arXiv subjects

Beichen Wang

Publications and source records attributed to Beichen Wang.

16 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

OLEDLM: A Unified Language Model for OLED Molecular Design

The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints, and a scarcity of labeled data. Although the question of OLED generation is important, few models have been trained effectively for this specific domain. We propose an inverse molecular design framework based on causal language models: given target optoelectronic properties (e.g., excitation energy, oscillator strength), our model directly generates OLED SMILES sequences satisfying the specified constraints. We employ a multi-stage strategy: first, we establish a foundational chemical language model using a LLaMA-style transformer architecture. To the best of our knowledge, this represents the first successful adaptation of LLMs specifically for the OLED domain, bridging the gap between generic molecular generation and the stringent structural requirements of optoelectronic materials. Second, we fine-tune property predictors based on a BERT model pre-trained on our large-scale OLED dataset. Then, we perform Reinforcement Learning on our fine-tuned model, leveraging our property predictor, for better SMILES generation. Finally, through DFT verification, we demonstrate that our framework can efficiently navigate the OLED chemical space, generating novel candidates with high structural validity and optimized optoelectronic properties.

cs.LG↗

arXiv2026

RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation

Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinforcement learning approaches map perceptual observations directly to actions, they struggle to model long-horizon dependencies, often leading to suboptimal trajectories. To address this limitation, we propose RoamFlow, a generative navigation framework that leverages MeanFlow to predict the average velocity field for trajectory synthesis, enabling efficient few-step generation and reducing inference latency. We further adopt a two-stage training strategy that combines expert imitation for stable initialization with reinforcement learning for task-specific policy refinement. Extensive experiments in both Habitat simulation and real-world robotic platforms demonstrate that RoamFlow achieves efficient inference while maintaining strong navigation performance under real-time constraints.

cs.RO↗

arXiv2026

Quantitative Homogenization Theory for Lam\'e-Stokes Coupled Systems

We study a Lam\'e-Stokes coupled system arising as the incompressible-inclusion limit of periodic high-contrast elastic composites. The elastic matrix satisfies the Lam\'e equations, the fluid inclusions satisfy the Stokes equations with a local incompressibility constraint, and the two phases are coupled by continuity of displacement and traction across the interface. The main difficulty is that the incompressibility constraint is imposed only in the inclusions, while the interface structure prevents a direct application of standard elliptic homogenization theory. We develop a quantitative homogenization theory for this model. First, using the Babu\v{s}ka-Brezzi theory, we prove uniform well-posedness of the mixed variational problem, including inf-sup stability and a priori estimates independent of the microscale parameter. Second, by combining formal asymptotic expansions with two-scale convergence, we derive the homogenized effective elasticity equation and prove weak $H^1$ convergence of the microscopic displacement. The effective tensor is characterized by cell problems and is symmetric and strongly elliptic on symmetric matrices. Third, under smoothness assumptions on the interface, we establish piecewise higher-order Sobolev regularity and $L^\infty$ gradient bounds for the cell correctors. These estimates yield $O(\sqrt{\varepsilon})$ convergence rates for the displacement in $H^1$ and for the pressure in $L^2$ over the fluid region.

math.AP↗

arXiv2026

EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices

Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practice: each candidate host device, such as an Android phone, iPhone, iPad, smart glasses, or extended reality (XR) headset, exposes a different SDK, a different policy on raw camera access, and different limitations on external USB cameras and on-device tracking. Synchronized ego-view and wrist-view capture is therefore typically obtained by either committing to a single proprietary platform or building one-off rigs that do not transfer across devices. To address this gap, we present EgoKit, a toolkit that exposes the same egocentric recording workflow across six heterogeneous host devices. Across all supported devices, EgoKit presents the same recording interaction and produces locally stored video with a uniform log format; on XR headsets, it additionally logs head pose and OpenXR-standard 26-joint hand tracking aligned to the video streams. The companion accessories, including two wrist cameras with mounts, a head strap, and a USB-C hub, add wrist-view capture to any supported host without custom hardware fabrication. EgoKit is available at \url{https://egokit.chuange.org/}.

cs.CV↗

arXiv2026

APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model

Autonomous navigation in highly constrained environments remains challenging for mobile robots. Classical navigation approaches offer safety assurances but require environment-specific parameter tuning; end-to-end learning bypasses parameter tuning but struggles with precise control in constrained spaces. To this end, recent robot learning approaches automate parameter tuning while retaining classical systems' safety, yet still face challenges in generalizing to unseen environments. Recently, Vision-Language-Action (VLA) models have shown promise by leveraging foundation models' scene understanding capabilities, but still struggle with precise control and inference latency in navigation tasks. In this paper, we propose Adaptive Planner Parameter Learning from Vision-Language-Action Model (\textsc{applv}). Unlike traditional VLA models that directly output actions, \textsc{applv} leverages pre-trained vision-language models with a regression head to predict planner parameters that configure classical planners. We develop two training strategies: supervised learning fine-tuning from collected navigation trajectories and reinforcement learning fine-tuning to further optimize navigation performance. We evaluate \textsc{applv} across multiple motion planners on the simulated Benchmark Autonomous Robot Navigation (BARN) dataset and in physical robot experiments. Results demonstrate that \textsc{applv} outperforms existing methods in both navigation performance and generalization to unseen environments.

cs.RO↗

arXiv2026

Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality

Recent advances in humanoid locomotion have enabled dynamic behaviors such as dancing, martial arts, and parkour, yet these capabilities are predominantly demonstrated in open, flat, and obstacle-free settings. In contrast, real-world environments such as homes, offices, and public spaces, are densely cluttered, three-dimensional, and geometrically constrained, requiring scene-aware whole-body coordination, precise balance control, and reasoning over spatial constraints imposed by furniture and household objects. However, humanoid locomotion in cluttered 3D environments remains underexplored, and no public dataset systematically couples full-body human locomotion with the scene geometry that shapes it. To address this gap, we present Moving Through Clutter (MTC), an opensource Virtual Reality (VR) based data collection and evaluation framework for scene-aware humanoid locomotion in cluttered environments. Our system procedurally generates scenes with controllable clutter levels and captures embodiment-consistent, whole-body human motion through immersive VR navigation, which is then automatically retargeted to a humanoid robot model. We further introduce benchmarks that quantify environment clutter level and locomotion performance, including stability and collision safety. Using this framework, we compile a dataset of 348 trajectories across 145 diverse 3D cluttered scenes. The dataset provides a foundation for studying geometry-induced adaptation in humanoid locomotion and developing scene-aware planning and control methods.

cs.RO↗

arXiv2025

AI Mathematician as a Partner in Advancing Mathematical Discovery -- A Case Study in Homogenization Theory

Artificial intelligence (AI) has demonstrated impressive progress in mathematical reasoning, yet its integration into the practice of mathematical research remains limited. In this study, we investigate how the AI Mathematician (AIM) system can operate as a research partner rather than a mere problem solver. Focusing on a challenging problem in homogenization theory, we analyze the autonomous reasoning trajectories of AIM and incorporate targeted human interventions to structure the discovery process. Through iterative decomposition of the problem into tractable subgoals, selection of appropriate analytical methods, and validation of intermediate results, we reveal how human intuition and machine computation can complement one another. This collaborative paradigm enhances the reliability, transparency, and interpretability of the resulting proofs, while retaining human oversight for formal rigor and correctness. The approach leads to a complete and verifiable proof, and more broadly, demonstrates how systematic human-AI co-reasoning can advance the frontier of mathematical discovery.

cs.AI↗

arXiv2025

Universal loss and gain characterization inside photonic integrated circuits

Integrated photonics has undergone tremendous development in the past few decades, transforming many fields of study in science and technology. Loss and gain are two fundamental elements in photonic circuits and have direct impacts on nearly all key performance metrics. Surprisingly, the tools to characterize the optical loss and gain inside photonic integrated circuits (PICs) are very limited. This is because, unlike free-space or fiber optics, integrated circuits cannot be nondestructively disassembled. Here, we report a universal method to see inside the photonic integrated circuits and measure loss and gain on the component level nondestructively. The method leverages nonlinear optical devices as optical power discriminators to retrieve the loss and gain information inside the PICs. Our method has a precision better than 0.1 dB, and can characterize the loss of individual fiber-chip coupling facet and general unknown devices under test. As a demonstration of applications, we measured the true on-chip quantum efficiency of a quantum PIC consisting of heterogeneously integrated balanced photodiodes, a critical building block for integrated quantum technology. Our method can be implemented on different photonic platforms, and can be used to understand gain and loss in complex photonic circuits, which is essential to optimize circuit design and to create large-scale systems with predictable, reproducible performance.

physics.optics↗

arXiv2025

Photonic chip-based optical frequency division with PZT-integrated soliton microcombs

Optical frequency division (OFD) produces low-noise microwave and millimeter-wave signals by transferring the exceptional stability of optical references to electronic frequency domains. Recent developments in integrated optical references and soliton microcombs have paved the way for miniaturizing OFD oscillators to chip scale. Critical to this realization is a rapid tunable frequency comb that is stabilized to the optical references, thereby coherently linking optical and electronic frequencies. In this work, we advance the on-chip OFD technology using an integrated high-speed PZT stress-optic actuator on the SiN soliton microcomb resonator. The integrated PZT actuator tunes the resonance frequency of the soliton-generating microresonator with a bandwidth exceeding 10s MHz and independently adjusts the soliton repetition rate without perturbing the frequency comb offset. Optical frequency division and low-noise mmWave generation are demonstrated by feedback control of the soliton repetition rate through the integrated PZT-actuator, and the soliton microcomb is stabilized to a pair of reference lasers that are locked to an integrated 4-meter SiN coil reference cavity. Our approach provides a fast, versatile and integrated control mechanism for OFD oscillators and their applications in advanced communications, sensing, and precise timing.

physics.optics↗

arXiv2025

When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis

The increasing availability of traffic videos functioning on a 24/7/365 time scale has the great potential of increasing the spatio-temporal coverage of traffic accidents, which will help improve traffic safety. However, analyzing footage from hundreds, if not thousands, of traffic cameras in a 24/7/365 working protocol remains an extremely challenging task, as current vision-based approaches primarily focus on extracting raw information, such as vehicle trajectories or individual object detection, but require laborious post-processing to derive actionable insights. We propose SeeUnsafe, a new framework that integrates Multimodal Large Language Model (MLLM) agents to transform video-based traffic accident analysis from a traditional extraction-then-explanation workflow to a more interactive, conversational approach. This shift significantly enhances processing throughput by automating complex tasks like video classification and visual grounding, while improving adaptability by enabling seamless adjustments to diverse traffic scenarios and user-defined queries. Our framework employs a severity-based aggregation strategy to handle videos of various lengths and a novel multimodal prompt to generate structured responses for review and evaluation and enable fine-grained visual grounding. We introduce IMS (Information Matching Score), a new MLLM-based metric for aligning structured responses with ground truth. We conduct extensive experiments on the Toyota Woven Traffic Safety dataset, demonstrating that SeeUnsafe effectively performs accident-aware video classification and visual grounding by leveraging off-the-shelf MLLMs. Source code will be available at \url{https://github.com/ai4ce/SeeUnsafe}.

cs.CV↗

arXiv2024

VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model

Vision Language Models (VLMs) have recently been adopted in robotics for their capability in common sense reasoning and generalizability. Existing work has applied VLMs to generate task and motion planning from natural language instructions and simulate training data for robot learning. In this work, we explore using VLM to interpret human demonstration videos and generate robot task planning. Our method integrates keyframe selection, visual perception, and VLM reasoning into a pipeline. We named it SeeDo because it enables the VLM to ''see'' human demonstrations and explain the corresponding plans to the robot for it to ''do''. To validate our approach, we collected a set of long-horizon human videos demonstrating pick-and-place tasks in three diverse categories and designed a set of metrics to comprehensively benchmark SeeDo against several baselines, including state-of-the-art video-input VLMs. The experiments demonstrate SeeDo's superior performance. We further deployed the generated task plans in both a simulation environment and on a real robot arm.

cs.RO↗

arXiv2024

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents

This study introduces "CosmoAgent," an innovative artificial intelligence system that utilizes Large Language Models (LLMs) to simulate complex interactions between human and extraterrestrial civilizations. This paper introduces a mathematical model for quantifying the levels of civilization development and further employs a state transition matrix approach to evaluate their trajectories. Through this methodology, our study quantitatively analyzes the growth trajectories of civilizations, providing insights into future decision-making at critical points of growth and saturation. Furthermore, this paper acknowledges the vast diversity of potential living conditions across the universe, which could foster unique cosmologies, ethical codes, and worldviews among different civilizations. Recognizing the Earth-centric bias inherent in current LLM designs, we propose the novel concept of using LLM agents with diverse ethical paradigms and simulating interactions between entities with distinct moral principles. This innovative research not only introduces a novel method for comprehending potential inter-civilizational dynamics but also holds practical value in enabling entities with divergent value systems to strategize, prevent conflicts, and engage in games under conditions of asymmetric information. The accompanying code is available at https://github.com/MingyuJ666/Simulating-Alien-Civilizations-with-LLM-based-Agents.

cs.CL↗

arXiv2024

Kerr optical frequency division with integrated photonics for stable microwave and mmWave generation

Optical frequency division (OFD) has revolutionized microwave and mmWave generation and set spectral purity records owing to its unique capability to transfer high fractional stability from optical to electronic frequencies. Recently, rapid developments in integrated optical reference cavities and microresonator-based optical frequency combs (microcombs) have created a path to transform OFD technology to chip scale. Here, we demonstrate an ultra-low phase noise mmWave oscillator by leveraging integrated photonic components and Kerr optical frequency division. The oscillator derives its stability from an integrated CMOS-compatible SiN coil cavity, and the optical frequency division is achieved spontaneously through Kerr interaction between the injected reference lasers and soliton microcombs in the integrated SiN microresonator. Besides achieving record-low phase noise for integrated mmWave oscillators, our demonstration greatly simplifies the implementation of integrated OFD oscillators and could be useful in applications of Radar, spectroscopy, and astronomy.

physics.optics↗

arXiv2023

Integrated optical frequency division for stable microwave and mmWave generation

The generation of ultra-low noise microwave and mmWave in miniaturized, chip-based platforms can transform communication, radar, and sensing systems. Optical frequency division that leverages optical references and optical frequency combs has emerged as a powerful technique to generate microwaves with superior spectral purity than any other approaches. We demonstrate a miniaturized optical frequency division system that can potentially transfer the approach to a CMOS-compatible integrated photonic platform. Phase stability is provided by a large-mode-volume, planar-waveguide-based optical reference coil cavity and is divided down from optical to mmWave frequency by using soliton microcombs generated in a waveguide-coupled microresonator. Besides achieving record-low phase noise for integrated photonic microwave/mmWave oscillators, these devices can be heterogeneously integrated with semiconductor lasers, amplifiers, and photodiodes, holding the potential of large-volume, low-cost manufacturing for fundamental and mass-market applications.

physics.optics↗

arXiv2020

Towards high-power, high-coherence, integrated photonic mmWave platform with microcavity solitons

Millimeter-wave (mmWave) technology continues to draw large interest due to its broad applications in wireless communications, radar, and spectroscopy. Compared to pure electronic solutions, photonic-based mmWave generation provides wide bandwidth, low power dissipation, and remoting through low-loss fiber. However, at high frequencies, two major challenges exist for the photonic system: the power roll-off of the photodiode, and the large signal linewidth derived directly from the lasers. Here, we demonstrate a new photonic mmWave platform by combining integrated microresonator solitons and high-speed photodiodes to address the challenges in both power and coherence. The solitons, being inherently mode-locked, are measured to provide 5.8 dB additional gain through constructive interference among mmWave beatnotes, and the absolute mmWave power approaches the theoretical limit of conventional heterodyne detection at 100 GHz. In our free-running system, the soliton is capable of reducing the mmWave linewidth by two orders of magnitude from that of the pump laser. Our work leverages microresonator solitons and high-speed modified uni-traveling carrier photodiodes to provide a viable path to chip-scale high-power, low-noise, high-frequency sources for mmWave applications.

physics.app-ph↗