arXiv subjects

Qian Feng

Publications and source records attributed to Qian Feng.

At least 19 recordsLinked to original sources

arXiv2026

REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching

Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental dilemma: data-driven methods require inefficient parameter scaling to implicitly learn rotations, whereas strictly equivariant networks lack the semantic capacity of modern VFMs. Consequently, current frameworks typically freeze VFMs and shift the entire burden of rotation generalization to the downstream decoder. To break this architectural bottleneck, we propose REDI-Match, an efficient framework driven by a novel Rotation-Equivariant Distillation (REDI) paradigm. Instead of relying on rotation data augmentation to establish rotational correspondences, REDI distills the non-equivariant semantic representations of a VFM into a lightweight, strictly rotation-equivariant encoder, leveraging an equivariant geometric architecture to constrain robust high-dimensional semantics. To fully exploit these features, we equip the decoder with an entropy-driven spatial alignment module. By evaluating discrete rotation hypotheses, this mechanism explicitly locks onto the canonical coordinate system, eliminating global ambiguity before continuous refinement. Extensive experiments demonstrate that REDI-Match establishes a new state-of-the-art (SOTA) across multiple benchmarks. Notably, it achieves a 13.89% absolute pose accuracy improvement on the highly challenging SatAst dataset while operating 1.9x faster than the current SOTA (RoMa v2), enabling real-time inference (~41 FPS) on a single RTX 4090 GPU. Code: https://github.com/YinjiGe/REDI-Match.

cs.CV↗

arXiv2026

Fusion-E2Pulse: A Multimodal Event-RGB Fusion Network for Non-contact Pulse Wave Reconstruction

Non-contact pulse wave reconstruction hinges on the precise recovery of waveform morphology, including the dicrotic notch. Conventional Red-Green-Blue (RGB)-based methods, which extract physiological signals from recorded facial videos, are constrained by the integral imaging mechanism of standard cameras, where the exposure process induces a smoothing effect that attenuates subtle vascular pulsation details. Conversely, neuromorphic event cameras, while offering exceptional sensitivity to intensity fluctuations, are inherently susceptible to noise and artifacts induced by minor motion. To exploit the synergy between frame-based integration and event-based differential sensing, we propose a novel multimodal network named Fusion-E2Pulse. This framework utilizes filtered RGB signals as structural priors to suppress motion artifacts, while leveraging the high-sensitivity of event streams to recover fine-grained morphological details. Experimental results demonstrate that Fusion-E2Pulse achieves state-of-the-art performance, effectively balancing noise suppression and morphological fidelity, achieving a mean absolute error of 0.78 bpm for heart rate estimation, a waveform correlation of 0.89, and a systolic phase duration error of 16.74 ms, validating its efficacy in reconstructing fine-grained pathological features.

cs.CV↗

arXiv2026

Detecting Black hole surrounded by perfect fluid dark matter in Kalb-Ramond fields using quasinormal modes

This paper investigates the characteristics of quasinormal modes (QNMs) of static, spherically symmetric black holes under the combined influence of spontaneous Lorentz symmetry breaking (LSB) induced by the Kalb-Ramond (KR) field and perfect fluid dark matter (PFDM). Using M87$^\ast$ shadow data from the Event Horizon Telescope (EHT), we constrain the LSB factor $\tau$ and PFDM parameter $\zeta$ at 1$\sigma$ confidence. By combining the sixth-order WKB approximation method with timedomain numerical integration, we systematically compute the complex frequency spectrum of QNMs for black holes in this spacetime background. The numerical results reveal an intriguing conclusion: as the LSB factor $\tau$ or the PFDM parameter $\zeta$ increases, both the real part and the absolute value of the imaginary part of the QNMs frequencies exhibit a monotonic increase, demonstrating a unique "stiffening" effect. This characteristic stands in stark contrast to the decreasing trend of QNMs frequencies observed in models that consider only traditional dark matter, revealing the critical influence of the coupling between the KR field and PFDM on the dynamic evolution of black holes. This study not only enriches and deepens the understanding of black hole perturbation theory within the framework of modified gravity but also, by identifying the distinctive spectral features of QNMs, offers the potential to distinguish whether the KR field and dark matter are coupled in future observations. Thus, it provides a theoretical foundation for testing mechanisms of spacetime symmetry breaking beyond the standard model and for exploring the nature of dark matter.

gr-qc↗

arXiv2026

EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection

Remote photoplethysmography (rPPG) based on traditional frame-based cameras often struggles with motion artifacts and limited temporal resolution. To address these limitations, we introduce EMPD (Event-based Multimodal Physiological Dataset), the first benchmark dataset specifically designed for non-contact physiological sensing via event cameras. The dataset leverages a laser-assisted acquisition system where a high-coherence laser modulates subtle skin vibrations from the radial artery into significant signals detectable by a neuromorphic sensor. The hardware platform integrates a high-resolution event camera to capture micro-motions and intensity transients, an industrial RGB camera to provide traditional rPPG benchmarks, and a clinical-grade pulse oximeter to record ground truth PPG waveforms. EMPD contains 193 valid records collected from 83 subjects, covering a wide heart rate range (40-110 BPM) under both resting and post-exercise conditions. By providing precisely synchronized multimodal data with microsecond-level temporal precision, EMPD serves as a crucial resource for developing robust algorithms in the field of neuromorphic physiological monitoring. The dataset is publicly available at: https://doi.org/10.5281/zenodo.18765701

eess.SP↗

arXiv2026

Dynamics of thin accretion disks and accretion around a charged-PFDM black hole

This paper investigates the dynamical behavior of steady spherical accretion onto a static, magnetically charged black hole embedded in a perfect fluid dark matter (PFDM) background. Using the shadow observations of M87* from the Event Horizon Telescope (EHT), we establish constraints on the parameter space for the magnetic charge and the PFDM parameter. Within this constrained range, we analyze the orbital dynamics of particles in a thin accretion disk surrounding the black hole and find that the black hole parameters significantly influence the effective potential, angular velocity, specific energy, and specific angular momentum of the particles. Subsequently, we calculate the radiative energy flux, temperature profile, and observed spectrum of the disk. Our results show that, while the local radiative flux and temperature at a given radius are lower for the charged-PFDM black hole compared to a Schwarzschild black hole, its overall radiative efficiency and total luminosity are higher. Finally, we explore the spherically symmetric, steady-state accretion process around the black hole, revealing how the parameters govern how the fluid velocity, density profile, and black hole mass accretion rate are influenced.

astro-ph.HE↗

arXiv2026

FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning

Incremental unlearning (IU) is critical for pre-trained models to comply with sequential data deletion requests, yet existing methods primarily suppress parameters or confuse knowledge without explicit constraints on both feature and gradient level, resulting in \textit{superficial forgetting} where residual information remains recoverable. This incomplete forgetting risks security breaches and disrupts retention balance, especially in IU scenarios. We propose FG-OrIU (\textbf{F}eature-\textbf{G}radient \textbf{Or}thogonality for \textbf{I}ncremental \textbf{U}nlearning), the first framework unifying orthogonal constraints on both features and gradients level to achieve deep forgetting, where the forgetting effect is irreversible. FG-OrIU decomposes feature spaces via Singular Value Decomposition (SVD), separating forgetting and remaining class features into distinct subspaces. It then enforces dual constraints: feature orthogonal projection on both forgetting and remaining classes, while gradient orthogonal projection prevents the reintroduction of forgotten knowledge and disruption to remaining classes during updates. Additionally, dynamic subspace adaptation merges newly forgetting subspaces and contracts remaining subspaces, ensuring a stable balance between removal and retention across sequential unlearning tasks. Extensive experiments demonstrate the effectiveness of our method.

cs.LG↗

arXiv2025

DeepMath-Creative: A Benchmark for Evaluating Mathematical Creativity of Large Language Models

To advance the mathematical proficiency of large language models (LLMs), the DeepMath team has launched an open-source initiative aimed at developing an open mathematical LLM and systematically evaluating its mathematical creativity. This paper represents the initial contribution of this initiative. While recent developments in mathematical LLMs have predominantly emphasized reasoning skills, as evidenced by benchmarks on elementary to undergraduate-level mathematical tasks, the creative capabilities of these models have received comparatively little attention, and evaluation datasets remain scarce. To address this gap, we propose an evaluation criteria for mathematical creativity and introduce DeepMath-Creative, a novel, high-quality benchmark comprising constructive problems across algebra, geometry, analysis, and other domains. We conduct a systematic evaluation of mainstream LLMs' creative problem-solving abilities using this dataset. Experimental results show that even under lenient scoring criteria -- emphasizing core solution components and disregarding minor inaccuracies, such as small logical gaps, incomplete justifications, or redundant explanations -- the best-performing model, O3 Mini, achieves merely 70% accuracy, primarily on basic undergraduate-level constructive tasks. Performance declines sharply on more complex problems, with models failing to provide substantive strategies for open problems. These findings suggest that, although current LLMs display a degree of constructive proficiency on familiar and lower-difficulty problems, such performance is likely attributable to the recombination of memorized patterns rather than authentic creative insight or novel synthesis.

cs.AI↗

arXiv2025

Krasovski\u{i} Stability Theorem for FDEs in the Extended Sense

The analysis of the stability of systems' equilibria plays a central role in the study of dynamical systems and control theory. This note establishes an extension of the celebrated Krasovski\u{\i} stability theorem for functional differential equations (FDEs) in the extended sense. Namely, the FDEs hold for $t \geq t_0$ almost everywhere with respect to the Lebesgue measure. The existence and uniqueness of such FDEs were briefly discussed in J.K Hale's classical treatise on FDEs, yet a corresponding stability theorem was not provided. A key step in proving the proposed stability theorem was to utilize an alternative strategy instead of relying on the mean value theorem of differentiable functions. The proposed theorem can be useful in the stability analysis of cybernetic systems, which are often subject to noise and glitches that have a countably infinite number of jumps. To demonstrate the usefulness of the proposed theorem, we provide examples of linear systems with time-varying delays in which the FDEs cannot be defined in the conventional sense.

math.OC↗

arXiv2025

Robust Control of General Linear Delay Systems under Dissipativity: Part I -- A KSD-based Framework

This paper introduces an effective framework for designing memoryless dissipative full-state feedback for general linear delay systems via the Krasovski\u{i} functional (KF) approach, where an arbitrary finite number of pointwise and general distributed delays (DDs) exists in the state, input and output. To handle the infinite dimensionality of DDs, we employ the Kronecker-Seuret Decomposition (KSD) which we recently proposed for analyzing matrix-valued functions in the context of delay systems. The KSD enables factorization or least-squares approximation of any number of $\fL^2$ DD kernels from any number of DDs without introducing conservatism. This also facilitates the construction of a complete-type KF with flexible integral kernels by means of a novel integral inequality derived from the least-squares principle. Our solution includes two theorems and an iterative algorithm to compute controller gains without relying on nonlinear solvers. A numerical example is tested to show the effectiveness of the proposed approach.

math.OC↗

arXiv2025

LensDFF: Language-enhanced Sparse Feature Distillation for Efficient Few-Shot Dexterous Manipulation

Learning dexterous manipulation from few-shot demonstrations is a significant yet challenging problem for advanced, human-like robotic systems. Dense distilled feature fields have addressed this challenge by distilling rich semantic features from 2D visual foundation models into the 3D domain. However, their reliance on neural rendering models such as Neural Radiance Fields (NeRF) or Gaussian Splatting results in high computational costs. In contrast, previous approaches based on sparse feature fields either suffer from inefficiencies due to multi-view dependencies and extensive training or lack sufficient grasp dexterity. To overcome these limitations, we propose Language-ENhanced Sparse Distilled Feature Field (LensDFF), which efficiently distills view-consistent 2D features onto 3D points using our novel language-enhanced feature fusion strategy, thereby enabling single-view few-shot generalization. Based on LensDFF, we further introduce a few-shot dexterous manipulation framework that integrates grasp primitives into the demonstrations to generate stable and highly dexterous grasps. Moreover, we present a real2sim grasp evaluation pipeline for efficient grasp assessment and hyperparameter tuning. Through extensive simulation experiments based on the real2sim pipeline and real-world experiments, our approach achieves competitive grasping performance, outperforming state-of-the-art approaches.

cs.RO↗

arXiv2025

CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary

Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work) concepts is undesirable, e.g., producing sexually explicit photos, and licensed images. The concept erasure task for T2I diffusion models has attracted considerable attention and requires an effective and efficient method. To achieve this goal, we propose a CE-SDWV framework, which removes the target concepts (e.g., NSFW concepts) of T2I diffusion models in the text semantic space by only adjusting the text condition tokens and does not need to re-train the original T2I diffusion model's weights. Specifically, our framework first builds a target concept-related word vocabulary to enhance the representation of the target concepts within the text semantic space, and then utilizes an adaptive semantic component suppression strategy to ablate the target concept-related semantic information in the text condition tokens. To further adapt the above text condition tokens to the original image semantic space, we propose an end-to-end gradient-orthogonal token optimization strategy. Extensive experiments on I2P and UnlearnCanvas benchmarks demonstrate the effectiveness and efficiency of our method. Code is available at https://github.com/TtuHamg/CE-SDWV.

cs.CV↗

arXiv2024

LW2G: Learning Whether to Grow for Prompt-based Continual Learning

Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while learning and select the correct set during inference. Previous studies have revealed that learning task-wised prompt sets individually and low selection accuracy pose challenges to the performance of PCL. In this paper, we propose a plug-in method, $\textbf{L}$earning $\textbf{W}$hether $\textbf{t}$o $\textbf{G}$row $\textbf{(LW2G)}$, which leverages the disparities between tasks to form an effective and efficient prompt sets pool, thereby achieving intra-task knowledge sharing and cooperation and avoiding the unbounded increase in the cost of the prompt pool. Specifically, a shared set is utilized when several tasks share certain commonalities, and a new set is added when there are significant differences between the new and previous tasks. To achieve this, we develop a metric called Hinder Forward Capability (HFC) to measure the hindrance imposed on learning new tasks by surgically modifying the original gradient onto the orthogonal complement of the old feature space. With HFC, an automated scheme, Dynamic Growing Approach, adaptively learns whether to grow with a dynamic threshold. Furthermore, we design a gradient-based constraint to ensure consistency between the updating prompts and pre-trained knowledge. Extensive experiments show the effectiveness of our method. Code is available at https://github.com/RAIAN08/LW2G.

cs.CV↗

arXiv2024

DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation

We introduce DexGanGrasp, a dexterous grasping synthesis method that generates and evaluates grasps with single view in real time. DexGanGrasp comprises a Conditional Generative Adversarial Networks (cGANs)-based DexGenerator to generate dexterous grasps and a discriminator-like DexEvalautor to assess the stability of these grasps. Extensive simulation and real-world expriments showcases the effectiveness of our proposed method, outperforming the baseline FFHNet with an 18.57% higher success rate in real-world evaluation. We further extend DexGanGrasp to DexAfford-Prompt, an open-vocabulary affordance grounding pipeline for dexterous grasping leveraging Multimodal Large Language Models (MLLMs) and Vision Language Models (VLMs), to achieve task-oriented grasping with successful real-world deployments.

cs.RO↗

arXiv2024

FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference

Synthesizing diverse, uncertainty-aware grasps for multi-fingered hands from partial observations remains a critical challenge in robot learning. Prior generative methods struggle to model the intricate grasp distribution of dexterous hands and often fail to reason about shape uncertainty inherent in partial point clouds, leading to unreliable or overly conservative grasps. We propose FFHFlow, a flow-based variational framework that generates diverse, robust multi-finger grasps while explicitly quantifying perceptual uncertainty in the partial point clouds. Our approach leverages a normalizing flow-based deep latent variable model to learn a hierarchical grasp manifold, overcoming the mode collapse and rigid prior limitations of conditional Variational Autoencoders (cVAEs). By exploiting the invertibility and exact likelihoods of flows, FFHFlow introspects shape uncertainty in partial observations and identifies novel object structures, enabling risk-aware grasp synthesis. To further enhance reliability, we integrate a discriminative grasp evaluator with the flow likelihoods, formulating an uncertainty-aware ranking strategy that prioritizes grasps robust to shape ambiguity. Extensive experiments in simulation and real-world setups demonstrate that FFHFlow outperforms state-of-the-art baselines (including diffusion models) in grasp diversity and success rate, while achieving run-time efficient sampling. We also showcase its practical value in cluttered and confined environments, where diversity-driven sampling excels by mitigating collisions (Project Page: https://sites.google.com/view/ffhflow/home/).

cs.RO↗

arXiv2024

PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer

Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples (rehearsal-free) and with a memory constraint (memory-constrained): Prompt-extending and Prompt-fixed methods. However, prompt-extending methods need a large memory buffer to maintain an ever-expanding prompt pool and meet an extra challenging prompt selection problem. Prompt-fixed methods only learn a single set of prompts on one of the incremental tasks and can not handle all the incremental tasks effectively. To achieve a good balance between the memory cost and the performance on all the tasks, we propose a Parameter-Efficient Cross-Task Prompt (PECTP) framework with Prompt Retention Module (PRM) and classifier Head Retention Module (HRM). To make the final learned prompts effective on all incremental tasks, PRM constrains the evolution of cross-task prompts' parameters from Outer Prompt Granularity and Inner Prompt Granularity. Besides, we employ HRM to inherit old knowledge in the previously learned classifier heads to facilitate the cross-task prompts' generalization ability. Extensive experiments show the effectiveness of our method. The source codes will be available at \url{https://github.com/RAIAN08/PECTP}.

cs.CV↗

arXiv2024

Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation

Learning from demonstrations faces challenges in generalizing beyond the training data and often lacks collision awareness. This paper introduces Lan-o3dp, a language-guided object-centric diffusion policy framework that can adapt to unseen situations such as cluttered scenes, shifting camera views, and ambiguous similar objects while offering training-free collision avoidance and achieving a high success rate with few demonstrations. We train a diffusion model conditioned on 3D point clouds of task-relevant objects to predict the robot's end-effector trajectories, enabling it to complete the tasks. During inference, we incorporate cost optimization into denoising steps to guide the generated trajectory to be collision-free. We leverage open-set segmentation to obtain the 3D point clouds of related objects. We use a large language model to identify the target objects and possible obstacles by interpreting the user's natural language instructions. To effectively guide the conditional diffusion model using a time-independent cost function, we proposed a novel guided generation mechanism based on the estimated clean trajectories. In the simulation, we showed that diffusion policy based on the object-centric 3D representation achieves a much higher success rate (68.7%) compared to baselines with simple 2D (39.3%) and 3D scene (43.6%) representations across 21 challenging RLBench tasks with only 40 demonstrations. In real-world experiments, we extensively evaluated the generalization in various unseen situations and validated the effectiveness of the proposed zero-shot cost-guided collision avoidance.

cs.RO↗

arXiv2024

Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners

Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous works makes LLM-based planning error-prone and fragile. On the other hand, failure detection approaches for closed-loop planning are often limited by task-specific heuristics or following an unrealistic assumption that the prediction is trustworthy all the time. As a general-purpose reasoning machine, LLMs or Multimodal Large Language Models (MLLMs) are promising for detecting failures. However, However, the appropriateness of the aforementioned assumption diminishes due to the notorious hullucination problem. In this work, we attempt to mitigate these issues by introducing a framework for closed-loop LLM-based planning called KnowLoop, backed by an uncertainty-based MLLMs failure detector, which is agnostic to any used MLLMs or LLMs. Specifically, we evaluate three different ways for quantifying the uncertainty of MLLMs, namely token probability, entropy, and self-explained confidence as primary metrics based on three carefully designed representative prompting strategies. With a self-collected dataset including various manipulation tasks and an LLM-based robot system, our experiments demonstrate that token probability and entropy are more reflective compared to self-explained confidence. By setting an appropriate threshold to filter out uncertain predictions and seek human help actively, the accuracy of failure detection can be significantly enhanced. This improvement boosts the effectiveness of closed-loop planning and the overall success rate of tasks.

cs.RO↗

arXiv2024

High Spectral-Efficiency, Ultra-low MIMO SDM Transmission over a Field-Deployed Multi-Core OAM Fiber

Few-mode multi-core fiber (FM-MCF) based Space-Division Multiplexing (SDM) systems possess the potential to maximize the number of multiplexed spatial channels per fiber by harnessing both the space (fiber cores) and mode (optical mode per core) dimensions. However, to date, no SDM transmissions over field-deployed FM-MCFs in realistic outdoor settings have been reported, which contrasts with SDM schemes demonstrated using single-mode multi-core fibers (SM-MCFs) installed in practical fiber cable ducts. In this paper, we present the successful demonstration of bidirectional SDM transmission over a 5-km field-deployed seven ring-core fiber (7-RCF) with a cladding diameter of 178 ${\mu}$m, achieving a Spectral Efficiency (SE) of 2$\times$201.6 bit/s/Hz. This work establishes a new record for the highest SE attained in SDM demonstrations utilizing field-deployed fiber cables, achieving an approximate 10x increase compared to the SE of reported field-deployed optical fiber cable transmission systems. Notably, these results are realized through the utilization of small-scale modular 4$\times$4 multiple-input multiple-output (MIMO) processing with a time-domain equalization (TDE) tap number not exceeding 15, maintaining a complexity per unit capacity comparable to that of MIMO equalization in SDM demonstrations employing weakly coupled SM-MCF cables. These results underscore the significant potential for achieving heightened SE and expanding capacity per individual fiber using SDM techniques in practical applications.

cs.NI↗