arXiv subjects

Hongyi Chen

Publications and source records attributed to Hongyi Chen.

At least 19 recordsLinked to original sources

arXiv2026

High Fidelity Capture, Reconstruction, and Transfer of Human Demonstrations for Robot-Assisted Bathing

Despite the demand for robots in high-value clinical tasks like bathing, contemporary systems still lack the safety and reliability required for complex, sustained physical interaction with humans. A key challenge hindering the development of such systems is that collecting, understanding, and effectively transferring highly dynamic, contact-rich human bathing demonstrations is difficult, even with modern motion and tactile sensing equipment. We present a straightforward, but effective framework for doing so with high fidelity by utilizing contact regions as a key processing primitive. We use our framework to build a dataset of bathing demonstrations performed by trained clinicians on human subjects. We then use this dataset to design and control an arm-mounted dexterous soft hand to perform bathing tasks on a mannequin using open- and closed-loop strategies. Our dataset is the first to provide high quality synchronized motion, shape, contact, and force during sustained, contact-rich human-human interaction, and our transfer strategies demonstrate effective use of these data across multiple levels of the robotics stack. All relevant materials will be publicly released to enable further advancements in physical human-robot interaction (pHRI) research.

cs.RO↗

arXiv2026

IR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensing

Efficient processing is becoming increasingly important in infrared remote sensing, where satellite constellations produce large volumes of observations under constrained detector resolution, power, and downlink bandwidth. Multi-frame super-resolution (MFSR) offers a software-based route to spatial enhancement, but its evaluation in infrared sensing remains fragmented across private datasets and ad-hoc protocols. Existing benchmarks do not explicitly capture the thermal contrast, sensor noise, weak texture, and platform-induced frame-to-frame variation that characterize infrared video. We introduce IR275K, a curated benchmark containing 594 infrared video sequences and 275,196 frames. It provides sequence-level train/validation/test splits and a reproducible X4 evaluation protocol. As an initial architectural probe, we further evaluate CGMamba, a lightweight state-space model with 10.90M parameters and 112.14G FLOPs. CGMamba combines 2D rotary position encoding (2D~RoPE) with center-guided cross-Mamba (CGCM) fusion for implicit multi-frame reconstruction. It achieves 33.19dB PSNR, outperforming infrared single-image super-resolution references by 0.35--0.52~dB at substantially lower computational cost. Ablation results show that removing 2D~RoPE from CGCM causes a 1.53dB drop and severe grid-like artifacts. This indicates that explicit spatial anchoring is critical for stabilizing SSM-based cross-frame gating under infrared conditions. IR275K provides a reproducible foundation for accuracy--efficiency evaluation of infrared MFSR methods, while the architectural analysis offers a concrete starting point for spatially aware SSM design under resource-constrained infrared sensing. Dataset and evaluation resources are available at: https://github.com/InfraRecon7/IR275K.

cs.CV↗

arXiv2026

Martin Boundary and Invariant Fields of Multiplicative SHE

We study invariant measures of nonlinear multiplicative stochastic heat equations in the weak disorder regime. Under a natural second-moment condition, we show that positive invariant measures are in one-to-one correspondence with bounded positive harmonic functions of the underlying space. This implies that the space of invariant measures inherits the structure of the Martin boundary. We also show that whenever the deterministic semigroup flow converges to a bounded harmonic function, the stochastic evolution converges to the corresponding invariant measure. The results apply to many settings with nontrivial Martin boundary, such as negatively curved manifolds and trees.

math.PR↗

arXiv2026

SemAnCorr: Semantic Anchored Correspondence for Zero-Shot Manipulation Skill Transfer

Transferring manipulation skills across object instances that share functionality but differ in geometry remains a fundamental challenge in robot learning. While recent correspondence methods leverage dense visual descriptors and 3D feature fields, nearest-neighbor feature matching often produces spatially incoherent correspondences that fail to recover the local geometric frames required for reliable skill transfer. We introduce SemAnCorr, a training-free framework that establishes dense correspondence by selecting semantically consistent anchor regions through joint pose-correspondence optimization and propagating these constraints over the object surface using functional maps. The resulting correspondences preserve both semantic consistency and geometric coherence, enabling object-centric manipulation skills to transfer across geometrically diverse instances. We evaluate SemAnCorr on a dense correspondence benchmark built on PartNet-Mobility, achieving 90.8% semantic accuracy in our benchmark evaluation while improving geometric coherence over recent state-of-the-art baselines. Finally, we show that these improvements translate directly into real-world manipulation performance: using a single demonstration, SemAnCorr enables substantially more reliable zero-shot manipulation skill transfer to previously unseen objects than existing correspondence methods. Videos and additional visualizations are available at [https://semancorr.github.io](https://semancorr.github.io) .

cs.RO↗

arXiv2026

FARS: A Fully Automated Research System Deployed at Scale

Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few pre-defined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes. We evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

cs.AI↗

arXiv2026

Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation

Developing high-performance kernels for Neural Processing Units (NPUs) is a critical industry bottleneck, requiring developers to manually navigate implicit hardware constraints and strict memory hierarchies. While large language models offer immense automation potential, they fail catastrophically on NPUs due to a fundamental lack of hardware-specific priors. Naively transplanting code snippets from similar NPU kernels may pass the compiler, but it consistently triggers runtime crashes and performance degradation by blindly violating underlying hardware constraints. To overcome this, we introduce Hawk, a training-free framework that harnesses hardware-aware knowledge through three core modules: (1) Run-Time Knowledge Synthesis Module, which employs a Triple-Part Executable Knowledge Representation to inherently couple the error context with executable semantics; (2) Bottleneck-Aware Knowledge Retrieval Module, which implements a 2D-Retrieval paradigm to project queries into orthogonal syntactic and hardware-aligned semantic spaces; and (3) Effect-Driven Knowledge Distillation Module, which leverages LLM-driven semantic arbitration to continuously distill the knowledge by pruning errors and consolidating redundancies based on the empirical execution feedback. Extensive evaluations on real-world NPU workloads demonstrate that Hawk elevates generation accuracy from 49.4% to 80.0%, while achieving up to a 2.2x execution speedup over state-of-the-art baselines.

cs.AI↗

arXiv2026

Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions

Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. Prior work largely focuses on power grasps, which only involve holding an object, or relies on in-domain demonstrations for specific objects. We propose leveraging human grasp information extracted from web images, which capture natural and functional hand-object interactions (HOI). Using a pretrained 3D reconstruction model, we recover 3D human HOI meshes from RGB images. To train on these noisy HOI data, we propose to use: (1) an interaction-centric model to learn the functional interaction pattern between hand and object, and (2) geometry-based filtering to remove the infeasible grasps and physical simulation to retain grasps who can resist disturbance. In IssacGym simulation, our model trained on reconstructed HOI grasps achieves a 75.8% success rate on objects from the web dataset and generalizes to unseen objects, outperforming baseline methods in both grasp success and functional quality. In real-world experiments with the LEAP hand and Inspire hand, it attains a 77.5% success rate across 12 objects, including challenging ones such as a syringe, spray bottle, knife, and tongs. Project website is at: https://web2grasp.github.io/.

cs.CV↗

arXiv2026

Wick Renormalized Parabolic Stochastic Quantization Equations on Rough Metric Measure Spaces

On metric measure spaces with sub-Gaussian heat kernel behavior in small time, we obtain a sufficient condition to solve Wick renormalized stochastic quantization equations with polynomial interaction. Given the power of the nonlinearity, the local solution condition depends on the Hausdorff dimension $d_h$, the walk dimension $d_w$, and the maximal spatial Hölder regularity of the heat kernel $Θ$. A slightly more restrictive condition based on the same parameters is required for a global solution. For all global solutions, we construct an invariant measure for the Markov process defined by the solution. Our results apply to many rough spaces such as Barlow--Kigami type fractals as well as their Cartesian products and open up the possibility of making rigorous various structures in quantum field theory and statistical mechanics in non-integer dimensions. In the process, we build entirely from the short-time heat semigroup the necessary analytic framework that accommodates the issues which come with allowing rough local geometry.

math.PR↗

arXiv2026

Propagation of Singularities for the Damped Stochastic Klein-Gordon Equation

For the $1+1$ dimensional damped stochastic Klein-Gordon equation, we show that random singularities associated with the law of the iterated logarithm exist and propogate in the same way as the stochastic wave equation. This provides evidence for possible connections to microlocal analysis, ie. the exact regularity and singularities described in this paper should admit wavefront set type descriptions whose propagation is determined by the highest order terms of the linear operator. Despite the results being exactly the same as those of the wave equation, our proofs are significantly different than the proofs for the wave equation. Miraculously, proving our results for the critically damped equation implies them for the general equation, which significantly simplifies the problem. Even after this simplification, many important parts of the proof are significantly different than (and we think are more intuitive from the PDE viewpoint compared to) existing proofs for the wave equation.

math.PR↗

arXiv2026

Faster Deterministic Streaming Vertex Coloring

Graph coloring is a fundamental problem in computer science. In the semi-streaming model, an input graph $G$ on $n$ vertices and maximum degree $Δ$ is presented as a stream of edges, and the goal is to compute a vertex coloring using a small number of colors while storing only $\tilde{O}(n)$ bits of memory. Recent work has revealed an exponential separation between randomized and deterministic approaches in this setting: while randomized algorithms can achieve a $(Δ+1)$-coloring in a single pass [Assadi, Chen, and Khanna, 2019], any single-pass deterministic algorithm requires $\exp(Δ^{Ω(1)})$ colors [Assadi, Chen, and Sun, 2022]. Consequently, deterministic algorithms that use few colors must necessarily make multiple passes over the stream. Prior to this work, the best known deterministic trade-offs were: an $O(Δ^2)$-coloring in 2 passes, an $O(Δ)$-coloring in $O(\log Δ)$ passes [Assadi, Chen, and Sun, 2022], and a $(Δ+1)$-coloring in $O(\log Δ\cdot \log\log Δ)$ passes [Assadi, Chakrabarti, Ghosh, and Stoeckl, 2023]. It remained open whether better trade-offs -- particularly with sub-logarithmic pass complexity and linear-in-$Δ$ palette size -- were achievable. In this paper, we present a new deterministic semi-streaming algorithm that computes an $O(Δ)$-coloring in $O(\sqrt{\log Δ})$ passes. This is the first deterministic streaming algorithm to achieve a coloring with palette size linear-in-$Δ$ using sublogarithmic-in-$Δ$ passes.

cs.DS↗

arXiv2026

SkinGPT-X: A Self-Evolving Collaborative Multi-Agent System for Transparent and Trustworthy Dermatological Diagnosis

While recent advancements in Large Language Models have significantly advanced dermatological diagnosis, monolithic LLMs frequently struggle with fine-grained, large-scale multi-class diagnostic tasks and rare skin disease diagnosis owing to training data sparsity, while also lacking the interpretability and traceability essential for clinical reasoning. Although multi-agent systems can offer more transparent and explainable diagnostics, existing frameworks are primarily concentrated on Visual Question Answering and conversational tasks, and their heavy reliance on static knowledge bases restricts adaptability in complex real-world clinical settings. Here, we present SkinGPT-X, a multimodal collaborative multi-agent system for dermatological diagnosis integrated with a self-evolving dermatological memory mechanism. By simulating the diagnostic workflow of dermatologists and enabling continuous memory evolution, SkinGPT-X delivers transparent and trustworthy diagnostics for the management of complex and rare dermatological cases. To validate the robustness of SkinGPT-X, we design a three-tier comparative experiment. First, we benchmark SkinGPT-X against four state-of-the-art LLMs across four public datasets, demonstrating its state-of-the-art performance with a +9.6% accuracy improvement on DDI31 and +13% weighted F1 gain on Dermnet over the state-of-the-art model. Second, we construct a large-scale multi-class dataset covering 498 distinct dermatological categories to evaluate its fine-grained classification capabilities. Finally, we curate the rare skin disease dataset, the first benchmark to address the scarcity of clinical rare skin diseases which contains 564 clinical samples with eight rare dermatological diseases. On this dataset, SkinGPT-X achieves a +9.8% accuracy improvement, a +7.1% weighted F1 improvement, a +10% Cohen's Kappa improvement.

cs.CV↗

arXiv2026

Sharp Riemannian heat kernel estimates on the cut locus and the Parabolic Anderson model

Using sharp global heat kernel bounds and geodesic comparison geometry, we show that the Dalang condition for well-posedness of the parabolic Anderson model with measure-valued initial conditions, first introduced on Euclidean space, holds on general compact Riemannian manifolds. We furthermore establish upper and lower moment bounds for all such solutions, providing evidence for intermittency in this generality. This extends and simplifies earlier work that required non-positive curvature.

math.PR↗

arXiv2026

Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction

Multi-finger robotic hand manipulation and grasping are challenging due to the high-dimensional action space and the difficulty of acquiring large-scale training data. Existing approaches largely rely on human teleoperation with wearable devices or specialized sensing equipment to capture hand-object interactions, which limits scalability. In this work, we propose VIDEOMANIP, a device-free framework that learns dexterous manipulation directly from RGB human videos. Leveraging recent advances in computer vision, VIDEOMANIP reconstructs explicit 3D robot-object trajectories from monocular videos by estimating human hand poses, object meshes, and retargets the reconstructed human motions to robotic hands for manipulation learning. To make the reconstructed robot data suitable for dexterous manipulation training, we introduce hand-object contact optimization with interaction-centric grasp modeling, as well as a demonstration synthesis strategy that generates diverse training trajectories from a single video, enabling generalizable policy learning without additional robot demonstrations. In simulation, the learned grasping model achieves a 70.25% success rate across 20 diverse objects using the Inspire Hand. In the real world, manipulation policies trained from RGB videos achieve an average 62.86% success rate across seven tasks using the LEAP Hand, outperforming retargeting-based methods by 15.87%. Project videos are available at videomanip.github.io.

cs.RO↗

arXiv2026

Sample-Efficient Diffusion-based Control of Complex Physics Systems

Controlling complex physics systems is important in diverse domains. While diffusion-based methods have demonstrated advantages over classical model-based approaches and myopic sequential learning methods in achieving global trajectory consistency, they are limited by sample efficiency.This paper presents SEDC (Sample-Efficient Diffusion-based Control), a novel framework addressing core challenges in complex physics systems: high-dimensional state-control spaces, strong nonlinearities, and the gap between non-optimal training data and near-optimal control laws.Our approach introduces a novel control paradigm by architecturally decoupling state-control modeling and decomposing dynamics, while a guided self-finetuning process iteratively refines the control law towards optimality. We validate SEDC across diverse complex nonlinear systems, including high-dimensional fluid dynamics (Burgers), chaotic synchronization networks (Kuramoto), and real-world power grid stability control (Swing Equation). Our method achieves 39.5\%-47.3\% better control accuracy than state-of-the-art baselines while using only 10\% of the training samples. The implementation is available at \href{https://anonymous.4open.science/r/DIFOCON-C019}{here}.

eess.SY↗

arXiv2025

CEMG: Collaborative-Enhanced Multimodal Generative Recommendation

Generative recommendation models often struggle with two key challenges: (1) the superficial integration of collaborative signals, and (2) the decoupled fusion of multimodal features. These limitations hinder the creation of a truly holistic item representation. To overcome this, we propose CEMG, a novel Collaborative-Enhaned Multimodal Generative Recommendation framework. Our approach features a Multimodal Fusion Layer that dynamically integrates visual and textual features under the guidance of collaborative signals. Subsequently, a Unified Modality Tokenization stage employs a Residual Quantization VAE (RQ-VAE) to convert this fused representation into discrete semantic codes. Finally, in the End-to-End Generative Recommendation stage, a large language model is fine-tuned to autoregressively generate these item codes. Extensive experiments demonstrate that CEMG significantly outperforms state-of-the-art baselines.

cs.IR↗

arXiv2025

Global Geometry within an SPDE Well-Posedness Problem

On a closed Riemannian manifold, we construct a family of intrinsic Gaussian noises indexed by a regularity parameter $α\geq0$ to study the well-posedness of the parabolic Anderson model. We show that with rough initial conditions, the equation is well-posed assuming non-positive curvature with a condition on $α$ similar to that of Riesz kernel-correlated noise in Euclidean space. Non-positive curvature was used to overcome a new difficulty introduced by non-uniqueness of geodesics in this setting, which required exploration of global geometry. The well-posedness argument also produces exponentially growing in time upper bounds for the moments. Using Feynman-Kac formula for moments, we also obtain exponentially growing in time second moment lower bounds for our solutions with bounded initial condition.

math.PR↗

arXiv2025

PID-controlled Langevin Dynamics for Faster Sampling of Generative Models

Langevin dynamics sampling suffers from extremely low generation speed, fundamentally limited by numerous fine-grained iterations to converge to the target distribution. We introduce PID-controlled Langevin Dynamics (PIDLD), a novel sampling acceleration algorithm that reinterprets the sampling process using control-theoretic principles. By treating energy gradients as feedback signals, PIDLD combines historical gradients (the integral term) and gradient trends (the derivative term) to efficiently traverse energy landscapes and adaptively stabilize, thereby significantly reducing the number of iterations required to produce high-quality samples. Our approach requires no additional training, datasets, or prior information, making it immediately integrable with any Langevin-based method. Extensive experiments across image generation and reasoning tasks demonstrate that PIDLD achieves higher quality with fewer steps, making Langevin-based generative models more practical for efficiency-critical applications. The implementation can be found at \href{https://github.com/tsinghua-fib-lab/PIDLD}{https://github.com/tsinghua-fib-lab/PIDLD}.

cs.LG↗

arXiv2025

DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization

Prompt Optimization has emerged as a crucial approach due to its capabilities in steering Large Language Models to solve various tasks. However, current works mainly rely on the random rewriting ability of LLMs, and the optimization process generally focus on specific influencing factors, which makes it easy to fall into local optimum. Besides, the performance of the optimized prompt is often unstable, which limits its transferability in different tasks. To address the above challenges, we propose $\textbf{DelvePO}$ ($\textbf{D}$irection-Guid$\textbf{e}$d Se$\textbf{l}$f-E$\textbf{v}$olving Framework for Fl$\textbf{e}$xible $\textbf{P}$rompt $\textbf{O}$ptimization), a task-agnostic framework to optimize prompts in self-evolve manner. In our framework, we decouple prompts into different components that can be used to explore the impact that different factors may have on various tasks. On this basis, we introduce working memory, through which LLMs can alleviate the deficiencies caused by their own uncertainties and further obtain key insights to guide the generation of new prompts. Extensive experiments conducted on different tasks covering various domains for both open- and closed-source LLMs, including DeepSeek-R1-Distill-Llama-8B, Qwen2.5-7B-Instruct and GPT-4o-mini. Experimental results show that DelvePO consistently outperforms previous SOTA methods under identical experimental settings, demonstrating its effectiveness and transferability across different tasks.

cs.CL↗