arXiv subjects

Jiho Park

Publications and source records attributed to Jiho Park.

At least 19 recordsLinked to original sources

arXiv2026

Standard-Compliant Neuromorphic Integrated Sensing and Communications Aided by an Intelligent Reflecting Surface

Neuromorphic computing enables event-driven, low-power inference and is therefore an attractive technology for jointly carrying out communication, sensing, and processing at resource-constrained wireless devices. Impulse radio ultra-wideband (IR-UWB) signaling, which is standardized in the IEEE 802.15.4 family and widely deployed for ranging and short-range communication, is naturally matched to neuromorphic processing, since both operate through sparse temporal events, or spikes. In this context, this paper studies a standard-compliant neuromorphic integrated sensing and communications (N-ISAC) system in which a single spiking neural network (SNN) receiver jointly demodulates digital data and detects a passive radar target directly from a common IEEE 802.15.4z high-rate-pulse-repetition-frequency (HRP) UWB waveform. Unlike prior N-ISAC work, which assumed a basic pulse-position-modulation interface and a simplified multipath channel, we consider the full standardized physical layer together with a realistic ray-traced channel aided by a reconfigurable intelligent surface (RIS). The model accounts for the frequency-selective response of a metamaterial-based RIS, which disperses the wideband IR-UWB pulses and can degrade both communication and sensing. Numerical experiments quantify the impact of RIS frequency selectivity on UWB ISAC and characterize the trade-off between ISAC performance and receiver computation energy.

eess.SP↗

arXiv2026

SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering

A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semantic abstraction in sketches remains challenging. Existing evaluation methods that rely on reference images, low-level visual features, or recognition accuracy do not capture abstraction, the defining property of sketches. To address these limitations, we introduce SEA (Sketch Evaluation metric for Abstraction efficiency), a reference-free metric that assesses how economically a sketch represents class-defining visual elements while preserving semantic recognizability. These elements are derived per class from commonsense knowledge about features typically depicted in sketches. SEA leverages a visual question answering model to determine the presence of each element and returns a quantitative score that reflects semantic retention under visual economy. To support this metric, we present CommonSketch, the first semantically annotated sketch dataset, comprising 23,100 human-drawn sketches across 300 classes, each paired with a caption and element-level annotations. Experiments show that SEA aligns closely with human judgments and reliably discriminates levels of abstraction efficiency, while CommonSketch serves as a benchmark providing systematic evaluation of element-level sketch understanding across various vision-language models.

cs.CV↗

arXiv2026

Projected Representation Conditioning for High-fidelity Novel View Synthesis

We propose a novel framework for diffusion-based novel view synthesis in which we leverage external representations as conditions, harnessing their geometric and semantic correspondence properties for enhanced geometric consistency in generated novel viewpoints. First, we provide a detailed analysis exploring the correspondence capabilities emergent in the spatial attention of external visual representations. Building from these insights, we propose a representation-guided novel view synthesis through dedicated representation projection modules that inject external representations into the diffusion process, a methodology named ReNoV, short for representation-guided novel view synthesis. Our experiments show that this design yields marked improvements in both reconstruction fidelity and inpainting quality, outperforming prior diffusion-based novel-view methods on standard benchmarks and enabling robust synthesis from sparse, unposed image collections.

cs.CV↗

arXiv2026

Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely on a standard Gaussian distribution, a choice inherited from diffusion models, and rarely consider the source distribution itself as an optimization target in such settings. In this work, we show that principled design of the source distribution is not only feasible but also beneficial at the scale of modern text-to-image systems. Specifically, we propose learning a condition-dependent source distribution under flow matching objective that better exploit rich conditioning signals. We identify key failure modes that arise when directly incorporating conditioning into the source, including distributional collapse and instability, and show that appropriate variance regularization and directional alignment between source and target are critical for stable and effective learning. We further analyze how the choice of target representation space impacts flow matching with structured sources, revealing regimes in which such designs are most effective. Extensive experiments across multiple text-to-image benchmarks demonstrate consistent and robust improvements, including up to a 3x faster convergence in FID, highlighting the practical benefits of a principled source distribution design for conditional flow matching.

cs.CV↗

arXiv2026

AROMMA: Unifying Olfactory Embeddings for Single Molecules and Mixtures

Public olfaction datasets are small and fragmented across single molecules and mixtures, limiting learning of generalizable odor representations. Recent works either learn single-molecule embeddings or address mixtures via similarity or pairwise label prediction, leaving representations separate and unaligned. In this work, we propose AROMMA, a framework that learns a unified embedding space for single molecules and two-molecule mixtures. Each molecule is encoded by a chemical foundation model and the mixtures are composed by an attention-based aggregator, ensuring both permutation invariance and asymmetric molecular interactions. We further align odor descriptor sets using knowledge distillation and class-aware pseudo-labeling to enrich missing mixture annotations. AROMMA achieves state-of-the-art performance in both single-molecule and molecule-pair datasets, with up to 19.1% AUROC improvement, demonstrating a robust generalization in two domains.

cs.LG↗

arXiv2025

CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models

Multi-view diffusion models have recently emerged as a powerful paradigm for novel view synthesis, yet the underlying mechanism that enables their view-consistency remains unclear. In this work, we first verify that the attention maps of these models acquire geometric correspondence throughout training, attending to the geometrically corresponding regions across reference and target views for view-consistent generation. However, this correspondence signal remains incomplete, with its accuracy degrading under large viewpoint changes. Building on these findings, we introduce CAMEO, a simple yet effective training technique that directly supervises attention maps using geometric correspondence to enhance both the training efficiency and generation quality of multi-view diffusion models. Notably, supervising a single attention layer is sufficient to guide the model toward learning precise correspondences, thereby preserving the geometry and structure of reference images, accelerating convergence, and improving novel view synthesis performance. CAMEO reduces the number of training iterations required for convergence by half while achieving superior performance at the same iteration counts. We further demonstrate that CAMEO is model-agnostic and can be applied to any multi-view diffusion model.

cs.CV↗

arXiv2025

Passive Polarization Stabilization for Robust Entanglement Distribution via Cross-Aligned Polarization Maintaining Fiber Pairs

Maintaining stable entanglement distribution through perturbed fiber links is essential for practical quantum-optics experiments, yet it remains challenging because of polarization fluctuations and phase or temporal-delay variations. We demonstrate stable entangled-photon transmission using a cross-aligned polarization-maintaining fiber (CAPMF) structure composed of two polarization-maintaining fiber sections with mutually orthogonal principal axes. The CAPMF configuration passively compensates polarization fluctuations without real-time active polarization control. We theoretically analyze the CAPMF structure and experimentally verify its stabilization performance under external mechanical perturbations. In the experiment, the single-mode fiber configuration yields an average visibility of $0.7655$ and a CHSH value of $S=1.7714$, whereas the CAPMF configuration maintains an average visibility of $0.9843$ and a CHSH value of $S=2.6838$. These results show that CAPMF offers a simple and robust architecture for stabilizing fiber-interface sections in practical entanglement-distribution systems.

quant-ph↗

arXiv2025

Operon: Incremental Construction of Ragged Data via Named Dimensions

Modern data processing workflows frequently encounter ragged data: collections with variable-length elements that arise naturally in domains like natural language processing, scientific measurements, and autonomous AI agents. Existing workflow engines lack native support for tracking the shapes and dependencies inherent to ragged data, forcing users to manage complex indexing and dependency bookkeeping manually. We present Operon, a Rust-based workflow engine that addresses these challenges through a novel formalism of named dimensions with explicit dependency relations. Operon provides a domain-specific language where users declare pipelines with dimension annotations that are statically verified for correctness, while the runtime system dynamically schedules tasks as data shapes are incrementally discovered during execution. We formalize the mathematical foundation for reasoning about partial shapes and prove that Operon's incremental construction algorithm guarantees deterministic and confluent execution in parallel settings. The system's explicit modeling of partially-known states enables robust persistence and recovery mechanisms, while its per-task multi-queue architecture achieves efficient parallelism across heterogeneous task types. Empirical evaluation demonstrates that Operon outperforms an existing workflow engine with 14.94x baseline overhead reduction while maintaining near-linear end-to-end output rates as workloads scale, making it particularly suitable for large-scale data generation pipelines in machine learning applications.

cs.PL↗

arXiv2025

StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback

Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizing pixel-based human-drawn sketches, a representative example of abstract expression. To combat these challenges, we propose StableSketcher, a novel framework that empowers diffusion models to generate hand-drawn sketches with high prompt fidelity. Within this framework, we fine-tune the variational autoencoder to optimize latent decoding, enabling it to better capture the characteristics of sketches. In parallel, we integrate a new reward function for reinforcement learning based on visual question answering, which improves text-image alignment and semantic consistency. Extensive experiments demonstrate that StableSketcher generates sketches with improved stylistic fidelity, achieving better alignment with prompts compared to the Stable Diffusion baseline. Additionally, we introduce SketchDUO, to the best of our knowledge, the first dataset comprising instance-level sketches paired with captions and question-answer pairs, thereby addressing the limitations of existing datasets that rely on image-label pairs. Our code and dataset will be made publicly available upon acceptance. Project page: https://zihos.github.io/StableSketcher

cs.CV↗

arXiv2025

TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?

Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient multilinguality, (ii) fail to capture the implicit constraints inherent in user requests, and (iii) overlook the complexities of multi-turn dialogue. To address these critical gaps and provide a more realistic assessment, we introduce TRUEBench (Trustworthy Real-world Usage Evaluation Benchmark)1, a novel benchmark specifically designed for LLM-based productivity assistants. TRUEBench distinguishes itself by featuring input prompts across 12 languages, incorporating intra-instance multilingual instructions, employing rigorous evaluation criteria to capture both explicit and implicit constraints, and including complex multi-turn dialogue scenarios with both accumulating constraints and context switches. Furthermore, to ensure reliability in evaluation, we refined constraints using an LLM validator. Extensive experiments demonstrate that TRUEBench presents significantly greater challenges than existing benchmarks; for instance, a strong model like OpenAI o1 achieved only a 69.07% overall pass rate. TRUEBench offers a demanding and realistic assessment of LLMs in practical productivity settings, highlighting their capabilities and limitations.

cs.CL↗

arXiv2025

Spacer: Towards Engineered Scientific Inspiration

Recent advances in LLMs have made automated scientific research the next frontline in the path to artificial superintelligence. However, these systems are bound either to tasks of narrow scope or the limited creative capabilities of LLMs. We propose Spacer, a scientific discovery system that develops creative and factually grounded concepts without external intervention. Spacer attempts to achieve this via 'deliberate decontextualization,' an approach that disassembles information into atomic units - keywords - and draws creativity from unexplored connections between them. Spacer consists of (i) Nuri, an inspiration engine that builds keyword sets, and (ii) the Manifesting Pipeline that refines these sets into elaborate scientific statements. Nuri extracts novel, high-potential keyword sets from a keyword graph built with 180,000 academic publications in biological fields. The Manifesting Pipeline finds links between keywords, analyzes their logical structure, validates their plausibility, and ultimately drafts original scientific concepts. According to our experiments, the evaluation metric of Nuri accurately classifies high-impact publications with an AUROC score of 0.737. Our Manifesting Pipeline also successfully reconstructs core concepts from the latest top-journal articles solely from their keyword sets. An LLM-based scoring system estimates that this reconstruction was sound for over 85% of the cases. Finally, our embedding space analysis shows that outputs from Spacer are significantly more similar to leading publications compared with those from SOTA LLMs.

cs.AI↗

arXiv2025

Multi-User Contextual Cascading Bandits for Personalized Recommendation

We introduce a Multi-User Contextual Cascading Bandit model, a new combinatorial bandit framework that captures realistic online advertising scenarios where multiple users interact with sequentially displayed items simultaneously. Unlike classical contextual bandits, MCCB integrates three key structural elements: (i) cascading feedback based on sequential arm exposure, (ii) parallel context sessions enabling selective exploration, and (iii) heterogeneous arm-level rewards. We first propose Upper Confidence Bound with Backward Planning (UCBBP), a UCB-style algorithm tailored to this setting, and prove that it achieves a regret bound of $\widetilde{O}(\sqrt{THN})$ over $T$ episodes, $H$ session steps, and $N$ contexts per episode. Motivated by the fact that many users interact with the system simultaneously, we introduce a second algorithm, termed Active Upper Confidence Bound with Backward Planning (AUCBBP), which shows a strict efficiency improvement in context scaling, i.e., user scaling, with a regret bound of $\widetilde{O}(\sqrt{T+HN})$. We validate our theoretical findings via numerical experiments, demonstrating the empirical effectiveness of both algorithms under various settings.

cs.LG↗

arXiv2025

Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics

With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise seen actions on unseen objects due to the limitations in representing object shape and movement using 3D bounding boxes. Additionally, the reliance on object templates at test time limits their generalisability to unseen objects. To address these challenges, we propose to leverage superquadrics as an alternative 3D object representation to bounding boxes and demonstrate their effectiveness on both template-free object reconstruction and action recognition tasks. Moreover, as we find that pure appearance-based methods can outperform the unified methods, the potential benefits from 3D geometric information remain unclear. Therefore, we study the compositionality of actions by considering a more challenging task where the training combinations of verbs and nouns do not overlap with the testing split. We extend H2O and FPHA datasets with compositional splits and design a novel collaborative learning framework that can explicitly reason about the geometric relations between hands and the manipulated object. Through extensive quantitative and qualitative evaluations, we demonstrate significant improvements over the state-of-the-arts in (compositional) action recognition.

cs.CV↗

arXiv2024

Heterogeneous Beliefs Model of Stock Market Predictability

This paper proposes a theory of stock market predictability patterns based on a model of heterogeneous beliefs. In a discrete finite time framework, some agents receive news about an asset's fundamental value through a noisy signal. The investors are heterogeneous in that they have different beliefs about the stochastic supply. A momentum in the stock price arises from those agents who incorrectly underestimate the signal accuracy, dampening the initial price impact of the signal. A reversal in price occurs because the price reverts to the fundamental value in the long run. An extension of the model to multiple assets case predicts co-movement and lead-lag effect, in addition to cross-sectional momentum and reversal. The heterogeneous beliefs of investors about news demonstrate how the main predictability anomalies arise endogenously in a model of bounded rationality.

q-fin.PR↗

arXiv2024

Complementarity of which-path information in induced and stimulated coherences via four-wave mixing process from warm Rb atomic ensemble

We report a systematic approach for establishing a complementary relationship between the interference visibility, concurrence, and predictability in the crossing of induced and stimulated coherences of two-mode squeezed coherent states. This is achieved using a double-path interferometer involving two independent four-wave mixing (FWM) atomic samples generated via spontaneous and stimulated FWM processes from a warm atomic ensemble of 87Rb. We demonstrate that the transition from quantum to classical behavior can be characterized by the induced coherence effect, distinguishing between the two-mode squeezed vacuum and coherent states. Moreover, our experimental scheme, employing two FWM atomic ensembles with long-coherent photons, provides valuable insights into the complementarity of which-path information in induced and stimulated coherences.

quant-ph↗

arXiv2023

Violation of Bell inequality by four photon Greenberger Horne Zeilinger state with a phase from a warm atomic ensemble

A Greenberger Horne Zeilinger (GHZ) entangled state with a phase is crucial for realizing desired multipartite quantum states for practical applications. Here, we report violations of the general Bell inequality (GBI) introduced in [1] using the four photon polarization entangled phase GHZ state realized via intrinsic polarization correlation and collective two-photon coherence in the 5S1/2 5P3/2 5D5/2 transition of 87Rb atoms. The phase GHZ state can be achieved by the unitary transformation of only one local phase of the four photons. Theoretically, the GHZ state with the π/4 phase affords maximal violation of the GBI of 2sqrt(2) at the local measurement settings of the Pauli operators σ_x and σ_y. We experimentally demonstrate strong violations of the GBI of the phase-GHZ state by 47 standard deviations. In addition to the entanglement witness for the phase GHZ state, the results represent a genuine four photon entanglement of the phase GHZ state, thereby providing a novel resource for realizing photonic quantum computation, magic state distillation from entangled states, and quantum networks based on atom photon interactions.

quant-ph↗

arXiv2021

Hong-Ou-Mandel interference of two independent continuous-wave coherent photons

Interference between two completely independent photons lies at the heart of many photonic quantum information applications such as quantum repeaters, teleportation, and quantum key distribution. Here, we report the observation of Hong-Ou-Mandel (HOM) interference with two independent continuous-wave coherent light sources that are neither synchronized nor share any common reference. To prepare highly indistinguishable photons from two independent laser sources, we employ high-precision frequency-stabilization techniques using the 5S1/2(F=3)-5P1/2(F'=3) transition line of 85Rb atoms. We successfully observe a HOM interference fringe with two independent continuous-wave coherent photons originating from either the frequency-locked and frequency-modulated lasers. An interference fringe involving two-photon beating is also observed when the frequency difference between the two interfering photons is beyond the spectral bandwidth of the individual coherent photons. We carry out further experiments to verify the robustness of the source preparation regardless of the separation distance between the two independent photon sources.

quant-ph↗

arXiv2021

Four-Photon GHZ Entanglement via Collective Two-Photon Coherence in Doppler-Broadened Atoms

Bright, entangled multiphoton sources based on atom photon interactions are an essential requirement in the realization of several quantum information and quantum computation schemes based on photonic quantum systems. Here, we experimentally demonstrate a four photon polarization entangled GHZ state obtained from Doppler broadened atomic ensembles of 87Rb atoms. Owing to collective two photon coherence in the Doppler broadened cascade-type atomic system, our setup enables the generation of robust four photon GHZ states with a fidelity of 0.82 and a measured four photon average coincidence rate of 0.58 Hz. We believe that the generation of such bright and stable multiphoton GHZ states from atomic media is an important step toward realizing photonic quantum computation and practical quantum networks based on atom photon interactions.

quant-ph↗