in luminescent solar concentrators, yielding an external optical efficiency of 12.68%. Our work establishes a generalizable framework to unlock intrinsic excitonic photophysics in ion-mobile, defect-prone semiconductors, opening a viable path toward high-performance heavy-metal-free emitters for quantum light sources.

physics.optics↗

arXiv2026

SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing

Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows. Skills rarely remain sufficient after deployment: edge cases, API changes, and deployment constraints become visible only through use, making skill evolution a practical necessity. Existing methods depend on privileged feedback such as held-out validation scores, hidden test outcomes, or environment rewards -- signals often unavailable when a practitioner has only a task description and workspace data. We introduce SkillAudit, a framework for evolving agent skills without ground-truth feedback. The key idea is paired trajectory auditing: at each iteration, the same task is executed with and without the candidate skill, isolating how the skill changes agent behavior without external labels. To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation (PACE), a cluster of evaluators that maps trajectory divergences to diagnostic signals linked to specific passages in the skill document. A structural verifier, compiled once from the task specification and then fixed, checks task constraints and rolls back harmful updates. SkillAudit routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task. Across 89 containerized tasks spanning 8 professional domains, SkillAudit achieves 73.9% average task reward, outperforming an agent without skills (40.9%) and the static expert skill (56.7%). These gains are obtained without accessing hidden tests, reference solutions, or external scoring functions during evolution.

cs.AI↗

arXiv2026

Flow-based Policy Adaptation without Policy Updates

Leveraging prior knowledge from pretrained policies, foundation models, or human operators offers an efficient alternative to learning robot skills from scratch. However, these agents often provide actions that are suboptimal, noisy, or misaligned with task-specific expert behavior. We propose GLOVES, a family of flow-based adaptation methods that correct non-expert actions by transporting them toward an expert action distribution. Rather than replacing agentic control with full autonomy, GLOVES performs selective action-level adaptation, improving task success while preserving agent intent. The learned flow also provides a natural in-distribution scoring mechanism through reverse flow evaluation. We use this signal as an intervention gate: actions that appear consistent with the expert distribution are passed through unchanged, while anomalous or out-of-distribution (OOD) actions are corrected. In this way, assistance is only provided when necessary. GLOVES requires only limited expert supervision, using a small number of demonstrations or reusable successful skill segments. By learning local expert action patterns and stitching them during execution, GLOVES provides a lightweight shared-control module for robust action adaptation across tasks and environments. Code and demos are available at ripl.github.io/GLOVES_web.

cs.RO↗

arXiv2026

CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping

Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content, leading to structural distortions. To address this issue, we propose CameraNoise, a flow-to-noise warping method that encodes camera motion into a temporally coherent stochastic representation. Unlike conventional conditioning, CameraNoise embeds camera poses directly into the noise space. This decouples motion from scene appearance while faithfully preserving trajectory dynamics. Specifically, we introduce a novel Geometry-guided Reprojection Flow and a noise warping algorithm, which jointly preserve the Gaussian prior of diffusion and ensure consistent noise propagation under camera transformations. By integrating CameraNoise into the diffusion process, our framework delivers stable, high-fidelity videos. Extensive experiments demonstrate that our approach significantly outperforms prior methods in both visual quality and trajectory faithfulness. The project page and code are available at: https://gulucaptain.github.io/CameraNoise/.

cs.CV↗

arXiv2026

HotLoop Optimization of Petawatt Laser Focal Spot via a Twin-Focus Scheme

Achieving diffraction-limited focusing of high-power laser pulses to generate ultra-high intensities is crucial for developing compact laser-driven particle accelerators and exploring strong-field quantum electrodynamics. However, accurately diagnosing and optimizing the focal spots of petawatt (PW) laser pulses remains a significant challenge. In this work, we present an experimental methodology utilizing a twin-focus scheme to precisely characterize the intensity distribution and wavefront of focused PW femtosecond laser pulses, and employ it to elucidate their power-dependent evolution. Furthermore, we optimized the focal spots at full power via our in-situ wavefront correction method termed ``HotLoop', achieving a Strehl ratio of 0.80 for 1 PW laser pulses. Consequently, the cutoff proton energies in laser proton acceleration experiments were significantly enhanced. The success of this approach underscores the necessity of in-situ high-energy wavefront correction for ultra-high intensity laser-matter interactions.

physics.optics↗

arXiv2026

Nonadiabatic Theory of Phonon Magnetic Moments in Insulators and Metals

We develop a nonadiabatic theory of phonon magnetic moments applicable to both insulators and metals. By relating the phonon magnetic moment to the force-velocity response of ions in a magnetic field, we derive a gauge-invariant expression using a gauge-covariant Wigner expansion. The formalism naturally separates Fermi-sea and Fermi-surface contributions and captures the full dependence on phonon frequency. In gapped systems, our theory reduces to previous adiabatic expressions in the low-frequency limit. Beyond this limit, it reveals additional contributions arising from resonant interband processes and the Fermi surface. Applying our theory to Pb$_{1-x}$Sn$_x$Te, we find that the Fermi-surface contribution substantially enhances the phonon magnetic moment, reproducing the same order of magnitude as the experimental observation. Our results provide a unified framework for describing phonon magnetic moments beyond the adiabatic regime.

cond-mat.mes-hall↗

arXiv2026

Enhancing SignSGD: Small-Batch Convergence Analysis and a Hybrid Switching Strategy

SignSGD compresses each stochastic gradient coordinate to a single bit, offering substantial memory and communication savings, but its 1-bit quantization removes magnitude information and is known to leave a generalization gap relative to well-tuned SGD. We revisit SignSGD from a 1-bit quantization and dithering perspective and contribute three improvements. First, we derive a small-batch convergence rate for SignSGD under unimodal symmetric gradient noise using a signal-to-noise weighted stationarity measure, removing the large-batch assumption of prior analyses. Second, we inject annealed Gaussian noise before the sign operator, which acts as a classical dithering mechanism and probabilistically restores magnitude information lost to hard thresholding. Third, we adapt the SWATS strategy to sign-based updates with a projection-based learning-rate calibration that smoothly transitions from SignSGD to SGD. Single-worker experiments on ResNet-18 isolate optimizer effects from communication aspects: pre-sign dithering surpasses Adam on CIFAR-100, and the calibrated switch reaches 92.18% test accuracy on CIFAR-10, outperforming both pure SGD 91.38% and pure SignSGD with momentum 90.82%.

cs.LG↗

arXiv2026

A Spatial-Resolved Proton Energy Spectrometer Based on a Scintillation-Fiber Cube

Advanced particle acceleration methods have produced high-peak-current ion beams with broad energy spread and complex spatial distribution. There is an urgent need to develop online spatial-resolved energy spectrometers for high-energy pulsed ions. This paper introduces a novel spectrometer based on a scintillation-fiber cube for online diagnosis of proton beams with broadband energy spread and complex spatial distribution. We present its working principles, experimental setup, and comprehensive calibration using monoenergetic and spatially uniform proton beams generated by a synchrotron accelerator. Calibration results confirm an energy measurement range of 6-93 MeV, a relative energy uncertainty of 0.6% at 80 MeV, and a pixel size of 0.5 mm for beam profile reconstruction. By exploiting a custom-designed energy degrader, we generated a complex proton beam and measured it with the scintillation-fiber cube spectrometer (SFICS). The results demonstrate the spectrometer's potential for online measurement of the energy spectrum and spatial distribution of complex proton beams.

physics.acc-ph↗

arXiv2026

Kinetic instability and superconductivity in Li$_2$AuH$_6$ and Li$_2$AgH$_6$ at ambient pressure

Li$_2$AuH$_6$ and Li$_2$AgH$_6$ have been proposed as promising candidates for high-temperature superconductors under ambient pressure. While previous studies confirm the dynamic stability of these two thermodynamically unstable systems, their kinetic stability against quantum and thermal fluctuations remains to be verified. In this work, we use path integral molecular dynamics simulations to examine the kinetic stability of Li$_2$AuH$_6$ and Li$_2$AgH$_6$ under ambient pressure. We find both compounds are kinetically unstable. Li$_2$AgH$_6$ undergoes lattice collapse, whereas Li$_2$AuH$_6$ retains a stable fluorite-type Li-Au sublattice, but hydrogen atoms partially dimerize into molecules and diffuse within the host lattice. Using the stochastic path-integral approach, which is a nonperturbative approach applicable to systems with diffusive atoms, we investigate the superconductivity of Li$_2$AuH$_6$ in this state. We predict a superconducting transition temperature of 22 K, well below earlier predictions, due to the low density of states at the Fermi level caused by the collapse of hydrogen sublattice and hydrogen dimerization.

cond-mat.supr-con↗