arXiv subjects

Dohyeon Lee

Publications and source records attributed to Dohyeon Lee.

13 recordsLinked to original sources

arXiv2026

ComPose: When to Trust Hands for Object Pose Tracking

Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data or 3D templates, and remain highly vulnerable to severe occlusions by hand grasps despite the use of explicit masks. In this work, we present ComPose, a 6DoF object tracking framework designed for hand-aware object pose estimation from RGB video. Rather than treating the hand purely as an occluder, our method harmonizes hand motions as a \textit{complementary cue} for object tracking. In detail, we recover a variety of object motions over time by combining object and hand cues from foundation models within a unified tracking pipeline. Here, ComPose adaptively selects informative hand joints, combines object- and hand-derived cues for motion estimation, and refines the resulting object motion using visible geometric evidence and a learned correction. We further enforce the temporal consistency over both rotation and translation, yielding stable 3D object trajectories over time without any external smoothing. Extensive experiments show that our method is accurate, efficient, and robust under severe hand occlusion and geometric ambiguity. In addition, the resulting trajectories can also effectively transfer to downstream robot manipulation by enabling robots to reconstruct human actions from online videos.

cs.CV↗

arXiv2026

SARA: Scene-Aware Reconstruction Accelerator

We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs based on visual similarity alone, SARA introduces geometry-first pair selection by scoring reconstruction informativeness - the product of overlap and parallax - before expensive matching. A lightweight pre-matching stage uses mutual nearest neighbors and RANSAC to estimate these cues, then constructs an Information-Weighted Spanning Tree (IWST) augmented with targeted edges for loop closure, long-baseline anchors, and weak-view reinforcement. Compared to exhaustive matching, SARA reduces rotation errors by 46.5+-5.5% and translation errors by 12.5+-6.5% across modern learned detectors, while achieving at most 50x speedup through 98% pair reduction (from 30,848 to 580 pairs). This reduces matching complexity from quadratic to quasi-linear, maintaining within +-3% of baseline reconstruction metrics for 3D Gaussian Splatting and SVRaster.

cs.CV↗

arXiv2025

Chaining Event Spans for Temporal Relation Grounding

Accurately understanding temporal relations between events is a critical building block of diverse tasks, such as temporal reading comprehension (TRC) and relation extraction (TRE). For example in TRC, we need to understand the temporal semantic differences between the following two questions that are lexically near-identical: "What finished right before the decision?" or "What finished right after the decision?". To discern the two questions, existing solutions have relied on answer overlaps as a proxy label to contrast similar and dissimilar questions. However, we claim that answer overlap can lead to unreliable results, due to spurious overlaps of two dissimilar questions with coincidentally identical answers. To address the issue, we propose a novel approach that elicits proper reasoning behaviors through a module for predicting time spans of events. We introduce the Timeline Reasoning Network (TRN) operating in a two-step inductive reasoning process: In the first step model initially answers each question with semantic and syntactic information. The next step chains multiple questions on the same event to predict a timeline, which is then used to ground the answers. Results on the TORQUE and TB-dense, TRC and TRE tasks respectively, demonstrate that TRN outperforms previous methods by effectively resolving the spurious overlaps using the predicted timeline.

cs.CL↗

arXiv2025

ECoRAG: Evidentiality-guided Compression for Long Context RAG

Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer context, context compression is necessary. However, prior compression methods do not focus on filtering out non-evidential information, which limit the performance in LLM-based RAG. We thus propose Evidentiality-guided RAG, or ECoRAG framework. ECoRAG improves LLM performance by compressing retrieved documents based on evidentiality, ensuring whether answer generation is supported by the correct evidence. As an additional step, ECoRAG reflects whether the compressed content provides sufficient evidence, and if not, retrieves more until sufficient. Experiments show that ECoRAG improves LLM performance on ODQA tasks, outperforming existing compression methods. Furthermore, ECoRAG is highly cost-efficient, as it not only reduces latency but also minimizes token usage by retaining only the necessary information to generate the correct answer. Code is available at https://github.com/ldilab/ECoRAG.

cs.CL↗

arXiv2025

From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval

Chain-of-Thought (CoT) prompting enables complex reasoning in large language models (LLMs), including applications in information retrieval (IR). However, it often leads to overthinking, where models produce excessively long and semantically redundant traces with little or no benefit. We identify two key challenges in IR: redundant trajectories that revisit similar states and misguided reasoning that diverges from user intent. To address these, we propose State Machine Reasoning (SMR), a transition-based reasoning framework composed of discrete actions (Refine, Rerank, Stop) that support early stopping and fine-grained control. Experiments on the BEIR and BRIGHT benchmarks show that SMR improves retrieval performance (nDCG@10) by 3.4% while reducing token usage by 74.4%. It generalizes across LLMs and retrievers without requiring task-specific tuning, offering a practical alternative to conventional CoT reasoning. The code and details are available at https://github.com/ldilab/SMR.

cs.IR↗

arXiv2025

Improving precision of A/B experiments using trigger intensity

In industry, online randomized controlled experiment (a.k.a. A/B experiment) is a standard approach to measure the impact of a causal change. These experiments have small treatment effect to reduce the potential blast radius. As a result, these experiments often lack statistical significance due to low signal-to-noise ratio. A standard approach for improving the precision (or reducing the standard error) focuses only on the trigger observations, where the output of the treatment and the control model are different. Although evaluation with full information about trigger observations (full knowledge) improves the precision, detecting all such trigger observations is a costly affair. In this paper, we propose a sampling based evaluation method (partial knowledge) to reduce this cost. The randomness of sampling introduces bias in the estimated outcome. We theoretically analyze this bias and show that the bias is inversely proportional to the number of observations used for sampling. We also compare the proposed evaluation methods using simulation and empirical data. In simulation, bias in evaluation with partial knowledge effectively reduces to zero when a limited number of observations (<= 0.1%) are sampled for trigger estimation. In empirical setup, evaluation with partial knowledge reduces the standard error by 36.48%.

econ.EM↗

arXiv2025

A highly maneuverable flying squirrel drone with agility-improving foldable wings

Drones, like most airborne aerial vehicles, face inherent disadvantages in achieving agile flight due to their limited thrust capabilities. These physical constraints cannot be fully addressed through advancements in control algorithms alone. Drawing inspiration from the winged flying squirrel, this paper proposes a highly maneuverable drone equipped with agility-enhancing foldable wings. By leveraging collaborative control between the conventional propeller system and the foldable wings-coordinated through the Thrust-Wing Coordination Control (TWCC) framework-the controllable acceleration set is expanded, enabling the generation of abrupt vertical forces that are unachievable with traditional wingless drones. The complex aerodynamics of the foldable wings are modeled using a physics-assisted recurrent neural network (paRNN), which calibrates the angle of attack (AOA) to align with the real aerodynamic behavior of the wings. The additional air resistance generated by appropriately deploying these wings significantly improves the tracking performance of the proposed "flying squirrel" drone. The model is trained on real flight data and incorporates flat-plate aerodynamic principles. Experimental results demonstrate that the proposed flying squirrel drone achieves a 13.1% improvement in tracking performance, as measured by root mean square error (RMSE), compared to a conventional wingless drone. A demonstration video is available on YouTube: https://youtu.be/O8nrip18azY.

cs.RO↗

arXiv2025

A highly maneuverable flying squirrel drone with controllable foldable wings

Typical drones with multi rotors are generally less maneuverable due to unidirectional thrust, which may be unfavorable to agile flight in very narrow and confined spaces. This paper suggests a new bio-inspired drone that is empowered with high maneuverability in a lightweight and easy-to-carry way. The proposed flying squirrel inspired drone has controllable foldable wings to cover a wider range of flight attitudes and provide more maneuverable flight capability with stable tracking performance. The wings of a drone are fabricated with silicone membranes and sophisticatedly controlled by reinforcement learning based on human-demonstrated data. Specially, such learning based wing control serves to capture even the complex aerodynamics that are often impossible to model mathematically. It is shown through experiment that the proposed flying squirrel drone intentionally induces aerodynamic drag and hence provides the desired additional repulsive force even under saturated mechanical thrust. This work is very meaningful in demonstrating the potential of biomimicry and machine learning for realizing an animal-like agile drone.

cs.RO↗

arXiv2025

Compression benchmarking of holotomography data using the OME-Zarr storage format

Holotomography (HT) is a label-free, three-dimensional imaging technique that captures refractive index distributions of biological samples at sub-micron resolution. As modern HT systems enable high-throughput and large-scale acquisition, they produce terabyte-scale datasets that require efficient data management. This study presents a systematic benchmarking of data compression strategies for HT data stored in the OME-Zarr format, a cloud-compatible, chunked data structure suitable for scalable imaging workflows. Using representative datasets-including embryo, tissue, and birefringent tissue volumes-we evaluated combinations of preprocessing filters and 25 compression configurations across multiple compression levels. Performance was assessed in terms of compression ratio, bandwidth, and decompression speed. A throughput-based evaluation metric was introduced to simulate real-world conditions under varying network constraints, supporting optimal compressor selection based on system bandwidth. The results offer practical guidance for storage and transmission of large HT datasets and serve as a reference for implementing scalable, FAIR-aligned imaging workflows in cloud and high-performance computing environments.

physics.optics↗

arXiv2025

Advances in imaging techniques for the study of individual bacteria and their pathophysiology

Bacterial heterogeneity is pivotal for adaptation to diverse environments, posing significant challenges in microbial diagnostics and therapeutic interventions. Recent advancements in high-resolution optical microscopy have revolutionized our ability to observe and characterize individual bacteria, offering unprecedented insights into their metabolic states and behaviors at the single-cell level. This review discusses the transformative impact of various high-resolution imaging techniques, including fluorescence and label-free imaging, which have enhanced our understanding of bacterial pathophysiology. These methods provide detailed visualizations that are crucial for developing targeted treatments and improving clinical diagnostics. We highlight the integration of these imaging techniques with computational tools, which has facilitated rapid, accurate pathogen identification and real-time monitoring of bacterial responses to treatments. The ongoing development of these optical imaging technologies promises to significantly advance our understanding of microbiology and to catalyze the translation of these insights into practical healthcare solutions.

physics.bio-ph↗

arXiv2024

Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding

Recently, pre-trained language models (PLMs) have been increasingly adopted in spoken language understanding (SLU). However, automatic speech recognition (ASR) systems frequently produce inaccurate transcriptions, leading to noisy inputs for SLU models, which can significantly degrade their performance. To address this, our objective is to train SLU models to withstand ASR errors by exposing them to noises commonly observed in ASR systems, referred to as ASR-plausible noises. Speech noise injection (SNI) methods have pursued this objective by introducing ASR-plausible noises, but we argue that these methods are inherently biased towards specific ASR systems, or ASR-specific noises. In this work, we propose a novel and less biased augmentation method of introducing the noises that are plausible to any ASR system, by cutting off the non-causal effect of noises. Experimental results and analyses demonstrate the effectiveness of our proposed methods in enhancing the robustness and generalizability of SLU models against unseen ASR systems by introducing more diverse and plausible ASR noises in advance.

cs.CL↗

arXiv2024

Colorful Intersections and Tverberg Partitions

The colorful Helly theorem and Tverberg's theorem are fundamental results in discrete geometry. We prove a theorem which interpolates between the two. In particular, we show the following for any integers $d \geq m \geq 1$ and $k$ a prime power. Suppose $F_1, F_2, \dots, F_m$ are families of convex sets in $\mathbb{R}^d$, each of size $n > (\frac{d}{m}+1)(k-1)$, such that for any choice $C_i\in F_i$ we have $\bigcap_{i=1}^mC_i\neq \emptyset$. Then, one of the families $F_i$ admits a Tverberg $k$-partition. That is, one of the $F_i$ can be partitioned into $k$ nonempty parts such that the convex hulls of the parts have nonempty intersection. As a corollary, we also obtain a result concerning $r$-dimensional transversals to families of convex sets in $\mathbb{R}^d$ that satisfy the colorful Helly hypothesis, which extends the work of Karasev and Montejano.

math.CO↗

arXiv2021

Robustifying Multi-hop QA through Pseudo-Evidentiality Training

This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning chains. An existing direction is to annotate reasoning chains to train models, requiring expensive additional annotations. In contrast, we propose a new approach to learn evidentiality, deciding whether the answer prediction is supported by correct evidences, without such annotations. Instead, we compare counterfactual changes in answer confidence with and without evidence sentences, to generate "pseudo-evidentiality" annotations. We validate our proposed model on an original set and challenge set in HotpotQA, showing that our method is accurate and robust in multi-hop reasoning.

cs.CL↗