SearcharxivSearch

arXiv subjects

Junyi Huang

Publications and source records attributed to Junyi Huang.

13 recordsLinked to original sources

Counting Beyond Instances: A Benchmark for Group-Individual Object Counting

Visual counting is commonly formulated at the instance level, aiming to estimate how many objects of a queried category appear in an image. However, real-world counting often involves higher-level semantic units formed by multiple instances, such as a bunch of grapes, a stack of plates, or a pair of shoes. This exposes a key limitation of existing counting formulations, which mainly focus on what to count, while largely overlooking at which semantic unit to count. We introduce Group-Individual Object Counting (GIC), a new setting that requires models to count both individual objects and semantic groups within a unified framework. To support this new task, we present BunchCount, a real-world benchmark with 1,330 images, 89,254 individual annotations, and 11,065 group annotations. BunchCount provides paired individual-group annotations within the same image and explicitly records containment relations between each group and its constituent individuals. Experiments on BunchCount show that current advanced counting models perform well on individual instances but fail to count semantic groups more accurately. To mitigate semantic granularity conflict, we propose a counting-unit guided relational counting framework, which exploits group-individual containment relations to regularize cross-granularity representations during training. Our method substantially improves group-level counting while better preserving individual-level counting ability, establishing a strong baseline for counting beyond instances.

cs.CV

InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation

Pre-trained Vision-Language-Action (VLA) models provide useful semantic and spatial priors, yet their parallel-gripper action interfaces do not specify how those priors should be realized by a dexterous hand. Directly appending finger joints conflates two decisions with different structure: when contact should be established and how a morphology-specific hand trajectory should establish it. We introduce InDex, an intent-conditioned adaptation framework that separates these decisions without discarding full hand supervision. InDex derives a normalized grasp intent from retargeted demonstrations. A first stage predicts synchronized end-effector--intent chunks; conditioned on these predictions, VLA context, and proprioception, a diffusion decoder generates multi-joint hand actions. The scalar intent is therefore a temporal coordination interface rather than a compressed hand pose. Across four simulated tasks, three VLA backbones, and a physical arm--hand platform, InDex preserves the VLA's reaching competence while markedly improving conversion from approach to stable grasp and task completion. Ablations isolate complementary roles: intent aligns the contact transition, whereas diffusion represents the multiple hand trajectories compatible with the same task-space plan. These results identify post-reach arm--hand coordination, rather than object localization alone, as the principal bottleneck in adapting parallel-gripper VLAs to dexterous manipulation.

cs.RO

Revisiting RFID Missing Tag Identification

We revisit the problem of missing tag identification in RFID networks by making three contributions. Firstly, we quantitatively compare and gauge the existing propositions spanning over a decade on missing tag identification. We show that the expected execution time of the best solution in the literature is $\Theta \left(N+\frac{(1-\alpha)^2(1-\delta)^2}{ \epsilon^2}\right)$, where $\delta$ and $\epsilon$ are parameters quantifying the required identification accuracy, $N$ denotes the number of tags in the system, among which $\alpha N$ tags are missing. Secondly, we analytically establish the expected execution time lower-bound for any missing tag identification algorithm as $\Theta\left(\frac{N}{\log N}+\frac{(1-\delta)^2(1-\alpha)^2}{\epsilon^2 \log \frac{(1-\delta)(1-\alpha)}{\epsilon}}\right)$, thus giving the theoretical performance limit. Thirdly, we develop a novel missing tag identification algorithm by leveraging a tree structure with the expected execution time of $\Theta \left(\frac{\log\log N}{\log N}N+\frac{(1-\alpha)^2(1-\delta)^2}{ \epsilon^2}\right)$, reducing the time overhead by a factor of up to $\log N$ over the best algorithm in the literature. The key technicality in our design is a novel data structure termed as collision-partition tree (CPT), built on a subset of bits in tag pseudo-IDs, leading to more balanced tree structure and reducing the time complexity in parsing the entire tree.

cs.NI

Wavelength-division multiplexing optical Ising simulator enabling fully programmable spin couplings and external magnetic fields

Recently, spatial photonic Ising machines (SPIMs) have demonstrated the abilities to compute the Ising Hamiltonian of large-scale spin systems, with the advantages of ultrafast speed and high power efficiency. However, such optical computations have been limited to specific Ising models with fully connected couplings. Here we develop a wavelength-division multiplexing SPIM to enable programmable spin couplings and external magnetic fields as well for general Ising models. We experimentally demonstrate such a wavelength-division multiplexing SPIM with a single spatial light modulator, where the gauge transformation is implemented to eliminate the impact of pixel alignment. To show the programmable capability of general spin coupling interactions, we explore three spin systems: $\pm J$ models, Sherrington-Kirkpatrick models, and only locally connected ${{J}_{1}}\texttt{-}{{J}_{2}}$ models and observe the phase transitions among the spin-glass, the ferromagnetic, the paramagnetic and the stripe-antiferromagnetic phases. These results show that the wavelength-division multiplexing approach has great programmable flexibility of spin couplings and external magnetic fields, which provides the opportunities to solve general combinatorial optimization problems with large-scale and on-demand SPIM.

physics.optics

Observation of acoustic spatiotemporal vortices

Vortices in fluids and gases have piqued the interest of human for centuries. Development of classical-wave physics and quantum mechanics highlighted wave vortices characterized by phase singularities and topological charges. In particular, vortex beams have found numerous applications in modern optics and other areas. Recently, optical spatiotemporal vortex states exhibiting the phase singularity both in space and time have been reported. Here, we report the first generation of acoustic spatiotemporal vortex pulses. We utilize an acoustic meta-grating with mirror-symmetry breaking as the spatiotemporal vortex generator. In the momentum-frequency domain, we unravel that the transmission spectrum functions exhibit a topological phase transition where the vortices with opposite topological charges are created or annihilated in pairs. Furthermore, with the topological textures of the nodal lines, these vortices are robust and exploited to generate spatiotemporal vortex pulse against structural perturbations and disorder. Our work paves the way for studies and applications of spatiotemporal structured waves in acoustics and other wave systems.

physics.app-ph

Roadmap on spatiotemporal light fields

Spatiotemporal sculpturing of light pulse with ultimately sophisticated structures represents the holy grail of the human everlasting pursue of ultrafast information transmission and processing as well as ultra-intense energy concentration and extraction. It also holds the key to unlock new extraordinary fundamental physical effects. Traditionally, spatiotemporal light pulses are always treated as spatiotemporally separable wave packet as solution of the Maxwell's equations. In the past decade, however, more generalized forms of spatiotemporally nonseparable solution started to emerge with growing importance for their striking physical effects. This roadmap intends to highlight the recent advances in the creation and control of increasingly complex spatiotemporally sculptured pulses, from spatiotemporally separable to complex nonseparable states, with diverse geometric and topological structures, presenting a bird's eye viewpoint on the zoology of spatiotemporal light fields and the outlook of future trends and open challenges.

physics.optics

Topologically protected generation of spatiotemporal optical vortices with nonlocal spatial-mirror-symmetry-breaking metasurface

Recently nonlocal spatial-mirror-symmetry-breaking metasurfaces have been proposed to generate spatiotemporal optical vortices (STOVs), which carry transverse orbital angular momenta. Here we investigate the topological property of the STOV generator and show that spatial mirror symmetry breaking introduces a synthetic parameter dimension associated with the metasurface geometry. Furthermore, we demonstrate that there are well-defined vortices emerging with the synthetic parameter dimension, which can topologically protect the STOV generation robustly against structural perturbations and disorders. Since the vortices are always `created' or `annihilated' together in pairs of opposite charges in the ${{k}_{x}}\!-\!\omega $ domain, the total topological charge of these vortices is a conserved quantity. Our studies not only provide a new topological perspective for STOV generation but also lay a solid foundation for potential applications of STOV metasurfaces integrated with other optoelectronic devices, because of their robust immunity to fabrication defects.

physics.optics

Solving the Families In the Wild Kinship Verification Challenge by Program Synthesis

Kinship verification is the task of determining whether a parent-child, sibling, or grandparent-grandchild relationship exists between two people and is important in social media applications, forensic investigations, finding missing children, and reuniting families. We demonstrate high quality kinship verification by participating in the 2021 Recognizing Families in the Wild challenge which provides the largest publicly available dataset in the field. Our approach is among the top 3 winning entries in the competition. We ensemble models written by both human experts and a foundation model, OpenAI Codex, trained on text and code. We use Codex to generate model variants, and also demonstrate its ability to generate entire running programs for kinship verification tasks of specific relationships.

cs.CV

Spatiotemporal differentiators generating optical vortices with transverse orbital angular momentum and detecting sharp change of pulse envelope

As a new degree of freedom for optical manipulation, recently spatiotemporal optical vortices (STOVs) carrying transverse orbital angular momentums have been experimentally demonstrated with pulse shapers. Here a spatiotemporal differentiator is proposed to generate STOVs with transverse orbital angular momentum. In order to create phase singularity in the spatiotemporal domain, the spatiotemporal differentiator is designed by breaking spatial mirror symmetry. In contrast to pulse shapers, the device proposed here is a simple one-dimensional periodic nanostructure and thus it is much more compact. For a normal incident pulse, the differentiator generates a transmitted STOV pulse with transverse orbital angular momentum. Furthermore, the interference of the generated STOVs can be used to detect the sharp changes of pulse envelopes, in both spatial and temporal dimensions.

physics.optics

Antiferromagnetic spatial photonic Ising machine through optoelectronic correlation computing

Recently, spatial photonic Ising machines (SPIM) have been demonstrated to compute the minima of Hamiltonians for large-scale spin systems. Here we propose to implement an antiferromagnetic model through optoelectronic correlation computing with SPIM. Also we exploit the gauge transformation which enables encoding the spins and the interaction strengths in a single phase-only spatial light modulator. With a simple setup, we experimentally show the ground state search of an antiferromagnetic model with $40000$ spins in number-partitioning problem. Thus such an optoelectronic computing exhibits great programmability and scalability for the practical applications of studying statistical systems and combinatorial optimization problems.

cs.ET

Experimental Observation of Phase Transitions in Spatial Photonic Ising Machine

Statistical spin dynamics plays a key role to understand the working principle for novel optical Ising machines. Here we propose the gauge transformations for spatial photonic Ising machine, where a single spatial phase modulator simultaneously encodes spin configurations and programs interaction strengths. Thanks to gauge transformation, we experimentally evaluate the phase diagram of high-dimensional spin-glass equilibrium system with $100$ fully-connected spins. We observe the presence of paramagnetic, ferromagnetic as well as spin-glass phases and determine the critical temperature $T_c$ and the critical probability ${{p}_{c}}$ of phase transitions, which agree well with the mean-field theory predictions. Thus the approximation of the mean-field model is experimentally validated in the spatial photonic Ising machine. Furthermore, we discuss the phase transition in parallel with solving combinatorial optimization problems during the cooling process and identify that the spatial photonic Ising machine is robust with sufficient many-spin interactions, even when the system is associated with the optical aberrations and the measurement uncertainty.

cond-mat.dis-nn

Optical phase mining by adjustable spatial differentiator

Phase is a fundamental resource for optical imaging but cannot be directly observed with intensity measurements. The existing methods to quantify a phase distribution rely on complex devices and structures. Here we experimentally demonstrate a phase mining method based on so-called adjustable spatial differentiation, just generally by analyzing the polarization in light reflection on a single planar dielectric interface. With introducing an adjustable bias, we create a virtual light source to render the measured images with a shadow-cast effect. We further successfully recover the phase distribution of a transparent object from the virtual shadowed images. Without any dependence on resonance or material dispersion, this method directly stems from the intrinsic properties of light and can be generally extended to a board frequency range.

physics.optics

Generalized spatial differentiation from spin Hall effect of light

Optics naturally provides us with some powerful mathematical operations. Here we experimentally demonstrate that during reflection or refraction at a single optical planar interface, the optical computing of spatial differentiation can be realized by analyzing specific orthogonal polarization states of light. We show that the spatial differentiation is intrinsically due to the spin Hall effect of light and generally accompanies light reflection and refraction at any planar interface, regardless of material composition or incident angles. The proposed spin-optical method takes advantages of a simple and common structure to enable vectorial-field computation and perform edge detection for ultra-fast and energy-efficient image processing.

physics.optics