arXiv subjects

Woosung Kim

Publications and source records attributed to Woosung Kim.

9 recordsLinked to original sources

arXiv2026

Articulated Object Reconstruction from Rest-State Observation

Building interactive digital twins requires recovering both 3D geometry and the kinematic structures that govern how objects articulate. Yet existing methods for articulated object reconstruction require explicitly observable motion from multiple articulation states. We introduce a rest-state formulation that reconstructs articulated objects from a single closed configuration, an inherently ill-posed setting where geometry, semantics, and motion priors compensate for the absence of motion cues. Our framework adopts an explicit mesh as an intermediate representation for cross-model verification and fusion, reconciling noisy outputs from vision-language and segmentation models into spatially consistent part structures. To estimate joint parameters without observed motion, we use a video diffusion model to synthesize articulation hypotheses and validate them through geometric consistency. Our approach achieves accurate part decomposition and physically plausible articulation, performing competitively with motion-observing reconstruction-based, generation-based, and modular pretrained-model baselines.

cs.CV↗

arXiv2026

CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery

Inverse design is an emerging data-driven paradigm for efficiently navigating vast chemical spaces to discover new materials with targeted properties, and in the context of heterogeneous catalysis, surface generative models have recently advanced this goal by directly generating catalyst surface-adsorbate structures. However, these models typically operate at the slab level and do not provide the corresponding parent bulk structure, making it difficult to assess bulk-dependent properties such as formation energy, surface energy, crystallographic symmetry, and synthesizability. Here, we address this missing slab-to-bulk connection as a retrieval problem and introduce CatRetriever, a contrastive representation learning model that aligns slab and bulk crystal representations in a shared latent space. From a slab query, CatRetriever accurately retrieves plausible parent bulk candidates with R@1 > 91% and R@3 > 98% on both the in-distribution and holdout evaluation sets. We further extend the CatRetriever framework into an adsorption energy targeted bulk discovery pipeline that combines bulk retrieval, generative search space expansion, and adsorption energy distribution analysis. This workflow evaluates candidates by both structural compatibility with the query slab and their ability to access the target adsorption energy range across diverse surface environments. CatRetriever therefore provides a scalable route for connecting catalyst generative models with physically plausible and adsorption energy compatible bulk catalyst discovery.

cs.LG↗

arXiv2026

AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL

Optimizing nonlinear preferences in multi-objective reinforcement learning (MORL) is essential for capturing complex trade-offs like risk aversion or fairness. However, such non-linearity has historically bifurcated nonlinear MORL objectives into two distinct paradigms: Scalarized Expected Return (SER) and Expected Scalarized Return (ESR). While SER requires global-level optimization and ESR requires non-Markovian policies, leading to fragmented optimization strategies, we bridge this divide through the Aggregation-Expectation-Transformation (AET) framework. By unifying both criteria through a tripartite decomposition of scalarization, AET provides a principled foundation for general nonlinear MORL. Building on this framework, we propose AETDICE, a tractable offline RL algorithm for AET objectives. By utilizing DICE-style density-ratio estimation in an augmented state space, AETDICE enables sample-based optimization from static datasets. Our framework resolves long-standing barriers and captures respective trade-offs induced by AET framework, which existing methods fail to address.

cs.LG↗

arXiv2026

Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation

Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when training from scratch, motivating subsequent work to explain and stabilize these issues. While these efforts have provided valuable insights, the explanations remain fragmented, and the theoretical relationships remain unclear. In this work, we provide a theoretical examination of consistency models by analyzing them from a flow map-based perspective. This joint analysis clarifies how training stability and convergence behavior can give rise to degenerate solutions. Building on these insights, we revisit self-distillation as a practical remedy for certain forms of suboptimal convergence and reformulate it to avoid excessive gradient norms for stable optimization. We demonstrate that our strategy extends beyond image generation to diffusion-based policy learning, without reliance on pretrained diffusion models for initialization, illustrating its broader applicability.

cs.LG↗

arXiv2025

Semi-gradient DICE for Offline Constrained Reinforcement Learning

Stationary Distribution Correction Estimation (DICE) addresses the mismatch between the stationary distribution induced by a policy and the target distribution required for reliable off-policy evaluation (OPE) and policy optimization. DICE-based offline constrained RL particularly benefits from the flexibility of DICE, as it simultaneously maximizes return while estimating costs in offline settings. However, we have observed that recent approaches designed to enhance the offline RL performance of the DICE framework inadvertently undermine its ability to perform OPE, making them unsuitable for constrained RL scenarios. In this paper, we identify the root cause of this limitation: their reliance on a semi-gradient optimization, which solves a fundamentally different optimization problem and results in failures in cost estimation. Building on these insights, we propose a novel method to enable OPE and constrained RL through semi-gradient DICE. Our method ensures accurate cost estimation and achieves state-of-the-art performance on the offline constrained RL benchmark, DSRL.

cs.LG↗

arXiv2025

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valued returns into scalar signals. While effective for certain preferences, this approach cannot capture fairness-oriented goals such as Nash social welfare or max-min fairness, which require nonlinear and non-additive trade-offs. Although several online algorithms have been proposed for specific fairness objectives, a unified approach for optimizing nonlinear welfare criteria in the offline setting-where learning must proceed from a fixed dataset-remains unexplored. In this work, we present FairDICE, the first offline MORL framework that directly optimizes nonlinear welfare objective. FairDICE leverages distribution correction estimation to jointly account for welfare maximization and distributional regularization, enabling stable and sample-efficient learning without requiring explicit preference weights or exhaustive weight search. Across multiple offline benchmarks, FairDICE demonstrates strong fairness-aware performance compared to existing baselines.

cs.LG↗

arXiv2013

Detection and size measurement of individual hemozoin nanocrystals in aquatic environment using a whispering gallery mode resonator

We, for the first time, report the detection and the size measurement of single nanoparticles (i.e. polystyrene) in aquatic environment using mode splitting in a whispering gallery mode (WGM) optical resonator, namely a microtoroid resonator. Using this method we achieved detecting and measuring individual synthetic hemozoin nanocrystals, which are a hemoglobin degradation by-product of malarial parasites, dispersed in a solution or in air. The results of size measurement in solution and in air agree with each other and with those obtained using scanning electron microscope and dynamic light scattering. Moreover, we compare the sensing capabilities of the degenerate (single resonance) and non-degenerate (split mode, doublet) operation regimes of the WGM resonator.

physics.optics↗

arXiv2011

Detecting single viruses and nanoparticles using whispering gallery microlasers

Detection and characterization of individual nano-scale particles, virions, and pathogens are of paramount importance to human health, homeland security, diagnostic and environmental monitoring[1]. There is a strong demand for high-resolution, portable, and cost-effective systems to make label-free detection and measurement of individual nanoparticles, molecules, and viruses [2-6]. Here, we report an easily accessible, real-time and label-free detection method with single nanoparticle resolution that surpasses detection limit of existing micro- and nano-photonic devices. This is achieved by using an ultra-narrow linewidth whispering gallery microlaser, whose lasing line undergoes frequency splitting upon the binding of individual nano-objects. We demonstrate detection of polystyrene and gold nanoparticles as small as 15 nm and 10 nm in radius, respectively, and Influenza A virions by monitoring changes in self-heterodyning beat note of the split lasing modes. Experiments are performed in both air and aqueous environment. The built-in self-heterodyne interferometric method achieved in a microlaser provides a self-reference scheme with extraordinary sensitivity [7,8], and paves the way for detection and spectroscopy of nano-scale objects using micro- and nano-lasers.

physics.optics↗

arXiv2010

Demonstration of mode splitting in an optical microcavity in aqueous environment

Scatterer induced modal coupling and the consequent mode splitting in a whispering gallery mode resonator is demonstrated in aqueous environment. The rate of change in splitting as particles enter the resonator mode volume strongly depends on the concentration of particle solution: The higher is the concentration, the higher is the rate of change. Polystyrene nanoparticles of radius 50nm with concentration as low as 5x10^(-6)wt% have been detected using the mode splitting spectra. Observation of mode splitting in water paves the way for constructing advanced resonator based sensors for measuring nanoparticles and biomolecules in various environments.

physics.optics↗