arXiv subjects

Taehoon Kim

Publications and source records attributed to Taehoon Kim.

At least 19 recordsLinked to original sources

arXiv2026

Bridging CLIP with DINO: Cross-Modal Information Maximization for Online Test-Time Adaptation

Vision-language models such as CLIP enable zero-shot classification from arbitrary class names, but under test-time corruptions, their visual encoder projects distorted features onto incorrect textual anchors with high confidence: a phenomenon we term modality bias. Standard entropy minimization reinforces these overconfident errors, which creates a confirmation-bias loop and collapses the predicted label distribution. We propose an online test-time adaptation (TTA) method that breaks this loop at three levels. At the representation level, a frozen self-supervised backbone (e.g., DINO v2) is combined with CLIP through a cross-covariance logit ensemble. CLIP text prototypes are projected into the feature space of this text-free backbone, so the self-supervised branch classifies native image features and is less affected by the text bias of CLIP. At the optimization level, a gated test-time information-maximization objective pairs per-sample sharpening with batch-level diversity, while an adaptive gate excludes unreliable samples from the gradient. At the prediction level, an online logit adjustment corrects the residual class-distribution skew. CDIM outperforms the compared CLIP-based online TTA baselines on ImageNet-C, CIFAR10-C, and CIFAR100-C, and remains competitive in continual and mixed-domain TTA. Extensive analyses and ablation studies verify the contribution of each of its components. Our code is available at https://github.com/B1ueC1oud/CDIM

cs.CV↗

arXiv2026

PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI

Generative AI models now produce images indistinguishable from real data, making publicly verifiable provenance essential; however, existing watermarking methods become vulnerable to forgeries and adversarial optimization attacks once their detectors are made public. We propose PP-Mark, a provenance framework that anchors lightweight statistical detection to a zero-knowledge proof of the embedding process, ensuring that forged content cannot pass full verification by construction. We establish formal unforgeability under standard cryptographic assumptions and validate PP-Mark against representative baselines across two latent-diffusion models (SD2.1 and SDXL), demonstrating resistance to black-box imprint forgery, white-box optimization, and regeneration attacks while remaining practical for decentralized verification. Code is available at https://github.com/hko920920/PP-Mark_NeurIPS2026

cs.CR↗

arXiv2026

Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation

Reasoning capabilities are critical for advancing Large Language Models, yet current approaches either require massive computational budgets or struggle to effectively distill reasoning to smaller models. Standard distillation methods rely on outcome-based rewards, failing to distinguish between sound reasoning and lucky guesses. We propose Collaborative Reasoning Distillation (CRD), a framework that enhances reasoning in compact models through three innovations: (1) interactive cross-feedback where teachers iteratively critique each other's reasoning, (2) fine-grained step-wise quality assessment capturing logical validity independent of final answers, and (3) coherence-aware step stitching that synthesizes complementary strengths. Students are trained via Reasoning Quality Optimization (RQO) with budget constraints. Our model, CRD-4B, achieves 97.3% on MATH-500 and 70.3% on AIME'25, surpassing baselines while using only 50K training examples, up to 12 times smaller than the datasets of comparable models.

cs.LG↗

arXiv2026

Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing

While Vision-Language Models (VLMs) excel at visual reasoning, generating structured, editable Scalable Vector Graphics (SVG) remains a fundamental challenge. Existing pipelines predominantly yield flat, semantically agnostic collections of paths, where editing a single object requires manually identifying its constituent paths. To address this, we propose a VLM-driven agentic framework for semantic compositional SVG generation. Our pipeline recursively parses visual scenes into semantic and geometric hierarchies via top-down decomposition, visual grounding, and prompt-driven amodal occlusion recovery, ensuring each component is geometrically complete. Furthermore, we introduce the Semantic SVG Benchmark with human-annotated semantic groups and novel sub-component metrics (Semantic Recall/Precision, PERE) to explicitly evaluate structural compositionality and functional editability. Experiments show that our natively predicted structures surpass the upper bounds of existing flat-generation methods in both grouping quality and editability, while maintaining state-of-the-art visual fidelity.

cs.CV↗

arXiv2026

Deterministic patterning and alignment of tellurium quantum wires using nanoscale templates

Tellurium (Te) is an intriguing one-dimensional (1D) semiconductor that has recently attracted considerable interest as a p-type channel material. However, scalable synthesis methods have lacked control over the orientation and patterning of the Te atomic chains, thus limiting its practical use. Guided by theory, we overcome this challenge using nanowire-shaped templates to achieve oriented, single-crystal growth of Te on amorphous substrates. Strong alignment of Te atomic chains is achieved as template widths are reduced to sub-20 nm. This high structural order, confirmed by 4D scanning transmission electron microscopy, enables the observation of pristine quantum transport phenomena for deterministically patterned Te. Field-effect transistors exhibit well-defined conductance plateaus at 77 K due to population of individual 1D subbands. Furthermore, Coulomb blockade emerges at 1.7 K, with the Te channel acting as a gate-tunable quantum dot. This synthesis approach provides a scalable pathway for integration of Te-based quantum materials for future electronic and quantum technologies.

cond-mat.mtrl-sci↗

arXiv2026

Preserving Knowledge across Space and Time for Continual Video Deepfake Detection

The continuous emergence of high-quality video deepfakes requires detectors that continually adapt to new forgery patterns, yet existing approaches, which are designed for deepfake images, fail to capture video-specific cues. Unlike deepfake images that contain only spatial artifacts, deepfake videos leave distinct evidence along both spatial and temporal axes, necessitating the separate preservation of each modality during sequential model updates. To overcome this limitation, we introduce a continual deepfake video detection framework, Modality-Specific Frequency Distillation (MSFD), that explicitly decomposes video features into spatial, temporal, and spatiotemporal modalities in the frequency domain. This decomposition enables independent preservation of each modality, as different deepfake video types exhibit varying reliance on spatial and temporal cues across tasks. Furthermore, MSFD adopts a cross-modality decorrelation loss that encourages spatiotemporal representations to remain orthogonal to single-modality cues. Extensive experiments show that our framework achieves stronger adaptation and preserves performance more effectively than state-of-the-art methods across diverse continual deepfake video scenarios.

cs.CV↗

arXiv2026

Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning

Certifying the IID generalisation ability of deep networks is the first of many requirements for trusting AI in high-stakes applications from medicine to security. However, when instantiating generalisation bounds for deep networks it remains challenging to obtain non-vacuous guarantees, especially when applying contemporary large models on the small scale data prevalent in such high-stakes fields. In this paper, we draw a novel connection between a family of learning methods based on model fusion and generalisation certificates, and surprisingly show that with minor adjustment several existing learning strategies already provide non-trivial generalisation guarantees. Essentially, by focusing on data-driven learning of downstream tasks by fusion rather than fine-tuning, the certified generalisation gap becomes tiny and independent of the base network size, facilitating its certification. Our results show for the first time non-trivial generalisation guarantees for learning with as low as 100 examples, while using vision models such as VIT-B and language models such as mistral-7B. This observation is significant as it has immediate implications for facilitating the certification of existing systems as trustworthy, and opens up new directions for research at the intersection of practice and theory.

cs.LG↗

arXiv2026

Biodegradable, Millimeter-Scale Light-Emitting Sensors for Distributed Environmental Monitoring-Functional Pixie Dust

Methods for large-area, precise monitoring across natural environments are of growing interest due to pressing needs for sustainable management of rapidly increasing anthropogenic activities. Established approaches involve sparse spatial sampling and/or sequential measurements, while emerging techniques exploit miniaturized electronics or passive optical methods. Various constraints in scalability, costs, robustness, operational range and other factors create a need for alternatives. Here, we introduce a concept that overcomes many of these limitations through the combined use of chemically induced light emission and chemically responsive optical filter elements in millimeter-scale systems that we refer to as functional pixie dust (fPD) sensors, designed specifically for monitoring natural water systems during nighttime to eliminate background optical interference and to enhance remote analysis. These floating devices act as Lagrangian tracers to follow surface flows and to simultaneously measure the concentrations of key chemical species along their trajectories. Optimized designs exploit environmentally compatible constituent materials that are also degradable through natural processes to benign end products, thereby eliminating the need for recovery. Spatially and spectrally resolved ratiometric measurement schemes ensure robust operation and ability to address practical requirements in range, operational lifetime, time response and sensitivity. Demonstrations include distributed measurements of pH, Hg2+, and NO2-, each of relevance to industrial discharge, toxic metal contamination, and nitrogen-rich runoff, adapted for static concentration gradients, flow-driven transport conditions, and outdoor aquatic settings. The results establish a framework for environmental sensing using degradable, self-powered microsystems capable of scalable deployment and remote readout.

physics.app-ph↗

arXiv2026

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment (Null-TTA), which aligns diffusion models by optimising the unconditional embedding in classifier-free guidance, rather than manipulating latent or noise variables. Due to the structured semantic nature of the text embedding space, this ensures alignment occurs on a semantically coherent manifold and prevents reward hacking (exploiting non-semantic noise patterns to improve the reward). Since the unconditional embedding in classifier-free guidance serves as the anchor for the model's generative distribution, Null-TTA directly steers model's generative distribution towards the target reward rather than just adjusting the samples, even without updating model parameters. Thanks to these desirable properties, we show that Null-TTA achieves state-of-the-art target test-time alignment while maintaining strong cross-reward generalisation. This establishes semantic-space optimisation as an effective and principled novel paradigm for TTA.

cs.CV↗

arXiv2026

Feasibility Determination for Subjective Probability Constraints

We consider the problem of determining feasible systems from a finite set of simulated alternatives with respect to probability constraints, where the observations from stochastic simulations are Bernoulli distributed. Most statistically valid procedures for feasibility determination focus on constraints on the means of normally distributed observations. Although these procedures can be adapted to Bernoulli-distributed data by treating batch means as basic observations, achieving approximate normality often requires a large batch size, potentially leading to the unnecessary waste of observations in reaching a decision. This paper proposes a procedure that utilizes the Bernoulli-distributed observations directly to determine feasibility. In addition, we incorporate subjective constraints, allowing for multiple thresholds for each constraint. We demonstrate that our proposed procedure is statistically valid and that it outperforms an existing feasibility determination procedure for subjective constraints originally developed for normally distributed observations. Furthermore, we propose two heuristic feasibility check approaches for thresholds that are sequentially added by decision makers, allowing thresholds to be tightened when many systems are feasible or relaxed when no feasible system exists. We show by experiments that the proposed procedures can efficiently provide feasibility decisions to systems with respect to all thresholds considered.

math.OC↗

arXiv2026

Terahertz magneto-nanoscopy of encapsulated monolayer graphene

This study investigates the nanoscale conductivity of encapsulated monolayer graphene at temperatures down to 5 K and magnetic fields of up to 1 T. We use the scattering-type scanning near-field optical microscopy (s-SNOM) technique to probe magnetic-field-dependent responses from graphene close to charge neutrality in the terahertz spectral region. We observe the near-perfect high-$q$ reflector behavior of graphene but with subtle changes by the presence of magnetic fields. Measurements align with calculations of the magneto-optical conductivity and the near-field spectroscopic contrast that describes the field-tunable cyclotron resonance of Dirac fermions. Our result provides an initial step toward understanding temperature and magnetic-field effects on nanoscale terahertz transport in two-dimensional quantum materials.

cond-mat.mes-hall↗

arXiv2025

Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning

We present a novel training approach, named Merge-and-Bound (M&B) for Class Incremental Learning (CIL), which directly manipulates model weights in the parameter space for optimization. Our algorithm involves two types of weight merging: inter-task weight merging and intra-task weight merging. Inter-task weight merging unifies previous models by averaging the weights of models from all previous stages. On the other hand, intra-task weight merging facilitates the learning of current task by combining the model parameters within current stage. For reliable weight merging, we also propose a bounded update technique that aims to optimize the target model with minimal cumulative updates and preserve knowledge from previous tasks; this strategy reveals that it is possible to effectively obtain new models near old ones, reducing catastrophic forgetting. M&B is seamlessly integrated into existing CIL methods without modifying architecture components or revising learning objectives. We extensively evaluate our algorithm on standard CIL benchmarks and demonstrate superior performance compared to state-of-the-art methods.

cs.CV↗

arXiv2025

Machine Learning-Based Detection of Pump-and-Dump Schemes in Real-Time

Cryptocurrency markets often face manipulation through prevalent pump-and-dump (P&D) schemes, where self-organized Telegram groups, some exceeding two million members, artificially inflate target cryptocurrency prices. These groups sell premium access to inside information, worsening information asymmetry and financial risks for subscribers and all investors. This paper presents a real-time prediction pipeline to forecast target coins and alert investors to possible P&D schemes. In a Poloniex case study, the model accurately identified the target coin among the top five from 50 random coins in 24 out of 43 (55.81%) P&D events. The pipeline uses advanced natural language processing (NLP) to classify Telegram messages, identifying 2,079 past pump events and detecting new ones in real-time.

cs.CE↗

arXiv2025

Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented Generation

Understanding complex multimodal documents remains challenging due to their structural inconsistencies and limited training data availability. We introduce \textit{DocsRay}, a training-free document understanding system that integrates pseudo Table of Contents (TOC) generation with hierarchical Retrieval-Augmented Generation (RAG). Our approach leverages multimodal Large Language Models' (LLMs) native capabilities to seamlessly process documents containing diverse elements such as text, images, charts, and tables without requiring specialized models or additional training. DocsRay's framework synergistically combines three key techniques: (1) a semantic structuring module using prompt-based LLM interactions to generate a hierarchical pseudo-TOC, (2) zero-shot multimodal analysis that converts diverse document elements into unified, text-centric representations using the inherent capabilities of multimodal LLMs, and (3) an efficient two-stage hierarchical retrieval system that reduces retrieval complexity from $O(N)$ to $O(S + k_1 \cdot N_s)$. Evaluated on documents averaging 49.4 pages and 20,971 textual tokens, DocsRay reduced query latency from 3.89 to 2.12 seconds, achieving a 45% efficiency improvement. On the MMLongBench-Doc benchmark, DocsRay-Pro attains an accuracy of 64.7%, substantially surpassing previous state-of-the-art results.

cs.LG↗

arXiv2025

Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection

We introduce a deepfake video detection approach that exploits pixel-wise temporal inconsistencies, which traditional spatial frequency-based detectors often overlook. Traditional detectors represent temporal information merely by stacking spatial frequency spectra across frames, resulting in the failure to detect temporal artifacts in the pixel plane. Our approach performs a 1D Fourier transform on the time axis for each pixel, extracting features highly sensitive to temporal inconsistencies, especially in areas prone to unnatural movements. To precisely locate regions containing the temporal artifacts, we introduce an attention proposal module trained in an end-to-end manner. Additionally, our joint transformer module effectively integrates pixel-wise temporal frequency features with spatio-temporal context features, expanding the range of detectable forgery artifacts. Our framework represents a significant advancement in deepfake video detection, providing robust performance across diverse and challenging detection scenarios.

cs.CV↗

arXiv2025

Future-Proof Yourself: An AI Era Survival Guide

Future-Proof Yourself is a practical guide that helps readers navigate the fast-changing world of artificial intelligence in everyday life. The book begins by explaining how computers learn from data in simple, relatable terms, and gradually introduces the methods used in modern AI. It shows how basic ideas in machine learning evolve into advanced systems that can recognize images, understand language, and even make decisions. The guide also reviews the history of AI and highlights the major breakthroughs that have shaped its growth. Looking ahead, the book explores emerging trends such as the integration of AI with digital twins, wearable devices, and virtual environments. Designed for a general audience, the text avoids heavy technical jargon and presents complex ideas in clear, straightforward language so that anyone can gain a solid understanding of the technology that is set to transform our future.

cs.LG↗

arXiv2025

Advancing ALS Applications with Large-Scale Pre-training: Dataset Development and Downstream Assessment

The pre-training and fine-tuning paradigm has revolutionized satellite remote sensing applications. However, this approach remains largely underexplored for airborne laser scanning (ALS), an important technology for applications such as forest management and urban planning. In this study, we address this gap by constructing a large-scale ALS point cloud dataset and evaluating its impact on downstream applications. Our dataset comprises ALS point clouds collected across the contiguous United States, provided by the United States Geological Survey's 3D Elevation Program. To ensure efficient data collection while capturing diverse land cover and terrain types, we introduce a geospatial sampling method that selects point cloud tiles based on land cover maps and digital elevation models. As a baseline self-supervised learning model, we adopt BEV-MAE, a state-of-the-art masked autoencoder for 3D outdoor point clouds, and pre-train it on the constructed dataset. The pre-trained models are subsequently fine-tuned for downstream tasks, including tree species classification, terrain scene recognition, and point cloud semantic segmentation. Our results show that the pre-trained models significantly outperform their scratch counterparts across all downstream tasks, demonstrating the transferability of the representations learned from the proposed dataset. Furthermore, we observe that scaling the dataset using our geospatial sampling method consistently enhances performance, whereas pre-training on datasets constructed with random sampling fails to achieve similar improvements. These findings highlight the utility of the constructed dataset and the effectiveness of our sampling strategy in the pre-training and fine-tuning paradigm. The source code and pre-trained models will be made publicly available at \url{https://github.com/martianxiu/ALS_pretraining}.

cs.CV↗

arXiv2024

Exploiting Style Latent Flows for Generalizing Deepfake Video Detection

This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos. We discovered that the generated facial videos suffer from the temporal distinctiveness in the temporal changes of style latent vectors, which are inevitable during the generation of temporally stable videos with various facial expressions and geometric transformations. Our framework utilizes the StyleGRU module, trained by contrastive learning, to represent the dynamic properties of style latent vectors. Additionally, we introduce a style attention module that integrates StyleGRU-generated features with content-based features, enabling the detection of visual and temporal artifacts. We demonstrate our approach across various benchmark scenarios in deepfake detection, showing its superiority in cross-dataset and cross-manipulation scenarios. Through further analysis, we also validate the importance of using temporal changes of style latent vectors to improve the generality of deepfake video detection.

cs.CV↗