Showing 1–50 of 168 results for author: Jung, M

Geometrically-Constrained Radar-Inertial Odometry via Continuous Point-Pose Uncertainty Modeling

Authors: Wooseong Yang, Dongjae Lee, Minwoo Jung, Ayoung Kim

Abstract: Radar odometry is crucial for robust localization in challenging environments; however, the sparsity of reliable returns and distinctive noise characteristics impede its performance. This paper introduces geometrically-constrained radar-inertial odometry and mapping that jointly consolidates point and pose uncertainty. We employ the continuous trajectory model to estimate the pose uncertainty at a… ▽ More Radar odometry is crucial for robust localization in challenging environments; however, the sparsity of reliable returns and distinctive noise characteristics impede its performance. This paper introduces geometrically-constrained radar-inertial odometry and mapping that jointly consolidates point and pose uncertainty. We employ the continuous trajectory model to estimate the pose uncertainty at any arbitrary timestamp by propagating uncertainties of the control points. These pose uncertainties are continuously integrated with heteroscedastic measurement uncertainty during point projection, thereby enabling dynamic evaluation of observation confidence and adaptive down-weighting of uninformative radar points. By leveraging quantified uncertainties in radar mapping, we construct a high-fidelity map that improves odometry accuracy under imprecise radar measurements. Moreover, we reveal the effectiveness of explicit geometrical constraints in radar-inertial odometry when incorporated with the proposed uncertainty-aware mapping framework. Extensive experiments on diverse real-world datasets demonstrate the superiority of our method, yielding substantial performance improvements in both accuracy and efficiency compared to existing baselines. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: 8 pages, 8 figures, 6 tables, accepted to RA-L

Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMs

Authors: Jaehoon Lee, Mingi Jung, Soohyuk Jang, Seungryong Yoo, Dahuin Jung, Sungroh Yoon

Abstract: Large Vision-Language Models (VLMs) achieve strong multimodal understanding capabilities by leveraging high-resolution visual inputs, but the resulting large number of visual tokens creates a major computational bottleneck. Recent work mitigates this issue through visual token compression, typically compressing tokens based on saliency, diversity, or a fixed combination of both. We observe that th… ▽ More Large Vision-Language Models (VLMs) achieve strong multimodal understanding capabilities by leveraging high-resolution visual inputs, but the resulting large number of visual tokens creates a major computational bottleneck. Recent work mitigates this issue through visual token compression, typically compressing tokens based on saliency, diversity, or a fixed combination of both. We observe that the distribution of semantic prominence varies substantially across samples, leading to different optimal trade-offs between local saliency preservation and global coverage. This observation suggests that applying a static compression strategy across all samples can be suboptimal. Motivated by this insight, we propose PromPrune, a sample-adaptive visual token selection framework composed of semantic prominence-aware budget allocation and a two-stage selection pipeline. Our method adaptively balances local saliency preservation and global coverage according to the semantic prominence distribution of each sample. By allocating token budgets between locally salient regions and globally diverse regions, our method maintains strong performance even under high compression ratios. On LLaVA-NeXT-7B, our approach reduces FLOPs by 88% and prefill latency by 22% while preserving 97.5% of the original accuracy. △ Less

Submitted 16 March, 2026; originally announced March 2026.

Measuring Perceptions of Fairness in AI Systems: The Effects of Infra-marginality

Authors: Schrasing Tong, Minseok Jung, Ilaria Liccardi, Lalana Kagal

Abstract: Differences in data distributions between demographic groups, known as the problem of infra-marginality, complicate how people evaluate fairness in machine learning models. We present a user study with 85 participants in a hypothetical medical decision-making scenario to examine two treatments: group-specific model performance and training data availability. Our results show that participants did… ▽ More Differences in data distributions between demographic groups, known as the problem of infra-marginality, complicate how people evaluate fairness in machine learning models. We present a user study with 85 participants in a hypothetical medical decision-making scenario to examine two treatments: group-specific model performance and training data availability. Our results show that participants did not equate fairness with simple statistical parity. When group-specific performances were equal or unavailable, participants preferred models that produced equal outcomes; when performances differed, especially in ways consistent with data imbalances, they judged models that preserved those differences as more fair. These findings highlight that fairness judgments are shaped not only by outcomes, but also by beliefs about the causes of disparities. We discuss implications for popular group fairness definitions and system design, arguing that accounting for distributional context is critical to aligning algorithmic fairness metrics with human expectations in real-world applications. △ Less

Submitted 5 March, 2026; originally announced March 2026.

TreeLoc++: Robust 6-DoF LiDAR Localization in Forests with a Compact Digital Forest Inventory

Authors: Minwoo Jung, Dongjae Lee, Nived Chebrolu, Haedam Oh, Maurice Fallon, Ayoung Kim

Abstract: Reliable localization is essential for sustainable forest management, as it allows robots or sensor systems to revisit and monitor the status of individual trees over long periods. In modern forestry, this management is structured around Digital Forest Inventories (DFIs), which encode stems using compact geometric attributes rather than raw data. Despite their central role, DFIs have been overlook… ▽ More Reliable localization is essential for sustainable forest management, as it allows robots or sensor systems to revisit and monitor the status of individual trees over long periods. In modern forestry, this management is structured around Digital Forest Inventories (DFIs), which encode stems using compact geometric attributes rather than raw data. Despite their central role, DFIs have been overlooked in localization research, and most methods still rely on dense gigabyte-sized point clouds that are costly to store and maintain. To improve upon this, we propose TreeLoc++, a global localization framework that operates directly on DFIs as a discriminative representation, eliminating the need to use the raw point clouds. TreeLoc++ reduces false matches in structurally ambiguous forests and improves the reliability of full 6-DoF pose estimation. It augments coarse retrieval with a pairwise distance histogram that encodes local tree-layout context, subsequently refining candidates via DBH-based filtering and yaw-consistent inlier selection to further reduce mismatches. Furthermore, a constrained optimization leveraging tree geometry jointly estimates roll, pitch, and height, enhancing pose stability and enabling accurate localization without reliance on dense 3D point cloud data. Evaluations on 27 sequences recorded in forests across three datasets and four countries show that TreeLoc++ achieves precise localization with centimeter-level accuracy. We further demonstrate robustness to long-term change by localizing data recorded in 2025 against inventories built from 2023 data, spanning a two-year interval. The system represents 15 sessions spanning 7.98 km of trajectories using only 250KB of map data and outperforms both hand-crafted and learning-based baselines that rely on point cloud maps. This demonstrates the scalability of TreeLoc++ for long-term deployment. △ Less

Submitted 3 March, 2026; originally announced March 2026.

Comments: 25 pages, 27 figures and 15 tables

Mirroring the Mind: Distilling Human-Like Metacognitive Strategies into Large Language Models

Authors: Ik-hwan Kim, Hyeongrok Han, Mingi Jung, Sangwon Yu, Jinseok Hong, Sang Hun Kim, Yoonyoung Choi, Sungroh Yoon

Abstract: Large Reasoning Models (LRMs) often exhibit structural fragility in complex reasoning tasks, failing to produce correct answers even after successfully deriving valid intermediate steps. Through systematic analysis, we observe that these failures frequently stem not from a lack of reasoning capacity, but from a deficiency in self-regulatory control, where valid logic is destabilized by uncontrolle… ▽ More Large Reasoning Models (LRMs) often exhibit structural fragility in complex reasoning tasks, failing to produce correct answers even after successfully deriving valid intermediate steps. Through systematic analysis, we observe that these failures frequently stem not from a lack of reasoning capacity, but from a deficiency in self-regulatory control, where valid logic is destabilized by uncontrolled exploration or the failure to recognize logical sufficiency. Motivated by this observation, we propose Metacognitive Behavioral Tuning (MBT), a post-training framework that explicitly injects metacognitive behaviors into the model's thought process. MBT implements this via two complementary formulations: (1) MBT-S, which synthesizes rigorous reasoning traces from scratch, and (2) MBT-R, which rewrites the student's initial traces to stabilize intrinsic exploration patterns. Experiments across multi-hop QA benchmarks demonstrate that MBT consistently outperforms baselines, achieving notable gains on challenging benchmarks. By effectively eliminating reasoning collapse, MBT achieves higher accuracy with significantly reduced token consumption, demonstrating that internalizing metacognitive strategies leads to more stable and robust reasoning. △ Less

Submitted 25 February, 2026; originally announced February 2026.

Comments: 31 pages

Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning

Authors: Daehoon Gwak, Minseo Jung, Junwoo Park, Minho Park, ChaeHun Park, Junha Hyung, Jaegul Choo

Abstract: Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying mechanism behind these gains remains unclear, making it hard to decide when and how to apply the technique effectively. In this work, we argue that the key benefit… ▽ More Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying mechanism behind these gains remains unclear, making it hard to decide when and how to apply the technique effectively. In this work, we argue that the key benefit arises not from the generated examples themselves but from the act of creating them. To validate this, on reasoning-intensive tasks across diverse LLM architectures, we systematically evaluate three prompting strategies for in-context learning: (1) Zero-shot prompting; (2) Integrated prompting, where LLMs create and solve problems within a single, unified prompt; and (3) Decoupled prompting, where self-generated examples are reused as in-context examples, but the context of their creation itself is excluded. We conduct experiments across five widely used model architectures, demonstrating that Integrated prompting consistently outperforms both Zero-shot and Decoupled prompting. In contrast, Decoupled prompting offers only marginal gains over Zero-shot. Further, for a more in-depth analysis, we conduct an attention analysis and observe significant differences in attention patterns between Integrated and Decoupled prompting. These findings suggest that the advantage of self-generation prompting comes from the process of problem creation, not the examples themselves, providing valuable insights for designing more effective prompting strategies. △ Less

Submitted 26 January, 2026; originally announced February 2026.

Comments: Presented at AACL-IJCNLP 2025

DRAMPyML: A Formal Description of DRAM Protocols with Timed Petri Nets

Authors: Derek Christ, Thomas Zimmermann, Philippe Barbie, Dmitri Saberi, Yao Yin, Matthias Jung

Abstract: The JEDEC committee defines various domain-specific DRAM standards. These standards feature increasingly complex and evolving protocol specifications, which are detailed in timing diagrams and command tables. Understanding these protocols is becoming progressively challenging as new features and complex device hierarchies are difficult to comprehend without an expressive model. While each JEDEC st… ▽ More The JEDEC committee defines various domain-specific DRAM standards. These standards feature increasingly complex and evolving protocol specifications, which are detailed in timing diagrams and command tables. Understanding these protocols is becoming progressively challenging as new features and complex device hierarchies are difficult to comprehend without an expressive model. While each JEDEC standard features a simplified state machine, this state machine fails to reflect the parallel operation of memory banks. In this paper, we present an evolved modeling approach based on timed Petri nets and Python. This model provides a more accurate representation of DRAM protocols, making them easier to understand and directly executable, which enables the evaluation of interesting metrics and the verification of controller RTL models, DRAM logic and memory simulators. △ Less

Submitted 11 February, 2026; originally announced February 2026.

SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments

Authors: Keonyoung Koh, Moonkyeong Jung, Samuel Seungsup Lee, Daehyung Park

Abstract: We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that avoids all hard constraint regions while minimally traversing the least risky areas. Conventional methods often rely on pre-defined area costs, limiting generalizations. Further, the spatial continuity of navigation spaces makes it difficult to identify region… ▽ More We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that avoids all hard constraint regions while minimally traversing the least risky areas. Conventional methods often rely on pre-defined area costs, limiting generalizations. Further, the spatial continuity of navigation spaces makes it difficult to identify regions that are passable without overestimation. To overcome these challenges, we propose SuReNav, a superpixel graph-based constraint relaxation and navigation method that imitates human-like safe and efficient navigation. Our framework consists of three components: 1) superpixel graph map generation with regional constraints, 2) regional-constraint relaxation using graph neural network trained on human demonstrations for safe and efficient navigation, and 3) interleaving relaxation, planning, and execution for complete navigation. We evaluate our method against state-of-the-art baselines on 2D semantic maps and 3D maps from OpenStreetMap, achieving the highest human-likeness score of complete navigation while maintaining a balanced trade-off between efficiency and safety. We finally demonstrate its scalability and generalization performance in real-world urban navigation with a quadruped robot, Spot. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Comments: Accepted by ICRA 2026. Code and videos are available at https://sure-nav.github.io/

Understanding How Accessibility Practices Impact Teamwork in Mixed-Ability Teams that Collaborate Virtually

Authors: Crescentia Jung, Kexin Cheng, Sharon Heung, Malte F. Jung, Shiri Azenkot

Abstract: Virtual collaboration has transformed how people in mixed-ability teams, composed of disabled and non-disabled people, work together by offering greater flexibility. In these settings, accessibility practices, such as accommodations and inclusive norms, are essential for providing access to disabled people. However, we do not yet know how these practices shape broader facets of teamwork, such as p… ▽ More Virtual collaboration has transformed how people in mixed-ability teams, composed of disabled and non-disabled people, work together by offering greater flexibility. In these settings, accessibility practices, such as accommodations and inclusive norms, are essential for providing access to disabled people. However, we do not yet know how these practices shape broader facets of teamwork, such as productivity, participation, and camaraderie. To address this gap, we interviewed 18 participants (12 disabled, 6 non-disabled) who are part of mixed-ability teams. We found that beyond providing access, accessibility practices shaped how all participants coordinated tasks, sustained rapport, and negotiated responsibilities. Accessibility practices also introduced camaraderie challenges, such as balancing empathy and accountability. Non-disabled participants described allyship as a learning process and skill shaped by their disabled team members and team culture. Based on our findings, we present recommendations for team practices and design opportunities for virtual collaboration tools that reframe accessibility practices as a foundation for strong teamwork. △ Less

Submitted 3 February, 2026; originally announced February 2026.

TreeLoc: 6-DoF LiDAR Global Localization in Forests via Inter-Tree Geometric Matching

Authors: Minwoo Jung, Nived Chebrolu, Lucas Carvalho de Lima, Haedam Oh, Maurice Fallon, Ayoung Kim

Abstract: Reliable localization is crucial for navigation in forests, where GPS is often degraded and LiDAR measurements are repetitive, occluded, and structurally complex. These conditions weaken the assumptions of traditional urban-centric localization methods, which assume that consistent features arise from unique structural patterns, necessitating forest-centric solutions to achieve robustness in these… ▽ More Reliable localization is crucial for navigation in forests, where GPS is often degraded and LiDAR measurements are repetitive, occluded, and structurally complex. These conditions weaken the assumptions of traditional urban-centric localization methods, which assume that consistent features arise from unique structural patterns, necessitating forest-centric solutions to achieve robustness in these environments. To address these challenges, we propose TreeLoc, a LiDAR-based global localization framework for forests that handles place recognition and 6-DoF pose estimation. We represent scenes using tree stems and their Diameter at Breast Height (DBH), which are aligned to a common reference frame via their axes and summarized using the tree distribution histogram (TDH) for coarse matching, followed by fine matching with a 2D triangle descriptor. Finally, pose estimation is achieved through a two-step geometric verification. On diverse forest benchmarks, TreeLoc outperforms baselines, achieving precise localization. Ablation studies validate the contribution of each component. We also propose applications for long-term forest management using descriptors from a compact global tree database. TreeLoc is open-sourced for the robotics community at https://github.com/minwoo0611/TreeLoc. △ Less

Submitted 12 February, 2026; v1 submitted 1 February, 2026; originally announced February 2026.

Comments: An 8-page paper with 7 tables and 8 figures, accepted to ICRA 2026

AutoGNN: End-to-End Hardware-Driven Graph Preprocessing for Enhanced GNN Performance

Authors: Seungkwan Kang, Seungjun Lee, Donghyun Gouk, Miryeong Kwon, Hyunkyu Choi, Junhyeok Jang, Sangwon Lee, Huiwon Choi, Jie Zhang, Wonil Choi, Mahmut Taylan Kandemir, Myoungsoo Jung

Abstract: Graph neural network (GNN) inference faces significant bottlenecks in preprocessing, which often dominate overall inference latency. We introduce AutoGNN, an FPGA-based accelerator designed to address these challenges by leveraging FPGA's reconfigurability and specialized components. AutoGNN adapts to diverse graph inputs, efficiently performing computationally intensive tasks such as graph conver… ▽ More Graph neural network (GNN) inference faces significant bottlenecks in preprocessing, which often dominate overall inference latency. We introduce AutoGNN, an FPGA-based accelerator designed to address these challenges by leveraging FPGA's reconfigurability and specialized components. AutoGNN adapts to diverse graph inputs, efficiently performing computationally intensive tasks such as graph conversion and sampling. By utilizing components like adder trees, AutoGNN executes reduction operations in constant time, overcoming the limitations of serialization and synchronization on GPUs. AutoGNN integrates unified processing elements (UPEs) and single-cycle reducers (SCRs) to streamline GNN preprocessing. UPEs enable scalable parallel processing for edge sorting and unique vertex selection, while SCRs efficiently handle sequential tasks such as pointer array construction and subgraph reindexing. A user-level software framework dynamically profiles graph inputs, determines optimal configurations, and reprograms AutoGNN to handle varying workloads. Implemented on a 7$n$m enterprise FPGA, AutoGNN achieves up to 9.0$\times$ and 2.1$\times$ speedup compared to conventional and GPU-accelerated preprocessing systems, respectively, enabling high-performance GNN preprocessing across diverse datasets. △ Less

Submitted 31 January, 2026; originally announced February 2026.

MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spotting

Authors: Youngmoon Jung, Myunghun Jung, Joon-Young Yang, Yong-Hyeok Lee, Jaeyoung Roh, Hoon-Young Cho

Abstract: Open-vocabulary keyword spotting (KWS) with text-based enrollment has emerged as a flexible alternative to fixed-phrase triggers. Prior utterance-level matching methods, from an embedding-learning standpoint, learn embeddings at a single fixed dimensionality. We depart from this design and propose Matryoshka Audio-Text Embeddings (MATE), a dual-encoder framework that encodes multiple embedding gra… ▽ More Open-vocabulary keyword spotting (KWS) with text-based enrollment has emerged as a flexible alternative to fixed-phrase triggers. Prior utterance-level matching methods, from an embedding-learning standpoint, learn embeddings at a single fixed dimensionality. We depart from this design and propose Matryoshka Audio-Text Embeddings (MATE), a dual-encoder framework that encodes multiple embedding granularities within a single vector via nested sub-embeddings ("prefixes"). Specifically, we introduce a PCA-guided prefix alignment: PCA-compressed versions of the full text embedding for each prefix size serve as teacher targets to align both audio and text prefixes. This alignment concentrates salient keyword cues in lower-dimensional prefixes, while higher dimensions add detail. MATE is trained with standard deep metric learning objectives for audio-text KWS, and is loss-agnostic. To our knowledge, this is the first application of matryoshka-style embeddings to KWS, achieving state-of-the-art results on WSJ and LibriPhrase without any inference overhead. △ Less

Submitted 20 January, 2026; originally announced January 2026.

Comments: 5 pages, 1 figure, Accepted at ICASSP 2026

A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription

Authors: Unggi Lee, Joo Young Kim, Ran Ju, Minyoung Jung, Jeyeon Eo

Abstract: Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require fine-tuning and exhibit unstable or near-random performance. Moreover, prior KT systems primarily focus on prediction and rely on multi-stage pipelines for feedback and… ▽ More Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require fine-tuning and exhibit unstable or near-random performance. Moreover, prior KT systems primarily focus on prediction and rely on multi-stage pipelines for feedback and recommendation, resulting in increased system complexity and resources. To address this gap, we propose Thinking-KT, a training-free KT framework that incorporates Test-Time Scaling (TTS), enabling even small LLMs to achieve competitive KT performance. Moreover, in this framework, a small LLM can jointly perform KT prediction, personalized feedback generation, and learning recommendation in a unified output without degrading prediction accuracy. Beyond performance, we present the systematic analysis of reasoning traces in KT. Our results demonstrate that TTS is a critical yet underexplored factor in LLM-based KT, and that small LLMs can serve as unified ITS engines. △ Less

Submitted 4 January, 2026; originally announced January 2026.

IM HERE: Interaction Model for Human Effort Based Robot Engagement

Authors: Dominykas Strazdas, Magnus Jung, Jan Marquenie, Ingo Siegert, Ayoub Al-Hamadi

Abstract: The effectiveness of human-robot interaction often hinges on the ability to cultivate engagement - a dynamic process of cognitive involvement that supports meaningful exchanges. Many existing definitions and models of engagement are either too vague or lack the ability to generalize across different contexts. We introduce IM HERE, a novel framework that models engagement effectively in human-human… ▽ More The effectiveness of human-robot interaction often hinges on the ability to cultivate engagement - a dynamic process of cognitive involvement that supports meaningful exchanges. Many existing definitions and models of engagement are either too vague or lack the ability to generalize across different contexts. We introduce IM HERE, a novel framework that models engagement effectively in human-human, human-robot, and robot-robot interactions. By employing an effort-based description of bilateral relationships between entities, we provide an accurate breakdown of relationship patterns, simplifying them to focus placement and four key states. This framework captures mutual relationships, group behaviors, and actions conforming to social norms, translating them into specific directives for autonomous systems. By integrating both subjective perceptions and objective states, the model precisely identifies and describes miscommunication. The primary objective of this paper is to automate the analysis, modeling, and description of social behavior, and to determine how autonomous systems can behave in accordance with social norms for full social integration while simultaneously pursuing their own social goals. △ Less

Submitted 3 December, 2025; originally announced December 2025.

Comments: 8 pages, 5 figures

Journal ref: 2025 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)

SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields

Authors: Sangheon Yang, Yeongin Yoon, Hong Mo Jung, Jongwoo Lim

Abstract: Traditional Visual Odometry (VO) and Visual Inertial Odometry (VIO) methods rely on a 'pose-centric' paradigm, which computes absolute camera poses from the local map thus requires large-scale landmark maintenance and continuous map optimization. This approach is computationally expensive, limiting their real-time performance on resource-constrained devices. To overcome these limitations, we intro… ▽ More Traditional Visual Odometry (VO) and Visual Inertial Odometry (VIO) methods rely on a 'pose-centric' paradigm, which computes absolute camera poses from the local map thus requires large-scale landmark maintenance and continuous map optimization. This approach is computationally expensive, limiting their real-time performance on resource-constrained devices. To overcome these limitations, we introduce Sparse Motion Field Visual Odometry (SMF-VO), a lightweight, 'motion-centric' framework. Our approach directly estimates instantaneous linear and angular velocity from sparse optical flow, bypassing the need for explicit pose estimation or expensive landmark tracking. We also employed a generalized 3D ray-based motion field formulation that works accurately with various camera models, including wide-field-of-view lenses. SMF-VO demonstrates superior efficiency and competitive accuracy on benchmark datasets, achieving over 100 FPS on a Raspberry Pi 5 using only a CPU. Our work establishes a scalable and efficient alternative to conventional methods, making it highly suitable for mobile robotics and wearable devices. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Mitigating Semantic Collapse in Partially Relevant Video Retrieval

Authors: WonJun Moon, MinSeok Jung, Gilhan Park, Tae-Young Kim, Cheol-Ho Cho, Woojin Jun, Jae-Pil Heo

Abstract: Partially Relevant Video Retrieval (PRVR) seeks videos where only part of the content matches a text query. Existing methods treat every annotated text-video pair as a positive and all others as negatives, ignoring the rich semantic variation both within a single video and across different videos. Consequently, embeddings of both queries and their corresponding video-clip segments for distinct eve… ▽ More Partially Relevant Video Retrieval (PRVR) seeks videos where only part of the content matches a text query. Existing methods treat every annotated text-video pair as a positive and all others as negatives, ignoring the rich semantic variation both within a single video and across different videos. Consequently, embeddings of both queries and their corresponding video-clip segments for distinct events within the same video collapse together, while embeddings of semantically similar queries and segments from different videos are driven apart. This limits retrieval performance when videos contain multiple, diverse events. This paper addresses the aforementioned problems, termed as semantic collapse, in both the text and video embedding spaces. We first introduce Text Correlation Preservation Learning, which preserves the semantic relationships encoded by the foundation model across text queries. To address collapse in video embeddings, we propose Cross-Branch Video Alignment (CBVA), a contrastive alignment method that disentangles hierarchical video representations across temporal scales. Subsequently, we introduce order-preserving token merging and adaptive CBVA to enhance alignment by producing video segments that are internally coherent yet mutually distinctive. Extensive experiments on PRVR benchmarks demonstrate that our framework effectively prevents semantic collapse and substantially improves retrieval accuracy. △ Less

Submitted 31 October, 2025; originally announced October 2025.

Comments: Accpeted to NeurIPS 2025. Code is available at https://github.com/admins97/MSC_PRVR

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

Authors: Minjoon Jung, Junbin Xiao, Junghyun Kim, Byoung-Tak Zhang, Angela Yao

Abstract: Can Video-LLMs achieve consistent temporal understanding when videos capture the same event from different viewpoints? To study this, we introduce EgoExo-Con (Consistency), a benchmark of comprehensively synchronized egocentric and exocentric video pairs with human-refined queries in natural language. EgoExo-Con emphasizes two temporal understanding tasks: Temporal Verification and Temporal Ground… ▽ More Can Video-LLMs achieve consistent temporal understanding when videos capture the same event from different viewpoints? To study this, we introduce EgoExo-Con (Consistency), a benchmark of comprehensively synchronized egocentric and exocentric video pairs with human-refined queries in natural language. EgoExo-Con emphasizes two temporal understanding tasks: Temporal Verification and Temporal Grounding. It evaluates not only correctness but consistency across viewpoints. Our analysis reveals two critical limitations of existing Video-LLMs: (1) models often fail to maintain consistency, with results far worse than their single-view performances. (2) When naively finetuned with synchronized videos of both viewpoints, the models show improved consistency but often underperform those trained on a single view. For improvements, we propose View-GRPO, a novel reinforcement learning framework that effectively strengthens view-specific temporal reasoning while encouraging consistent comprehension across viewpoints. Our method demonstrates its superiority over naive SFT and GRPO, especially for improving cross-view consistency. All resources will be made publicly available. △ Less

Submitted 29 October, 2025; originally announced October 2025.

Comments: project page: \url{https://minjoong507.github.io/projects/EgoExo-Con/}

3D Optimization for AI Inference Scaling: Balancing Accuracy, Cost, and Latency

Authors: Minseok Jung, Abhas Ricky, Muhammad Rameez Chatni

Abstract: AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that jointly calibrates accuracy, cost, and latency within a unified decision space, enabling constraints-aware inference scaling. Using Monte Carlo simulations acros… ▽ More AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that jointly calibrates accuracy, cost, and latency within a unified decision space, enabling constraints-aware inference scaling. Using Monte Carlo simulations across three representative scenarios and nine simulated large language models, we evaluate four optimization methods to address the 3D multi-objective optimization (MOO) problem. Framing inference scaling in MOO shapes a feasible space that 1D and 2D optimizations fail to capture, enabling environment-adaptive selection of the inference scaling~$k$. Results show that knee-point optimization based on Pareto frontiers achieves the best balance, while accuracy-maximization remains favorable when accuracy is prioritized. Our results further show that smaller models, when combined with optimal inference scaling, can match or exceed the performance of larger models at a fraction of the cost. The framework establishes a theoretical foundation for deployment-aware inference scaling across diverse operational conditions. △ Less

Submitted 15 November, 2025; v1 submitted 20 October, 2025; originally announced October 2025.

Architecture, Simulation and Software Stack to Support Post-CMOS Accelerators: The ARCHYTAS Project

Authors: Giovanni Agosta, Stefano Cherubin, Derek Christ, Francesco Conti, Asbjørn Djupdal, Matthias Jung, Georgios Keramidas, Roberto Passerone, Paolo Rech, Elisa Ricci, Philippe Velha, Flavio Vella, Kasim Sinan Yildirim, Nils Wilbert

Abstract: ARCHYTAS aims to design and evaluate non-conventional hardware accelerators, in particular, optoelectronic, volatile and non-volatile processing-in-memory, and neuromorphic, to tackle the power, efficiency, and scalability bottlenecks of AI with an emphasis on defense use cases (e.g., autonomous vehicles, surveillance drones, maritime and space platforms). In this paper, we present the system arch… ▽ More ARCHYTAS aims to design and evaluate non-conventional hardware accelerators, in particular, optoelectronic, volatile and non-volatile processing-in-memory, and neuromorphic, to tackle the power, efficiency, and scalability bottlenecks of AI with an emphasis on defense use cases (e.g., autonomous vehicles, surveillance drones, maritime and space platforms). In this paper, we present the system architecture and software stack that ARCHYTAS will develop to integrate and support those accelerators, as well as the simulation software needed for early prototyping of the full system and its components. △ Less

Submitted 18 October, 2025; originally announced October 2025.

Journal ref: 2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)

MPI-over-CXL: Enhancing Communication Efficiency in Distributed HPC Systems

Authors: Miryeong Kwon, Donghyun Gouk, Hyein Woo, Junhee Kim, Jinwoo Baek, Kyungkuk Nam, Sangyoon Ji, Jiseon Kim, Hanyeoreum Bae, Junhyeok Jang, Hyunwoo You, Junseok Moon, Myoungsoo Jung

Abstract: MPI implementations commonly rely on explicit memory-copy operations, incurring overhead from redundant data movement and buffer management. This overhead notably impacts HPC workloads involving intensive inter-processor communication. In response, we introduce MPI-over-CXL, a novel MPI communication paradigm leveraging CXL, which provides cache-coherent shared memory across multiple hosts. MPI-ov… ▽ More MPI implementations commonly rely on explicit memory-copy operations, incurring overhead from redundant data movement and buffer management. This overhead notably impacts HPC workloads involving intensive inter-processor communication. In response, we introduce MPI-over-CXL, a novel MPI communication paradigm leveraging CXL, which provides cache-coherent shared memory across multiple hosts. MPI-over-CXL replaces traditional data-copy methods with direct shared memory access, significantly reducing communication latency and memory bandwidth usage. By mapping shared memory regions directly into the virtual address spaces of MPI processes, our design enables efficient pointer-based communication, eliminating redundant copying operations. To validate this approach, we implement a comprehensive hardware and software environment, including a custom CXL 3.2 controller, FPGA-based multi-host emulation, and dedicated software stack. Our evaluations using representative benchmarks demonstrate substantial performance improvements over conventional MPI systems, underscoring MPI-over-CXL's potential to enhance efficiency and scalability in large-scale HPC environments. △ Less

Submitted 16 October, 2025; originally announced October 2025.

ScalePool: Hybrid XLink-CXL Fabric for Composable Resource Disaggregation in Unified Scale-up Domains

Authors: Hyein Woo, Miryeong Kwon, Jiseon Kim, Eunjee Na, Hanjin Choi, Seonghyeon Jang, Myoungsoo Jung

Abstract: This paper proposes ScalePool, a novel cluster architecture designed to interconnect numerous accelerators using unified hardware interconnects rather than traditional long-distance networking. ScalePool integrates Accelerator-Centric Links (XLink) and Compute Express Link (CXL) into a unified XLink-CXL hybrid fabric. Specifically, ScalePool employs XLink for intra-cluster, low-latency accelerator… ▽ More This paper proposes ScalePool, a novel cluster architecture designed to interconnect numerous accelerators using unified hardware interconnects rather than traditional long-distance networking. ScalePool integrates Accelerator-Centric Links (XLink) and Compute Express Link (CXL) into a unified XLink-CXL hybrid fabric. Specifically, ScalePool employs XLink for intra-cluster, low-latency accelerator communication, while using hierarchical CXL-based switching fabrics for scalable and coherent inter-cluster memory sharing. By abstracting interfaces through CXL, ScalePool structurally resolves interoperability constraints, enabling heterogeneous cluster operation and composable resource disaggregation. In addition, ScalePool introduces explicit memory tiering: the latency-critical tier-1 combines accelerator-local memory with coherence-centric CXL and XLink, whereas the highcapacity tier-2 employs dedicated memory nodes interconnected by a CXL-based fabric, achieving scalable and efficient memory pooling. Evaluation results show that ScalePool accelerates LLM training by 1.22x on average and up to 1.84x compared to conventional RDMA-based environments. Furthermore, the proposed tier-2 memory disaggregation strategy reduces latency by up to 4.5x for memory-intensive workloads. △ Less

Submitted 16 October, 2025; originally announced October 2025.

Beat Tracking as Object Detection

Authors: Jaehoon Ahn, Moon-Ryul Jung

Abstract: Recent beat and downbeat tracking models (e.g., RNNs, TCNs, Transformers) output frame-level activations. We propose reframing this task as object detection, where beats and downbeats are modeled as temporal "objects." Adapting the FCOS detector from computer vision to 1D audio, we replace its original backbone with WaveBeat's temporal feature extractor and add a Feature Pyramid Network to capture… ▽ More Recent beat and downbeat tracking models (e.g., RNNs, TCNs, Transformers) output frame-level activations. We propose reframing this task as object detection, where beats and downbeats are modeled as temporal "objects." Adapting the FCOS detector from computer vision to 1D audio, we replace its original backbone with WaveBeat's temporal feature extractor and add a Feature Pyramid Network to capture multi-scale temporal patterns. The model predicts overlapping beat/downbeat intervals with confidence scores, followed by non-maximum suppression (NMS) to select final predictions. This NMS step serves a similar role to DBNs in traditional trackers, but is simpler and less heuristic. Evaluated on standard music datasets, our approach achieves competitive results, showing that object detection techniques can effectively model musical beats with minimal adaptation. △ Less

Submitted 16 October, 2025; v1 submitted 16 October, 2025; originally announced October 2025.

Comments: 11 pages, 4 figures, 5 tables

PhysioME: A Robust Multimodal Self-Supervised Framework for Physiological Signals with Missing Modalities

Authors: Cheol-Hui Lee, Hwa-Yeon Lee, Min-Kyung Jung, Dong-Joo Kim

Abstract: Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in substantial performance degradation in the absence of any modality. To overcome this limitation, this study proposes PhysioME, a robust framework designed to ensure rel… ▽ More Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in substantial performance degradation in the absence of any modality. To overcome this limitation, this study proposes PhysioME, a robust framework designed to ensure reliable performance under missing modality conditions. PhysioME adopts: (1) a multimodal self-supervised learning approach that combines contrastive learning with masked prediction; (2) a Dual-PathNeuroNet backbone tailored to capture the temporal dynamics of each physiological signal modality; and (3) a restoration decoder that reconstructs missing modality tokens, enabling flexible processing of incomplete inputs. The experimental results show that PhysioME achieves high consistency and generalization performance across various missing modality scenarios. These findings highlight the potential of PhysioME as a reliable tool for supporting clinical decision-making in real-world settings with imperfect data availability. △ Less

Submitted 13 October, 2025; originally announced October 2025.

Comments: 9 pages, 2 figures

Confidence-guided Refinement Reasoning for Zero-shot Question Answering

Authors: Youwon Jang, Woo Suk Choi, Minjoon Jung, Minsu Lee, Byoung-Tak Zhang

Abstract: We propose Confidence-guided Refinement Reasoning (C2R), a novel training-free framework applicable to question-answering (QA) tasks across text, image, and video domains. C2R strategically constructs and refines sub-questions and their answers (sub-QAs), deriving a better confidence score for the target answer. C2R first curates a subset of sub-QAs to explore diverse reasoning paths, then compare… ▽ More We propose Confidence-guided Refinement Reasoning (C2R), a novel training-free framework applicable to question-answering (QA) tasks across text, image, and video domains. C2R strategically constructs and refines sub-questions and their answers (sub-QAs), deriving a better confidence score for the target answer. C2R first curates a subset of sub-QAs to explore diverse reasoning paths, then compares the confidence scores of the resulting answer candidates to select the most reliable final answer. Since C2R relies solely on confidence scores derived from the model itself, it can be seamlessly integrated with various existing QA models, demonstrating consistent performance improvements across diverse models and benchmarks. Furthermore, we provide essential yet underexplored insights into how leveraging sub-QAs affects model behavior, specifically analyzing the impact of both the quantity and quality of sub-QAs on achieving robust and reliable reasoning. △ Less

Submitted 25 September, 2025; originally announced September 2025.

Comments: 18 pages (including references and appendix)

LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring

Authors: Jinhee Jang, Ayoung Moon, Minkyoung Jung, YoungBin Kim, Seung Jin Lee

Abstract: The emergence of large language models (LLMs) has brought a new paradigm to automated essay scoring (AES), a long-standing and practical application of natural language processing in education. However, achieving human-level multi-perspective understanding and judgment remains a challenge. In this work, we propose Roundtable Essay Scoring (RES), a multi-agent evaluation framework designed to perfo… ▽ More The emergence of large language models (LLMs) has brought a new paradigm to automated essay scoring (AES), a long-standing and practical application of natural language processing in education. However, achieving human-level multi-perspective understanding and judgment remains a challenge. In this work, we propose Roundtable Essay Scoring (RES), a multi-agent evaluation framework designed to perform precise and human-aligned scoring under a zero-shot setting. RES constructs evaluator agents based on LLMs, each tailored to a specific prompt and topic context. Each agent independently generates a trait-based rubric and conducts a multi-perspective evaluation. Then, by simulating a roundtable-style discussion, RES consolidates individual evaluations through a dialectical reasoning process to produce a final holistic score that more closely aligns with human evaluation. By enabling collaboration and consensus among agents with diverse evaluation perspectives, RES outperforms prior zero-shot AES approaches. Experiments on the ASAP dataset using ChatGPT and Claude show that RES achieves up to a 34.86% improvement in average QWK over straightforward prompting (Vanilla) methods. △ Less

Submitted 18 September, 2025; v1 submitted 18 September, 2025; originally announced September 2025.

One-shot acceleration of transient PDE solvers via online-learned preconditioners

Authors: Mikhail Khodak, Min Ki Jung, Brian Wynne, Edmond Chow, Egemen Kolemen

Abstract: Data-driven acceleration of scientific computing workflows has been a high-profile aim of machine learning (ML) for science, with numerical simulation of transient partial differential equations (PDEs) being one of the main applications. The focus thus far has been on methods that require classical simulations to train, which when combined with the data-hungriness and optimization challenges of ne… ▽ More Data-driven acceleration of scientific computing workflows has been a high-profile aim of machine learning (ML) for science, with numerical simulation of transient partial differential equations (PDEs) being one of the main applications. The focus thus far has been on methods that require classical simulations to train, which when combined with the data-hungriness and optimization challenges of neural networks has caused difficulties in demonstrating a convincing advantage against strong classical baselines. We consider an alternative paradigm in which the learner uses a classical solver's own data to accelerate it, enabling a one-shot speedup of the simulation. Concretely, since transient PDEs often require solving a sequence of related linear systems, the feedback from repeated calls to a linear solver such as preconditioned conjugate gradient (PCG) can be used by a bandit algorithm to online-learn an adaptive sequence of solver configurations (e.g. preconditioners). The method we develop, PCGBandit, is implemented directly on top of the popular open source software OpenFOAM, which we use to show its effectiveness on a set of fluid and magnetohydrodynamics (MHD) problems. △ Less

Submitted 3 December, 2025; v1 submitted 10 September, 2025; originally announced September 2025.

Comments: code available at https://github.com/mkhodak/PCGBandit

RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts

Authors: Lauren H. Cooke, Matthias Jung, Jan M. Brendel, Nora M. Kerkovits, Borek Foldyna, Michael T. Lu, Vineet K. Raghu

Abstract: Chest radiographs (CXRs) are among the most common tests in medicine. Automated image interpretation may reduce radiologists\' workload and expand access to diagnostic expertise. Deep learning multi-task and foundation models have shown strong performance for CXR interpretation but are vulnerable to shortcut learning, where models rely on spurious and off-target correlations rather than clinically… ▽ More Chest radiographs (CXRs) are among the most common tests in medicine. Automated image interpretation may reduce radiologists\' workload and expand access to diagnostic expertise. Deep learning multi-task and foundation models have shown strong performance for CXR interpretation but are vulnerable to shortcut learning, where models rely on spurious and off-target correlations rather than clinically relevant features to make decisions. We introduce RoentMod, a counterfactual image editing framework that generates anatomically realistic CXRs with user-specified, synthetic pathology while preserving unrelated anatomical features of the original scan. RoentMod combines an open-source medical image generator (RoentGen) with an image-to-image modification model without requiring retraining. In reader studies with board-certified radiologists and radiology residents, RoentMod-produced images appeared realistic in 93\% of cases, correctly incorporated the specified finding in 89-99\% of cases, and preserved native anatomy comparable to real follow-up CXRs. Using RoentMod, we demonstrate that state-of-the-art multi-task and foundation models frequently exploit off-target pathology as shortcuts, limiting their specificity. Incorporating RoentMod-generated counterfactual images during training mitigated this vulnerability, improving model discrimination across multiple pathologies by 3-19\% AUC in internal validation and by 1-11\% for 5 out of 6 tested pathologies in external testing. These findings establish RoentMod as a broadly applicable tool for probing and correcting shortcut learning in medical AI. By enabling controlled counterfactual interventions, RoentMod enhances the robustness and interpretability of CXR interpretation models and provides a generalizable strategy for improving foundation models in medical imaging. △ Less

Submitted 10 September, 2025; originally announced September 2025.

Comments: 25 + 8 pages, 4 + 7 figures

MSC Class: I.4; I.2; J.3

Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs

Authors: Daehoon Gwak, Minseo Jung, Junwoo Park, Minho Park, ChaeHun Park, Junha Hyung, Jaegul Choo

Abstract: Masked diffusion models (MDMs) offer a promising non-autoregressive alternative for large language modeling. Standard decoding methods for MDMs, such as confidence-based sampling, select tokens independently based on individual token confidences at each diffusion step. However, we observe that this independent token selection often results in generation orders resembling sequential autoregressive… ▽ More Masked diffusion models (MDMs) offer a promising non-autoregressive alternative for large language modeling. Standard decoding methods for MDMs, such as confidence-based sampling, select tokens independently based on individual token confidences at each diffusion step. However, we observe that this independent token selection often results in generation orders resembling sequential autoregressive processes, limiting the advantages of non-autoregressive modeling. To mitigate this pheonomenon, we propose Reward-Weighted Sampling (RWS), a novel decoding strategy that leverages an external reward model to provide a principled global signal during the iterative diffusion process. Specifically, at each diffusion step, RWS evaluates the quality of the entire intermediate sequence and scales token logits accordingly, guiding token selection by integrating global sequence-level coherence. This method selectively increases the confidence of tokens that initially have lower scores, thereby promoting a more non-autoregressive generation order. Furthermore, we provide theoretical justification showing that reward-weighted logit scaling induces beneficial rank reversals in token selection and consistently improves expected reward. Experiments demonstrate that RWS significantly promotes non-autoregressive generation orders, leading to improvements across multiple evaluation metrics. These results highlight the effectiveness of integrating global signals in enhancing both the non-autoregressive properties and overall performance of MDMs. △ Less

Submitted 20 September, 2025; v1 submitted 31 August, 2025; originally announced September 2025.

Comments: EMNLP 2025 Main Paper (Long)

A Similarity Measure for Comparing Conversational Dynamics

Authors: Sang Min Jung, Kaixiang Zhang, Cristian Danescu-Niculescu-Mizil

Abstract: The quality of a conversation goes beyond the individual quality of each reply, and instead emerges from how these combine into interactional dynamics that give the conversation its distinctive overall "shape". However, there is no robust automated method for comparing conversations in terms of their overall dynamics. Such methods could enhance the analysis of conversational data and help evaluate… ▽ More The quality of a conversation goes beyond the individual quality of each reply, and instead emerges from how these combine into interactional dynamics that give the conversation its distinctive overall "shape". However, there is no robust automated method for comparing conversations in terms of their overall dynamics. Such methods could enhance the analysis of conversational data and help evaluate conversational agents more holistically. In this work, we introduce a similarity measure for comparing conversations with respect to their dynamics. We design a validation procedure for testing the robustness of the metric in capturing differences in conversation dynamics and for assessing its sensitivity to the topic of the conversations. To illustrate the measure's utility, we use it to analyze conversational dynamics in a large online community, bringing new insights into the role of situational power in conversations. △ Less

Submitted 20 September, 2025; v1 submitted 25 July, 2025; originally announced July 2025.

Comments: Proceedings of EMNLP 2025 (Findings). Code and demos available in ConvoKit (https://convokit.cornell.edu/)

GhostUMAP2: Measuring and Analyzing (r,d)-Stability of UMAP

Authors: Myeongwon Jung, Takanori Fujiwara, Jaemin Jo

Abstract: Despite the widespread use of Uniform Manifold Approximation and Projection (UMAP), the impact of its stochastic optimization process on the results remains underexplored. We observed that it often produces unstable results where the projections of data points are determined mostly by chance rather than reflecting neighboring structures. To address this limitation, we introduce (r,d)-stability to… ▽ More Despite the widespread use of Uniform Manifold Approximation and Projection (UMAP), the impact of its stochastic optimization process on the results remains underexplored. We observed that it often produces unstable results where the projections of data points are determined mostly by chance rather than reflecting neighboring structures. To address this limitation, we introduce (r,d)-stability to UMAP: a framework that analyzes the stochastic positioning of data points in the projection space. To assess how stochastic elements, specifically initial projection positions and negative sampling, impact UMAP results, we introduce "ghosts", or duplicates of data points representing potential positional variations due to stochasticity. We define a data point's projection as (r,d)-stable if its ghosts perturbed within a circle of radius r in the initial projection remain confined within a circle of radius d for their final positions. To efficiently compute the ghost projections, we develop an adaptive dropping scheme that reduces a runtime up to 60% compared to an unoptimized baseline while maintaining approximately 90% of unstable points. We also present a visualization tool that supports the interactive exploration of the (r,d)-stability of data points. Finally, we demonstrate the effectiveness of our framework by examining the stability of projections of real-world datasets and present usage guidelines for the effective use of our framework. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Compute Can't Handle the Truth: Why Communication Tax Prioritizes Memory and Interconnects in Modern AI Infrastructure

Authors: Myoungsoo Jung

Abstract: Modern AI workloads such as large language models (LLMs) and retrieval-augmented generation (RAG) impose severe demands on memory, communication bandwidth, and resource flexibility. Traditional GPU-centric architectures struggle to scale due to growing inter-GPU communication overheads. This report introduces key AI concepts and explains how Transformers revolutionized data representation in LLMs.… ▽ More Modern AI workloads such as large language models (LLMs) and retrieval-augmented generation (RAG) impose severe demands on memory, communication bandwidth, and resource flexibility. Traditional GPU-centric architectures struggle to scale due to growing inter-GPU communication overheads. This report introduces key AI concepts and explains how Transformers revolutionized data representation in LLMs. We analyze large-scale AI hardware and data center designs, identifying scalability bottlenecks in hierarchical systems. To address these, we propose a modular data center architecture based on Compute Express Link (CXL) that enables disaggregated scaling of memory, compute, and accelerators. We further explore accelerator-optimized interconnects-collectively termed XLink (e.g., UALink, NVLink, NVLink Fusion)-and introduce a hybrid CXL-over-XLink design to reduce long-distance data transfers while preserving memory coherence. We also propose a hierarchical memory model that combines local and pooled memory, and evaluate lightweight CXL implementations, HBM, and silicon photonics for efficient scaling. Our evaluations demonstrate improved scalability, throughput, and flexibility in AI infrastructure. △ Less

Submitted 13 July, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

ACM Class: B.4.3; C.0; C.2.1; C.2.2

From Block to Byte: Transforming PCIe SSDs with CXL Memory Protocol and Instruction Annotation

Authors: Miryeong Kwon, Donghyun Gouk, Junhyeok Jang, Jinwoo Baek, Hyunwoo You, Sangyoon Ji, Hongjoo Jung, Junseok Moon, Seungkwan Kang, Seungjun Lee, Myoungsoo Jung

Abstract: This paper explores how Compute Express Link (CXL) can transform PCIe-based block storage into a scalable, byte-addressable working memory. We address the challenges of adapting block storage to CXL's memory-centric model by emphasizing cacheability as a key enabler and advocating for Type 3 endpoint devices, referred to as CXL-SSDs. To validate our approach, we prototype a CXL-SSD on a custom FPG… ▽ More This paper explores how Compute Express Link (CXL) can transform PCIe-based block storage into a scalable, byte-addressable working memory. We address the challenges of adapting block storage to CXL's memory-centric model by emphasizing cacheability as a key enabler and advocating for Type 3 endpoint devices, referred to as CXL-SSDs. To validate our approach, we prototype a CXL-SSD on a custom FPGA platform and propose annotation mechanisms, Determinism and Bufferability, to enhance performance while preserving data persistency. Our simulation-based evaluation demonstrates that CXL-SSD achieves 10.9x better performance than PCIe-based memory expanders and further reduces latency by 5.4x with annotation enhancements. In workloads with high locality, CXL-SSD approaches DRAM-like performance due to efficient on-chip caching. This work highlights the feasibility of integrating block storage into CXL's ecosystem and provides a foundation for future memory-storage convergence. △ Less

Submitted 18 June, 2025; originally announced June 2025.

CXL-GPU: Pushing GPU Memory Boundaries with the Integration of CXL Technologies

Authors: Donghyun Gouk, Seungkwan Kang, Seungjun Lee, Jiseon Kim, Kyungkuk Nam, Eojin Ryu, Sangwon Lee, Dongpyung Kim, Junhyeok Jang, Hanyeoreum Bae, Myoungsoo Jung

Abstract: This work introduces a GPU storage expansion solution utilizing CXL, featuring a novel GPU system design with multiple CXL root ports for integrating diverse storage media (DRAMs and/or SSDs). We developed and siliconized a custom CXL controller integrated at the hardware RTL level, achieving two-digit nanosecond roundtrip latency, the first in the field. This study also includes speculative read… ▽ More This work introduces a GPU storage expansion solution utilizing CXL, featuring a novel GPU system design with multiple CXL root ports for integrating diverse storage media (DRAMs and/or SSDs). We developed and siliconized a custom CXL controller integrated at the hardware RTL level, achieving two-digit nanosecond roundtrip latency, the first in the field. This study also includes speculative read and deterministic store mechanisms to efficiently manage read and write operations to hide the endpoint's backend media latency variation. Performance evaluations reveal our approach significantly outperforms existing methods, marking a substantial advancement in GPU storage technology. △ Less

Submitted 18 June, 2025; originally announced June 2025.

SHeRLoc: Synchronized Heterogeneous Radar Place Recognition for Cross-Modal Localization

Authors: Hanjun Kim, Minwoo Jung, Wooseong Yang, Ayoung Kim

Abstract: Despite the growing adoption of radar in robotics, the majority of research has been confined to homogeneous sensor types, overlooking the integration and cross-modality challenges inherent in heterogeneous radar technologies. This leads to significant difficulties in generalizing across diverse radar data types, with modality-aware approaches that could leverage the complementary strengths of het… ▽ More Despite the growing adoption of radar in robotics, the majority of research has been confined to homogeneous sensor types, overlooking the integration and cross-modality challenges inherent in heterogeneous radar technologies. This leads to significant difficulties in generalizing across diverse radar data types, with modality-aware approaches that could leverage the complementary strengths of heterogeneous radar remaining unexplored. To bridge these gaps, we propose SHeRLoc, the first deep network tailored for heterogeneous radar, which utilizes RCS polar matching to align multimodal radar data. Our hierarchical optimal transport-based feature aggregation method generates rotationally robust multi-scale descriptors. By employing FFT-similarity-based data mining and adaptive margin-based triplet loss, SHeRLoc enables FOV-aware metric learning. SHeRLoc achieves an order of magnitude improvement in heterogeneous radar place recognition, increasing recall@1 from below 0.1 to 0.9 on a public dataset and outperforming state of-the-art methods. Also applicable to LiDAR, SHeRLoc paves the way for cross-modal place recognition and heterogeneous sensor SLAM. The supplementary materials and source code are available at https://sites.google.com/view/radar-sherloc. △ Less

Submitted 10 October, 2025; v1 submitted 18 June, 2025; originally announced June 2025.

Comments: 9 pages, 9 figures, accepted to RA-L

Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval

Authors: CH Cho, WJ Moon, W Jun, MS Jung, JP Heo

Abstract: Partially Relevant Video Retrieval~(PRVR) aims to retrieve a video where a specific segment is relevant to a given text query. Typical training processes of PRVR assume a one-to-one relationship where each text query is relevant to only one video. However, we point out the inherent ambiguity between text and video content based on their conceptual scope and propose a framework that incorporates th… ▽ More Partially Relevant Video Retrieval~(PRVR) aims to retrieve a video where a specific segment is relevant to a given text query. Typical training processes of PRVR assume a one-to-one relationship where each text query is relevant to only one video. However, we point out the inherent ambiguity between text and video content based on their conceptual scope and propose a framework that incorporates this ambiguity into the model learning process. Specifically, we propose Ambiguity-Restrained representation Learning~(ARL) to address ambiguous text-video pairs. Initially, ARL detects ambiguous pairs based on two criteria: uncertainty and similarity. Uncertainty represents whether instances include commonly shared context across the dataset, while similarity indicates pair-wise semantic overlap. Then, with the detected ambiguous pairs, our ARL hierarchically learns the semantic relationship via multi-positive contrastive learning and dual triplet margin loss. Additionally, we delve into fine-grained relationships within the video instances. Unlike typical training at the text-video level, where pairwise information is provided, we address the inherent ambiguity within frames of the same untrimmed video, which often contains multiple contexts. This allows us to further enhance learning at the text-frame level. Lastly, we propose cross-model ambiguity detection to mitigate the error propagation that occurs when a single model is employed to detect ambiguous pairs for its training. With all components combined, our proposed method demonstrates its effectiveness in PRVR. △ Less

Submitted 9 June, 2025; originally announced June 2025.

Comments: Accepted to AAAI 2025

Containerized In-Storage Processing and Computing-Enabled SSD Disaggregation

Authors: Miryeong Kwon, Donghyun Gouk, Eunjee Na, Jiseon Kim, Junhee Kim, Hyein Woo, Eojin Ryu, Hyunkyu Choi, Jinwoo Baek, Hanyeoreum Bae, Mahmut Kandemir, Myoungsoo Jung

Abstract: ISP minimizes data transfer for analytics but faces challenges in adaptation and disaggregation. We propose DockerSSD, an ISP model leveraging OS-level virtualization and lightweight firmware to enable containerized data processing directly on SSDs. Key features include Ethernet over NVMe for network-based ISP management and Virtual Firmware for secure, efficient container execution. DockerSSD sup… ▽ More ISP minimizes data transfer for analytics but faces challenges in adaptation and disaggregation. We propose DockerSSD, an ISP model leveraging OS-level virtualization and lightweight firmware to enable containerized data processing directly on SSDs. Key features include Ethernet over NVMe for network-based ISP management and Virtual Firmware for secure, efficient container execution. DockerSSD supports disaggregated storage pools, reducing host overhead and enhancing large-scale services like LLM inference. It achieves up to 2.0x better performance for I/O-intensive workloads, and 7.9x improvement in distributed LLM inference. △ Less

Submitted 7 June, 2025; originally announced June 2025.

High-speed control and navigation for quadrupedal robots on complex and discrete terrain

Authors: Hyeongjun Kim, Hyunsik Oh, Jeongsoo Park, Yunho Kim, Donghoon Youm, Moonkyu Jung, Minho Lee, Jemin Hwangbo

Abstract: High-speed legged navigation in discrete and geometrically complex environments is a challenging task because of the high-degree-of-freedom dynamics and long-horizon, nonconvex nature of the optimization problem. In this work, we propose a hierarchical navigation pipeline for legged robots that can traverse such environments at high speed. The proposed pipeline consists of a planner and tracker mo… ▽ More High-speed legged navigation in discrete and geometrically complex environments is a challenging task because of the high-degree-of-freedom dynamics and long-horizon, nonconvex nature of the optimization problem. In this work, we propose a hierarchical navigation pipeline for legged robots that can traverse such environments at high speed. The proposed pipeline consists of a planner and tracker module. The planner module finds physically feasible foothold plans by sampling-based optimization with fast sequential filtering using heuristics and a neural network. Subsequently, rollouts are performed in a physics simulation to identify the best foothold plan regarding the engineered cost function and to confirm its physical consistency. This hierarchical planning module is computationally efficient and physically accurate at the same time. The tracker aims to accurately step on the target footholds from the planning module. During the training stage, the foothold target distribution is given by a generative model that is trained competitively with the tracker. This process ensures that the tracker is trained in an environment with the desired difficulty. The resulting tracker can overcome terrains that are more difficult than what the previous methods could manage. We demonstrated our approach using Raibo, our in-house dynamic quadruped robot. The results were dynamic and agile motions: Raibo is capable of running on vertical walls, jumping a 1.3-meter gap, running over stepping stones at 4 meters per second, and autonomously navigating on terrains full of 30° ramps, stairs, and boxes of various sizes. △ Less

Submitted 3 June, 2025; originally announced June 2025.

Journal ref: Science Robotics 10.102 (2025): eads6192

Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation

Authors: Seungmin Lee, Yongsang Yoo, Minhwa Jung, Min Song

Abstract: Dialogue Topic Segmentation (DTS) aims to divide dialogues into coherent segments. DTS plays a crucial role in various NLP downstream tasks, but suffers from chronic problems: data shortage, labeling ambiguity, and incremental complexity of recently proposed solutions. On the other hand, Despite advances in Large Language Models (LLMs) and reasoning strategies, these have rarely been applied to DT… ▽ More Dialogue Topic Segmentation (DTS) aims to divide dialogues into coherent segments. DTS plays a crucial role in various NLP downstream tasks, but suffers from chronic problems: data shortage, labeling ambiguity, and incremental complexity of recently proposed solutions. On the other hand, Despite advances in Large Language Models (LLMs) and reasoning strategies, these have rarely been applied to DTS. This paper introduces Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation, which utilizes LLM-based multi-step deductive reasoning to enhance DTS performance and enable case study using intermediate result. Our method employs a structured prompting approach for bidirectional context summarization, utterance intent classification, and deductive topic shift detection. In the intent classification process, we propose the generalizable intent list for domain-agnostic dialogue intent classification. Experiments in various dialogue settings demonstrate that Def-DTS consistently outperforms traditional and state-of-the-art approaches, with each subtask contributing to improved performance, particularly in reducing type 2 error. We also explore the potential for autolabeling, emphasizing the importance of LLM reasoning techniques in DTS. △ Less

Submitted 27 May, 2025; originally announced May 2025.

Comments: 19 pages, 3 figures, Accepted to Findings of the ACL 2025

CXL Topology-Aware and Expander-Driven Prefetching: Unlocking SSD Performance

Authors: Dongsuk Oh, Miryeong Kwon, Jiseon Kim, Eunjee Na, Junseok Moon, Hyunkyu Choi, Seonghyeon Jang, Hanjin Choi, Hongjoo Jung, Sangwon Lee, Myoungsoo Jung

Abstract: Integrating compute express link (CXL) with SSDs allows scalable access to large memory but has slower speeds than DRAMs. We present ExPAND, an expander-driven CXL prefetcher that offloads last-level cache (LLC) prefetching from host CPU to CXL-SSDs. ExPAND uses a heterogeneous prediction algorithm for prefetching and ensures data consistency with CXL.mem's back-invalidation. We examine prefetch t… ▽ More Integrating compute express link (CXL) with SSDs allows scalable access to large memory but has slower speeds than DRAMs. We present ExPAND, an expander-driven CXL prefetcher that offloads last-level cache (LLC) prefetching from host CPU to CXL-SSDs. ExPAND uses a heterogeneous prediction algorithm for prefetching and ensures data consistency with CXL.mem's back-invalidation. We examine prefetch timeliness for accurate latency estimation. ExPAND, being aware of CXL multi-tiered switching, provides end-to-end latency for each CXL-SSD and precise prefetch timeliness estimations. Our method reduces CXL-SSD reliance and enables direct host cache access for most data. ExPAND enhances graph application performance and SPEC CPU's performance by 9.0$\times$ and 14.7$\times$, respectively, surpassing CXL-SSD pools with diverse prefetching strategies. △ Less

Submitted 24 May, 2025; originally announced May 2025.

ImLPR: Image-based LiDAR Place Recognition using Vision Foundation Models

Authors: Minwoo Jung, Lanke Frank Tarimo Fu, Maurice Fallon, Ayoung Kim

Abstract: LiDAR Place Recognition (LPR) is a key component in robotic localization, enabling robots to align current scans with prior maps of their environment. While Visual Place Recognition (VPR) has embraced Vision Foundation Models (VFMs) to enhance descriptor robustness, LPR has relied on task-specific models with limited use of pre-trained foundation-level knowledge. This is due to the lack of 3D foun… ▽ More LiDAR Place Recognition (LPR) is a key component in robotic localization, enabling robots to align current scans with prior maps of their environment. While Visual Place Recognition (VPR) has embraced Vision Foundation Models (VFMs) to enhance descriptor robustness, LPR has relied on task-specific models with limited use of pre-trained foundation-level knowledge. This is due to the lack of 3D foundation models and the challenges of using VFM with LiDAR point clouds. To tackle this, we introduce ImLPR, a novel pipeline that employs a pre-trained DINOv2 VFM to generate rich descriptors for LPR. To the best of our knowledge, ImLPR is the first method to utilize a VFM for LPR while retaining the majority of pre-trained knowledge. ImLPR converts raw point clouds into novel three-channel Range Image Views (RIV) to leverage VFM in the LiDAR domain. It employs MultiConv adapters and Patch-InfoNCE loss for effective feature learning. We validate ImLPR on public datasets and outperform state-of-the-art (SOTA) methods across multiple evaluation metrics in both intra- and inter-session LPR. Comprehensive ablations on key design choices such as channel composition, RIV, adapters, and the patch-level loss quantify each component's impact. We release ImLPR as open source for the robotics community: https://github.com/minwoo0611/ImLPR. △ Less

Submitted 7 August, 2025; v1 submitted 23 May, 2025; originally announced May 2025.

Comments: CoRL2025 Accepted, 23 Pages, 15 Figures and 14 Tables

Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting

Authors: Youngmoon Jung, Yong-Hyeok Lee, Myunghun Jung, Jaeyoung Roh, Chang Woo Han, Hoon-Young Cho

Abstract: For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric learning (DML), enabling direct comparison of multi-modal embeddings in a shared embedding space. However, the inherent heterogeneity between audio and text modali… ▽ More For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric learning (DML), enabling direct comparison of multi-modal embeddings in a shared embedding space. However, the inherent heterogeneity between audio and text modalities presents a significant challenge. To address this, we propose Modality Adversarial Learning (MAL), which reduces the domain gap in heterogeneous modality representations. Specifically, we train a modality classifier adversarially to encourage both encoders to generate modality-invariant embeddings. Additionally, we apply DML to achieve phoneme-level alignment between audio and text, and conduct extensive comparisons across various DML objectives. Experiments on the Wall Street Journal (WSJ) and LibriPhrase datasets demonstrate the effectiveness of the proposed approach. △ Less

Submitted 22 May, 2025; v1 submitted 22 May, 2025; originally announced May 2025.

Comments: 5 pages, 1 figure, Accepted at Interspeech 2025

Large Language Model Use Impact Locus of Control

Authors: Jenny Xiyu Fu, Brennan Antone, Kowe Kadoma, Malte Jung

Abstract: As AI tools increasingly shape how we write, they may also quietly reshape how we perceive ourselves. This paper explores the psychological impact of co-writing with AI on people's locus of control. Through an empirical study with 462 participants, we found that employment status plays a critical role in shaping users' reliance on AI and their locus of control. Current results demonstrated that em… ▽ More As AI tools increasingly shape how we write, they may also quietly reshape how we perceive ourselves. This paper explores the psychological impact of co-writing with AI on people's locus of control. Through an empirical study with 462 participants, we found that employment status plays a critical role in shaping users' reliance on AI and their locus of control. Current results demonstrated that employed participants displayed higher reliance on AI and a shift toward internal control, while unemployed users tended to experience a reduction in personal agency. Through quantitative results and qualitative observations, this study opens a broader conversation about AI's role in shaping personal agency and identity. △ Less

Submitted 16 May, 2025; originally announced May 2025.

The City that Never Settles: Simulation-based LiDAR Dataset for Long-Term Place Recognition Under Extreme Structural Changes

Authors: Hyunho Song, Dongjae Lee, Seunghun Oh, Minwoo Jung, Ayoung Kim

Abstract: Large-scale construction and demolition significantly challenge long-term place recognition (PR) by drastically reshaping urban and suburban environments. Existing datasets predominantly reflect limited or indoor-focused changes, failing to adequately represent extensive outdoor transformations. To bridge this gap, we introduce the City that Never Settles (CNS) dataset, a simulation-based dataset… ▽ More Large-scale construction and demolition significantly challenge long-term place recognition (PR) by drastically reshaping urban and suburban environments. Existing datasets predominantly reflect limited or indoor-focused changes, failing to adequately represent extensive outdoor transformations. To bridge this gap, we introduce the City that Never Settles (CNS) dataset, a simulation-based dataset created using the CARLA simulator, capturing major structural changes-such as building construction and demolition-across diverse maps and sequences. Additionally, we propose TCR_sym, a symmetric version of the original TCR metric, enabling consistent measurement of structural changes irrespective of source-target ordering. Quantitative comparisons demonstrate that CNS encompasses more extensive transformations than current real-world benchmarks. Evaluations of state-of-the-art LiDAR-based PR methods on CNS reveal substantial performance degradation, underscoring the need for robust algorithms capable of handling significant environmental changes. Our dataset is available at https://github.com/Hyunho111/CNS_dataset. △ Less

Submitted 8 May, 2025; originally announced May 2025.

Exploring Ordinal Bias in Action Recognition for Instructional Videos

Authors: Joochan Kim, Minjoon Jung, Byoung-Tak Zhang

Abstract: Action recognition models have achieved promising results in understanding instructional videos. However, they often rely on dominant, dataset-specific action sequences rather than true video comprehension, a problem that we define as ordinal bias. To address this issue, we propose two effective video manipulation methods: Action Masking, which masks frames of frequently co-occurring actions, and… ▽ More Action recognition models have achieved promising results in understanding instructional videos. However, they often rely on dominant, dataset-specific action sequences rather than true video comprehension, a problem that we define as ordinal bias. To address this issue, we propose two effective video manipulation methods: Action Masking, which masks frames of frequently co-occurring actions, and Sequence Shuffling, which randomizes the order of action segments. Through comprehensive experiments, we demonstrate that current models exhibit significant performance drops when confronted with nonstandard action sequences, underscoring their vulnerability to ordinal bias. Our findings emphasize the importance of rethinking evaluation strategies and developing models capable of generalizing beyond fixed action patterns in diverse instructional videos. △ Less

Submitted 5 December, 2025; v1 submitted 9 April, 2025; originally announced April 2025.

Comments: Accepted at SCSL @ ICLR 2025

An In-Situ Spatial-Temporal Sequence Detector for Neuromorphic Vision Sensor Empowered by High Density Vertical NAND Storage

Authors: Zijian Zhao, Varun Darshana Parekh, Po-Kai Hsu, Yixin Qin, Yiming Song, A N M Nafiul Islam, Ningyuan Cao, Siddharth Joshi, Thomas Kämpfe, Moonyoung Jung, Kwangyou Seo, Kwangsoo Kim, Wanki Kim, Daewon Ha, Sourav Dutta, Abhronil Sengupta, Xiao Gong, Shimeng Yu, Vijaykrishnan Narayanan, Kai Ni

Abstract: Neuromorphic vision sensors require efficient real-time pattern recognition, yet conventional architectures struggle with energy and latency constraints. Here, we present a novel in-situ spatiotemporal sequence detector that leverages vertical NAND storage to achieve massively parallel pattern detection. By encoding each cell with two single-transistor-based multi-level cell (MLC) memory elements,… ▽ More Neuromorphic vision sensors require efficient real-time pattern recognition, yet conventional architectures struggle with energy and latency constraints. Here, we present a novel in-situ spatiotemporal sequence detector that leverages vertical NAND storage to achieve massively parallel pattern detection. By encoding each cell with two single-transistor-based multi-level cell (MLC) memory elements, such as ferroelectric field-effect transistors (FeFETs), and mapping a pixel's temporal sequence onto consecutive word lines (WLs), we enable direct temporal pattern detection within NAND strings. Each NAND string serves as a dedicated reference for a single pixel, while different blocks store patterns for distinct pixels, allowing large-scale spatial-temporal pattern recognition via simple direct bit-line (BL) sensing, a well-established operation in vertical NAND storage. We experimentally validate our approach at both the cell and array levels, demonstrating that vertical NAND-based detector achieves more than six orders of magnitude improvement in energy efficiency and more than three orders of magnitude reduction in latency compared to conventional CPU-based methods. These findings establish vertical NAND storage as a scalable and energy-efficient solution for next-generation neuromorphic vision processing. △ Less

Submitted 30 March, 2025; originally announced March 2025.

Comments: 26 pages, 7 figures

Medical Hallucinations in Foundation Models and Their Impact on Healthcare

Authors: Yubin Kim, Hyewon Jeong, Shan Chen, Shuyue Stella Li, Chanwoo Park, Mingyu Lu, Kumail Alhamoud, Jimin Mun, Cristina Grau, Minseok Jung, Rodrigo Gameiro, Lizhou Fan, Eugene Park, Tristan Lin, Joonsik Yoon, Wonjin Yoon, Maarten Sap, Yulia Tsvetkov, Paul Liang, Xuhai Xu, Xin Liu, Chunjong Park, Hyeonhoon Lee, Hae Won Park, Daniel McDuff , et al. (2 additional authors not shown)

Abstract: Hallucinations in foundation models arise from autoregressive training objectives that prioritize token-likelihood optimization over epistemic accuracy, fostering overconfidence and poorly calibrated uncertainty. We define medical hallucination as any model-generated output that is factually incorrect, logically inconsistent, or unsupported by authoritative clinical evidence in ways that could alt… ▽ More Hallucinations in foundation models arise from autoregressive training objectives that prioritize token-likelihood optimization over epistemic accuracy, fostering overconfidence and poorly calibrated uncertainty. We define medical hallucination as any model-generated output that is factually incorrect, logically inconsistent, or unsupported by authoritative clinical evidence in ways that could alter clinical decisions. We evaluated 11 foundation models (7 general-purpose, 4 medical-specialized) across seven medical hallucination tasks spanning medical reasoning and biomedical information retrieval. General-purpose models achieved significantly higher proportions of hallucination-free responses than medical-specialized models (median: 76.6% vs 51.3%, difference = 25.2%, 95% CI: 18.7-31.3%, Mann-Whitney U = 27.0, p = 0.012, rank-biserial r = -0.64). Top-performing models such as Gemini-2.5 Pro exceeded 97% accuracy when augmented with chain-of-thought prompting (base: 87.6%), while medical-specialized models like MedGemma ranged from 28.6-61.9% despite explicit training on medical corpora. Chain-of-thought reasoning significantly reduced hallucinations in 86.4% of tested comparisons after FDR correction (q < 0.05), demonstrating that explicit reasoning traces enable self-verification and error detection. Physician audits confirmed that 64-72% of residual hallucinations stemmed from causal or temporal reasoning failures rather than knowledge gaps. A global survey of clinicians (n = 70) validated real-world impact: 91.8% had encountered medical hallucinations, and 84.7% considered them capable of causing patient harm. The underperformance of medical-specialized models despite domain training indicates that safety emerges from sophisticated reasoning capabilities and broad knowledge integration developed during large-scale pre-training, not from narrow optimization. △ Less

Submitted 2 November, 2025; v1 submitted 25 February, 2025; originally announced March 2025.

Rapidly Built Medical Crash Cart! Lessons Learned and Impacts on High-Stakes Team Collaboration in the Emergency Room

Authors: Angelique Taylor, Tauhid Tanjim, Michael Joseph Sack, Maia Hirsch, Kexin Cheng, Kevin Ching, Jonathan St. George, Thijs Roumen, Malte F. Jung, Hee Rin Lee

Abstract: Designing robots to support high-stakes teamwork in emergency settings presents unique challenges, including seamless integration into fast-paced environments, facilitating effective communication among team members, and adapting to rapidly changing situations. While teleoperated robots have been successfully used in high-stakes domains such as firefighting and space exploration, autonomous robots… ▽ More Designing robots to support high-stakes teamwork in emergency settings presents unique challenges, including seamless integration into fast-paced environments, facilitating effective communication among team members, and adapting to rapidly changing situations. While teleoperated robots have been successfully used in high-stakes domains such as firefighting and space exploration, autonomous robots that aid highs-takes teamwork remain underexplored. To address this gap, we conducted a rapid prototyping process to develop a series of seemingly autonomous robot designed to assist clinical teams in the Emergency Room. We transformed a standard crash cart--which stores medical equipment and emergency supplies into a medical robotic crash cart (MCCR). The MCCR was evaluated through field deployments to assess its impact on team workload and usability, identified taxonomies of failure, and refined the MCCR in collaboration with healthcare professionals. Our work advances the understanding of robot design for high-stakes, time-sensitive settings, providing insights into useful MCCR capabilities and considerations for effective human-robot collaboration. By publicly disseminating our MCCR tutorial, we hope to encourage HRI researchers to explore the design of robots for high-stakes teamwork. △ Less

Submitted 25 February, 2025; originally announced February 2025.

Comments: 10 pages, 6 figures, HRI conference

RoToR: Towards More Reliable Responses for Order-Invariant Inputs

Authors: Soyoung Yoon, Dongha Ahn, Youngwon Lee, Minkyu Jung, HyungJoo Jang, Seung-won Hwang

Abstract: Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have been proposed to solve this issue, their success on practical listwise problems has been limited. In this work, as a first contribution, we identify and overcome two limitations to make zero-shot invariant LMs more practi… ▽ More Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have been proposed to solve this issue, their success on practical listwise problems has been limited. In this work, as a first contribution, we identify and overcome two limitations to make zero-shot invariant LMs more practical: (1) training and inference distribution mismatch arising from modifying positional ID assignments to enforce invariance, and (2) failure to adapt to mixture of order-invariant and sensitive inputs in practical listwise problems. Then, to overcome these issues we propose (1) RoToR, a zero-shot invariant LM for genuinely order-invariant inputs with minimal modifications of positional IDs, and (2) Selective Routing, an adaptive framework that handles both order-invariant and order-sensitive inputs in listwise tasks. On the Lost in the middle (LitM), Knowledge Graph QA (KGQA), and MMLU benchmarks, we show that RoToR with Selective Routing can effectively handle practical listwise input tasks in a zero-shot manner (https://github.com/soyoung97/RoToR) △ Less

Submitted 2 June, 2025; v1 submitted 10 February, 2025; originally announced February 2025.

Comments: Accepted at ACL 2025 main

GaRLIO: Gravity enhanced Radar-LiDAR-Inertial Odometry

Authors: Chiyun Noh, Wooseong Yang, Minwoo Jung, Sangwoo Jung, Ayoung Kim

Abstract: Recently, gravity has been highlighted as a crucial constraint for state estimation to alleviate potential vertical drift. Existing online gravity estimation methods rely on pose estimation combined with IMU measurements, which is considered best practice when direct velocity measurements are unavailable. However, with radar sensors providing direct velocity data-a measurement not yet utilized for… ▽ More Recently, gravity has been highlighted as a crucial constraint for state estimation to alleviate potential vertical drift. Existing online gravity estimation methods rely on pose estimation combined with IMU measurements, which is considered best practice when direct velocity measurements are unavailable. However, with radar sensors providing direct velocity data-a measurement not yet utilized for gravity estimation-we found a significant opportunity to improve gravity estimation accuracy substantially. GaRLIO, the proposed gravity-enhanced Radar-LiDAR-Inertial Odometry, can robustly predict gravity to reduce vertical drift while simultaneously enhancing state estimation performance using pointwise velocity measurements. Furthermore, GaRLIO ensures robustness in dynamic environments by utilizing radar to remove dynamic objects from LiDAR point clouds. Our method is validated through experiments in various environments prone to vertical drift, demonstrating superior performance compared to traditional LiDAR-Inertial Odometry methods. We make our source code publicly available to encourage further research and development. https://github.com/ChiyunNoh/GaRLIO △ Less

Submitted 21 February, 2025; v1 submitted 11 February, 2025; originally announced February 2025.

Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection

Authors: Minseok Jung, Cynthia Fuertes Panizo, Liam Dugan, Yi R., Fung, Pin-Yu Chen, Paul Pu Liang

Abstract: The advancement of large language models (LLMs) has made it difficult to differentiate human-written text from AI-generated text. Several AI-text detectors have been developed in response, which typically utilize a fixed global threshold (e.g., $θ= 0.5$) to classify machine-generated text. However, one universal threshold could fail to account for distributional variations by subgroups. For exampl… ▽ More The advancement of large language models (LLMs) has made it difficult to differentiate human-written text from AI-generated text. Several AI-text detectors have been developed in response, which typically utilize a fixed global threshold (e.g., $θ= 0.5$) to classify machine-generated text. However, one universal threshold could fail to account for distributional variations by subgroups. For example, when using a fixed threshold, detectors make more false positive errors on shorter human-written text, and more positive classifications of neurotic writing styles among long texts. These discrepancies can lead to misclassifications that disproportionately affect certain groups. We address this critical limitation by introducing FairOPT, an algorithm for group-specific threshold optimization for probabilistic AI-text detectors. We partitioned data into subgroups based on attributes (e.g., text length and writing style) and implemented FairOPT to learn decision thresholds for each group to reduce discrepancy. FairOPT showed notable discrepancy mitigation across nine detectors and three heterogeneous datasets, and the remarkable mitigation of the minimax problem by decreasing overall discrepancy 27.4% across five metrics while minimally sacrificing accuracy by 0.005%. Our framework paves the way for more robust classification in AI-generated content detection via post-processing. We release our data, code, and project information at URL. △ Less

Submitted 1 February, 2026; v1 submitted 6 February, 2025; originally announced February 2025.