Showing 1–50 of 501 results for author: Hong, D

AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement

Authors: Yizhe Chi, Wenyi Li, Deyao Hong, Xiaoqiu Wang, Mingju Gao, Kaisen Yang, Bingxiang He, Youjie Zheng, Calvin Xiao, Qinhuai Na

Abstract: Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement. That process is the training algorithm: a better objective or update rule improves the compute\mbox{-}capability exchange rate for every subsequent run, including the one that produces the next agent. Whether RSI is feasible therefore turns… ▽ More Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement. That process is the training algorithm: a better objective or update rule improves the compute\mbox{-}capability exchange rate for every subsequent run, including the one that produces the next agent. Whether RSI is feasible therefore turns on whether an agent can design training algorithms. No benchmark isolates that ability: existing suites are won by collecting data or by tuning hyperparameters, and none tells a change to how a run is executed apart from a change to how the model learns. We present AI4AI\mbox{-}Bench, 10 frozen research repositories spanning 10 training algorithm families. In each task, an agent has 4 hours on one B300 to rewrite the training algorithm; its code is then rerun from scratch for up to 12 hours and scored by a fixed evaluator hidden from the agent, against the repository's original algorithm under the same procedure. Because the 10 metrics are incommensurable, every task is mapped onto one scale on which $0$ is an uninformative model, $0.1$ is the algorithm the repository ships, and $1.0$ is the task optimum. Across 29 configurations of 6 systems on all 10 tasks the mean score is $0.166$, and the best system reaches $0.250$: even the strongest closes under a fifth of the distance between the algorithm that was already there and the optimum. The submissions show where that distance went: most never change how the model learns at all, and the minority that do average $0.226$ against $0.126$ for the rest. More reasoning effort mostly buys the willingness to go there, taking that minority from $8\%$ of submissions to $64\%$ and the mean score from $0.094$ to $0.196$. We release the task suite, the evaluators and every scored submission, so that the measurement can be repeated as these systems change. △ Less

Submitted 20 August, 2026; originally announced August 2026.

Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank

Authors: Shanwen Wang, Xin Sun, Danfeng Hong, Junyu Dong, Patrick Le Callet

Abstract: Although semi-supervised semantic segmentation ($\text{S}^4$) utilizes abundant unlabeled data to reduce manual labeling burdens, independent training of labeled and unlabeled data causes the former to dominate, which severely degrades pseudo-label quality. To address this challenges, we propose a novel remote sensing (RS) $\text{S}^4$ method via unified flow with feature memory bank (UFFM). Speci… ▽ More Although semi-supervised semantic segmentation ($\text{S}^4$) utilizes abundant unlabeled data to reduce manual labeling burdens, independent training of labeled and unlabeled data causes the former to dominate, which severely degrades pseudo-label quality. To address this challenges, we propose a novel remote sensing (RS) $\text{S}^4$ method via unified flow with feature memory bank (UFFM). Specifically, UFFM comprises two key innovations: unified flow (UF) and feature memory bank (FMB). The UF is a new training flow that generates less biased pseudo-labels by combining an external visual foundation model (VFM) with an RS domain teacher, and jointly optimizes labeled and pseudo-labeled data under a unified training objective. The FMB is a novel memory module for $\text{S}^4$ that dynamically updates class-specific features during training and reduces the feature discrepancy between labeled and unlabeled data through class-feature alignment. To verify the effectiveness of our model, we conduct extensive experiments on RS datasets. The experimental results show the superiority of our method over SOTA $\text{S}^4$ methods. Moreover, the results demonstrate the effectiveness of our contributions in bridging the optimization and feature representation gap between labeled and unlabeled data. Our code is released at \href{https://github.com/wangshanwen001/RS-UFFM}{https://github.com/wangshanwen001/RS-UFFM}. △ Less

Submitted 17 August, 2026; originally announced August 2026.

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

Authors: Zhengze Huang, Luyang Yu, Di Hong, Xinzhe Huang, Wanyu Lin, Zhixuan Chu, Zhan Qin, Tianhang Zheng

Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinct failure sources: reasoning hallucination, where flawed inference steps propagate to an incorrect conclusion, and knowledge hallucination, where the model lacks the requisite factual knowledge to answer the query. To ad… ▽ More Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinct failure sources: reasoning hallucination, where flawed inference steps propagate to an incorrect conclusion, and knowledge hallucination, where the model lacks the requisite factual knowledge to answer the query. To address reasoning hallucination, we propose REIN, an alignment framework that trains LRMs to produce a structured reasoning sequence, $\texttt{<think>} $$\rightarrow$ $\texttt{<reflection>} $$\rightarrow$ $\texttt{<answer>}$, enabling explicit self-reflection before committing to a final answer. To address knowledge hallucination, REIN introduces a reward mechanism that encourages explicit abstention (e.g., "I don't know") when none of the sampled reasoning chains yields a correct answer, allowing the model to refrain from unsupported predictions. Extensive evaluations on mathematical and commonsense reasoning benchmarks show that REIN consistently improves selective accuracy, reduces incorrect-but-self-endorsed responses, and maintains high coverage compared with competitive baselines. Notably, REIN achieves these gains within a single forward pass, without requiring process supervision, inference-time controllers, external search, or multi-round critiques. Experiments on multiple backbones show that REIN reduces the hallucination proxy by $58\sim72\%$ relative to the base models while maintaining $86\sim91\%$ average coverage, and improves selective accuracy on attempted questions by $6.6\sim14.2\%$. △ Less

Submitted 8 August, 2026; originally announced August 2026.

Comments: 26 pages and 22 figures

MIFA: An MILP-based Framework for Improving Differential Fault Attacks

Authors: Hanbeom Shin, Insung Kim, Sunyeop Kim, Byoungjin Seok, Deukjo Hong, Jaechul Sung, Seokhie Hong, Sangjin Lee, Dongjae Lee

Abstract: At ASIACRYPT 2021, Baksi et al. introduced DEFAULT, a block cipher designed to algorithmically resist Differential Fault Attack (DFA), claiming 64-bit DFA security regardless of the number of injected faults. At EUROCRYPT 2022, Nageler et al. demonstrated that DEFAULT's claimed DFA resistance can be broken by applying an information-combining technique. More recently, at ASIACRYPT 2024, Jana et al… ▽ More At ASIACRYPT 2021, Baksi et al. introduced DEFAULT, a block cipher designed to algorithmically resist Differential Fault Attack (DFA), claiming 64-bit DFA security regardless of the number of injected faults. At EUROCRYPT 2022, Nageler et al. demonstrated that DEFAULT's claimed DFA resistance can be broken by applying an information-combining technique. More recently, at ASIACRYPT 2024, Jana et al. improved DFA by searching for differential trails with a single solution. They showed that, for DEFAULT with a simple key schedule, injecting five faults at the fifth-to-last round reduces the key space to one, and for BAKSHEESH, injecting twelve faults at the third-to-last round achieves the same result. In this paper, we propose a new DFA framework that utilizes a Mixed-Integer Linear Programming (MILP) solver. This framework makes it possible to attack deeper rounds than previously achieved, reducing the number of fault injections required for key recovery. Furthermore, we present a method to determine the most efficient fault injection bit positions by systematically analyzing the input differences from all possible single bit-flip faults, thereby further reducing the required number of faults. This systematic analysis has the significant advantage of allowing us to theoretically calculate the required number of faults. Applying our framework, for DEFAULT, injecting three faults at the sixth-to-last round and two faults at the seventh- and eighth-to-last rounds reduces the key space to one. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: 24 pages, 2 figures

Journal ref: IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2026, No. 3, pp. 465-488, 2026

K-EXAONE 2.0 Technical Report

Authors: Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Ahra Jo, Hyunjik Jo, Yeonsik Jo, Minhyeok Jung, Doyoung Kim, Heegyu Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Byungoh Ko, Changhun Lee, Dohaeng Lee, Haeju Lee, Jinsik Lee, Kyungmin Lee, Minwoo Lee , et al. (52 additional authors not shown)

Abstract: This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yielding a Mixture-of-Experts (MoE) model with 750B total parameters and approximately 37B activated per token---more than thr… ▽ More This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yielding a Mixture-of-Experts (MoE) model with 750B total parameters and approximately 37B activated per token---more than three times the capacity of its predecessor. K-EXAONE 2.0 supports context lengths of up to 256K tokens and expands multilingual coverage from six to ten languages. Its training pipeline combines continual pre-training, difficulty-focused mid-training, and post-training to strengthen reasoning, agentic coding, multilingual capability, and safety grounded in Korean sociocultural contexts. Across nine evaluation categories selected to reflect the conditions of practical use, K-EXAONE 2.0 improves over K-EXAONE and remains competitive with open-weight models, showing its largest gains in agentic coding and long-context understanding and its clearest strengths in long-context retrieval and safety. Released under the Apache 2.0 license, K-EXAONE 2.0 enables the wider AI ecosystem to evaluate, deploy, adapt, and build upon it, while marking the beginning---rather than the endpoint---of our challenge toward the global frontier. △ Less

Submitted 5 August, 2026; originally announced August 2026.

A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models

Authors: Shu Quan, Tianfang Hao, Sitong Fang, He Geng, Jiayi Zhou, Boyuan Chen, Kaile Wang, Donghai Hong, Juntao Dai, Yaodong Yang, Jiaming Ji

Abstract: Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equally be prompted to generate predicted toxin-like sequences, potentially lowering the barrier to biological misuse. Current safety evaluations, however, operate in natural language and cannot determine whether a model-gene… ▽ More Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equally be prompted to generate predicted toxin-like sequences, potentially lowering the barrier to biological misuse. Current safety evaluations, however, operate in natural language and cannot determine whether a model-generated amino acid sequence is biological gibberish or a computational risk signal. To address this evaluation blind spot, we introduce SPIKE-Bench, coupling 631 curated toxin-design prompts across seven functional categories with the SPIKE funnel, a three-stage protocol that filters output through compliance, biological plausibility, and predicted toxicity, producing stage-level diagnostics and an aggregate function-aware metric: the Functional Harmfulness Rate (FHR). An audit of 32 LLMs reveals that most models freely comply with toxin-design requests; FHR is driven primarily by biological generation capability rather than safety alignment, reaching 50.7%; and Refusal Rate fails to predict functional risk. As a first step toward mitigation, we provide BioSafe-Guard, a domain-specialized classifier that substantially reduces predicted functional risk while preserving benign utility. We release SPIKE-Bench and BioSafe-Guard at https://github.com/PKU-Alignment/SPIKE-Bench to support more rigorous biosecurity evaluation of LLMs. △ Less

Submitted 5 August, 2026; v1 submitted 2 August, 2026; originally announced August 2026.

Comments: Accepted to COLM 2026. 40 pages, 9 figures

DexDirect: Direct Kinesthetic Arm Guidance for Efficient Dexterous Demonstration Collection

Authors: Beom Jun Kim, Shiu-Jen Wang, Jonathan Liu, Alvin Zhu, Quanyou Wang, Hanzhang Fang, Feng Xu, Mingzhang Zhu, Yuchen Cui, Dennis W. Hong

Abstract: Scalable collection of dexterous manipulation demonstrations remains a major bottleneck for robot learning. High-fidelity interfaces often require costly hardware and extensive setup, while low-setup, low cost alternatives tend to provide less precise control and impose greater cognitive workload on operators. We present DexDirect, a direct kinesthetic arm guidance for efficient dexterous demonstr… ▽ More Scalable collection of dexterous manipulation demonstrations remains a major bottleneck for robot learning. High-fidelity interfaces often require costly hardware and extensive setup, while low-setup, low cost alternatives tend to provide less precise control and impose greater cognitive workload on operators. We present DexDirect, a direct kinesthetic arm guidance for efficient dexterous demonstration collection. The operator drags a 6-DoF gravity-compensated robot arm directly by a handle, while a single webcam retargets operator's other hand onto a 16 joints 13-DoF dexterous robot hand. User studies suggest DexDirect collects 17.2x and 3.2x more successful demonstrations compared to purely vision (AnyTeleop) and pose-tracking (TeleDex) baselines. An adapted NASA-TLX shows DexDirect greatly reduces mental demand, effort, and frustration, despite raising physical demand. A diffusion policy trained on DexDirect demonstrations reaches a 90% success rate on a cube pick-and-place task. These results suggest that direct kinesthetic arm guidance combined with vision-based hand retargeting provides an efficient low-setup and scalable interface for collecting dexterous manipulation demonstrations △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: 8pages, 6 figures

The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape

Authors: Deyao Hong, Kehan Zheng, Qian Li, Jun Zhang, Jie Jiang, Hongning Wang

Abstract: Online recommendation has traditionally taken place after a user enters a platform, which determines the candidate pool and the ranking shown to the user. LLM-based user agents enable a different recommendation process: a user specifies a need before choosing a platform, leaving platforms to compete for the user's attention, which we refer to as an agentic recommendation market. In our controlled… ▽ More Online recommendation has traditionally taken place after a user enters a platform, which determines the candidate pool and the ranking shown to the user. LLM-based user agents enable a different recommendation process: a user specifies a need before choosing a platform, leaving platforms to compete for the user's attention, which we refer to as an agentic recommendation market. In our controlled LLM-based experiments across three product domains, we find this new setting of recommendation creates a tension between access and attention. Compared with traditional platform-centric recommendation, user-centric recommendation greatly expands the opportunity for relevant items to enter comparison; yet broader participation does not translate directly into effective exposure. Competition directly triggers platforms' strategic play: selectively positive explanations occupy 73--78% of first-ranked positions. When the user agent relates platforms' actions to subsequent user feedback, this share falls to 36--41%, while the chance of a user purchasing the relevant item increases. A user agent is therefore more than a ranker over a larger pool of candidates: its querying, ranking, and feedback mechanism governing who can compete, how scarce attention is allocated, and how earlier outcomes shape the evaluation of platforms directly affect user utility. Designing agentic recommendation therefore requires treating access, attention, and accountability as a joint mechanism design problem. △ Less

Submitted 29 July, 2026; v1 submitted 27 July, 2026; originally announced July 2026.

DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization

Authors: Wenping Yin, Ziqi Liu, Naixia Mou, Weijia Li, Danfeng Hong, Hao Li

Abstract: Social media imagery (SMI) provides timely and fine-grained ground perspectives that are valuable for situational awareness and emergency response. Unlike satellite or aerial imagery, SMI can capture disaster impacts and ground-level conditions in a timely manner. However, geographic references in SMI are often vague or ambiguous, making accurate geolocalization challenging. To address this issue,… ▽ More Social media imagery (SMI) provides timely and fine-grained ground perspectives that are valuable for situational awareness and emergency response. Unlike satellite or aerial imagery, SMI can capture disaster impacts and ground-level conditions in a timely manner. However, geographic references in SMI are often vague or ambiguous, making accurate geolocalization challenging. To address this issue, we propose DisasterTD, a disaster toponym disambiguation framework that integrates multimodal large language model (MLLMs)-based semantic reasoning with cross-view geolocalization. First, MLLMs extract toponyms and generate candidate geolocations from noisy textual inputs. Then, cross-view matching between SMI, remote sensing imagery (RSI), and optionally street-view imagery (SVI) is used to verify and refine these candidate results. We evaluate DisasterTD on the Hurricane Harvey dataset, where SMI is augmented with collected RSI and SVI to construct a cross-view benchmark for disaster geolocalization. The dataset is divided into four categories based on toponym clarity and ambiguity, allowing a fine-grained performance analysis across scenarios. Results show that DisasterTD consistently outperforms MLLM-only and cross-view-only baselines without disambiguation, achieving geolocalization accuracies of 71.62% within 1000 m, 62.36% within 500 m, 57.99% within 250 m, 52.09% within 100 m, and 47.01% within 50 m, while reducing the mean and median errors to 11.33 km and 0.68 km, respectively. The largest improvements appear in ambiguous toponyms, where semantic reasoning with cross-view evidence reduces candidate dispersion and errors. These findings demonstrate the effectiveness of integrating MLLM-based candidate generation with cross-view verification for fine-grained disaster geolocalization. △ Less

Submitted 25 July, 2026; originally announced July 2026.

A Cyclic Adaptation-Generalization Framework with Uncertainty-Guided Self-Paced Learning for Long-Term Brain-Machine Interfaces

Authors: Jiyu Wei, Di Hong, Zhanjie Zhang, Dazhong Rong, Qinming He, Yueming Wang

Abstract: Brain-Machine Interfaces (BMIs), which link the brain to external devices, hold great potential in rehabilitation, human performance augmentation, and human-centered robotics. However, invasive BMIs face a critical challenge for long-term deployment due to neural drift, which degrades decoding performance over time and necessitates frequent recalibration. Existing methods designed to mitigate neur… ▽ More Brain-Machine Interfaces (BMIs), which link the brain to external devices, hold great potential in rehabilitation, human performance augmentation, and human-centered robotics. However, invasive BMIs face a critical challenge for long-term deployment due to neural drift, which degrades decoding performance over time and necessitates frequent recalibration. Existing methods designed to mitigate neural drift typically rely on either domain adaptation (DA) or domain generalization (DG) alone and often fail to capture fine-grained distribution shifts across neural subdomains, resulting in limited performance. To overcome these limitations, we propose Uncertainty-guided Self-paced Cycling (UnSPC), a robust framework that synergizes DA and DG for target domain refining under an Uncertainty-guided Self-paced Pseudo-labeling (UnSPL) mechanism. To handle subdomain neural drift across domains, UNSPL is proposed to iteratively mine reliable pseudo-labeled samples with a noise-robust ranking strategy for further fine-tuning. Leveraging these high-quality samples, we introduce a novel Cycling Adaptation and Generalization (CycAG) strategy, which integrates DA and DG within an iterative cycle to progressively mitigate both global and subdomain drift. This cyclic process enables effective alignment to evolving target distributions while preserving robust and transferable representations, thereby mitigating performance degradation under long-term neural drifts. Extensive experiments on multiple neural decoding datasets demonstrate the effectiveness and robustness of UnSPC. To our knowledge, our proposed UnSPC is the first to cyclically integrate DA and DG with pseudo-labeling, paving the way toward stable long-term BMI controls. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Self-Supervised Consistency Enhanced Disentangled Learning for Neural Decoding Generalization in Brain-Machine Interface

Authors: Jiyu Wei, Di Hong, Zhanjie Zhang, Dazhong Rong, Qinming He, Yueming Wang

Abstract: Brain-Machine Interfaces (BMIs) provide a direct communication pathway between the brain and external devices, enabling humans to control assistive and robotic technologies, with potential applications in rehabilitation, human motor augmentation, and human-centered robotics. However, due to neural drift, the performance of BMIs decreases over time, posing challenges for long-term viability, partic… ▽ More Brain-Machine Interfaces (BMIs) provide a direct communication pathway between the brain and external devices, enabling humans to control assistive and robotic technologies, with potential applications in rehabilitation, human motor augmentation, and human-centered robotics. However, due to neural drift, the performance of BMIs decreases over time, posing challenges for long-term viability, particularly for invasive BMIs (iBMIs). Existing solutions suffer from two main drawbacks: (i) difficulty in learning robust neural representations, and (ii) neglecting that neural drift varies across motor parameters (e.g., velocity, direction, and speed). To overcome these limitations, we propose Self-Supervised Consistency enhanced Disentangled Learning (SSCDL), a neural decoding generalization framework built on two key innovations. We first design a backbone model named Consistency enhanced Neural Decoder (CND), using a novel teacher-student consistency constraint with simulated neural signal perturbations to learn robust representations invariant to neural drift. Then, we employ three dedicated CNDs under the Complementary-Disentangled Generalization (CDG) mechanism, which disentangles motor signals into velocity, direction, and speed with inspiration from neural preference theory. This disentangled learning enables SSCDL to capture invariant neural representations from diverse neural preference perspectives, significantly enhancing cross-day generalization. Extensive experimental results show that SSCDL delivers state-of-the-art decoding performance, exhibiting high robustness and cross-day stability. These capabilities underscore its strong potential for long-term interaction in human-centric robotic and fine-grained assistive applications. △ Less

Submitted 27 July, 2026; originally announced July 2026.

The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

Authors: Xiang Chen, Hao Li, Jiangxin Dong, Jinshan Pan, Xin Li, Hongbo Ding, Junpeng Jiang, Xingyu Qiu, Yilian Zhong, Yuxiang Chen, Shibo Yin, Zixuan Huang, Yushun Fang, Xilei Zhu, Yahui Wang, Chen Lu, Xiaodong Zhou, Qingyue Cao, Changwei Gong, Jingyun Liu, Xingchen Yi, Hansen Shi, Ruiyi Liu, Jirui Xie, Tao Liu , et al. (67 additional authors not shown)

Abstract: This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common benchmark for evaluating the restoration accuracy, robustness, and generalization capability of models across multiple deg… ▽ More This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common benchmark for evaluating the restoration accuracy, robustness, and generalization capability of models across multiple degradation categories within a unified framework. The competition attracted 158 registered participants, and 20 teams were included in the final ranking after their submitted results were successfully reproduced and verified. This report provides a comprehensive analysis of the submitted solutions and corresponding results, highlighting recent advances in real-world all-in-one image restoration. The summarized methods and empirical findings reveal effective design strategies and establish an updated benchmark for future research in real-world low-level vision. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: ECCV 2026 Workshops; https://lowlevelcv.com/

RAVEN: Reinforcement-Adaptive Visibility-Graph Planning for Robust Humanoid Navigation with Collision-Free MPC

Authors: Ruochen Hou, Shiqi Wang, Beom Jun Kim, Hanzhang Fang, Mehak Singal, Dennis W. Hong

Abstract: Humanoid navigation in dynamic environments requires long-horizon planning while respecting short-horizon dynamic and safety constraints. Classical visibility-graph planners combined with model predictive control (MPC) can efficiently generate collision-free trajectories, but their performance depends on manually tuned parameters and accurate system modeling. In real robotic systems, control delay… ▽ More Humanoid navigation in dynamic environments requires long-horizon planning while respecting short-horizon dynamic and safety constraints. Classical visibility-graph planners combined with model predictive control (MPC) can efficiently generate collision-free trajectories, but their performance depends on manually tuned parameters and accurate system modeling. In real robotic systems, control delays, state-estimation noise, and locomotion uncertainties can cause overshoot and constraint violations even when the nominal path is geometrically optimal. We propose RAVEN, a hierarchical reinforcement learning (RL)-MPC framework for robust humanoid navigation. Unlike prior approaches that use learning to tune cost weights or replace planning entirely, RAVEN employs RL to adapt the geometric construction of a visibility-graph planner by modifying obstacle inflation and related graph parameters. By directly reshaping the free-space geometry, the learned planner alters the topology of the global path to compensate for delay and tracking imperfections. A collision-free MPC layer then tracks the planned trajectory while explicitly enforcing velocity bounds and obstacle-avoidance constraints. By training under realistic delays and observation noise, RAVEN learns planning adaptations that improve robustness while retaining explicit long-horizon geometric planning and constrained optimization, in contrast to end-to-end learning approaches. We evaluate RAVEN against a manually tuned visibility-graph MPC baseline and a pure RL navigation policy. Results demonstrate reduced overshoot near obstacles, improved robustness in narrow passages, and more reliable navigation under delay and noise. These findings indicate that reinforcement-adaptive graph construction combined with constrained MPC provides an effective and interpretable alternative to end-to-end learning for robust humanoid navigation. △ Less

Submitted 17 July, 2026; originally announced July 2026.

DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment

Authors: Zefeng Wu, Weiwei Qi, Jielong Chen, Tianhang Zheng, Di Hong, Chaochao Lu, Liang He, Zhan Qin, Kui Ren

Abstract: Fine-tuning large language models (LLMs) on domain-specific datasets has become a standard paradigm for adapting LLMs to specialized applications. However, recent work has shown that even fine-tuning on benign task-specific data can substantially weaken the safety capabilities of LLMs. While existing efforts have made progress in identifying data responsible for safety degradation, they usually re… ▽ More Fine-tuning large language models (LLMs) on domain-specific datasets has become a standard paradigm for adapting LLMs to specialized applications. However, recent work has shown that even fine-tuning on benign task-specific data can substantially weaken the safety capabilities of LLMs. While existing efforts have made progress in identifying data responsible for safety degradation, they usually rely on a single mean vector computed over a specific model with its tokenizer to represent the safety direction, which limits both the effectiveness and transferability of their risk assessment measures. To address these limitations, we propose DataShield, a data assessment framework that identifies risky fine-tuning samples and response segments through consensus subspace alignment over joint safety-critical semantic spaces derived from multiple safety-aligned LLMs. Within these spaces, DataShield extracts consensus safe and unsafe subspaces using semantic spectral decomposition over safe and unsafe data representations. The risk of a data sample or segment is then estimated by measuring its relative alignment with the unsafe and safe subspaces, enabling both sample-level filtering and fine-grained segment-level masking. Compared with state-of-the-art filtering and masking baselines, DataShield reduces ASR by 14.6\% with sample filtering and 32.3\% with segment masking, while preserving downstream utility and avoiding target-model-specific risk computation. △ Less

Submitted 16 July, 2026; originally announced July 2026.

Comments: 24 pages, 12 figures, 19 tables

MIDAS Hand: Modular low-Impedance Direct-drive Anthropomorphic Sensing Hand

Authors: Alvin Zhu, Mingzhang Zhu, Beom Jun Kim, Quanyou Wang, Jose Victor S. H. Ramos, Dennis Hong

Abstract: Dexterous manipulation is limited not only by algorithms but by a shortage of accessible hand hardware that combines human-scale morphology, ease of manufacturing or maintenance, tactile sensing, and practical cost. Existing dexterous hands tend to optimize some of these properties at the expense of others. We present MIDAS Hand, a low-cost, open-source, human-scale dexterous hand with integrated… ▽ More Dexterous manipulation is limited not only by algorithms but by a shortage of accessible hand hardware that combines human-scale morphology, ease of manufacturing or maintenance, tactile sensing, and practical cost. Existing dexterous hands tend to optimize some of these properties at the expense of others. We present MIDAS Hand, a low-cost, open-source, human-scale dexterous hand with integrated tactile sensing for manipulation research. MIDAS Hand provides 16 total degrees of freedom (DoF) with 13 active DoF, directly driven actuation with measurably low backdrive torque, and 283 three-axis tactile taxels in a compact 700 g package with a bill of materials under 3,000 USD. Built from 3D-printed components, it assembles in under three hours while providing the strength, repeatability, and maintainability needed for repeated real-world experiments. Alongside the hardware, we release a full stack: design files, build documentation, control and tactile Python APIs, simulation models, and retargeting and teleoperation pipelines. We characterize MIDAS Hand through workspace and grasp-taxonomy analysis, payload and reliability tests, backdrivability measurements, and teleoperation demonstrations with tactile sensing, showing that it offers a balanced, reproducible platform for tactile dexterous manipulation and human-to-robot data collection. Project page: https://midas-hand.com △ Less

Submitted 15 July, 2026; originally announced July 2026.

EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation

Authors: Dexiang Hong, Yijie Guo, Weidong Chen, Xinyan Liu, Zixuan Zou, Zhendong Mao, Yongdong Zhang

Abstract: Emotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion. In this challenge, the main difficulty is that the visual and affective attributes available in the training data are not explicitly provided at test time. Without these attributes, the generator has to decide not only what to depict, but also how… ▽ More Emotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion. In this challenge, the main difficulty is that the visual and affective attributes available in the training data are not explicitly provided at test time. Without these attributes, the generator has to decide not only what to depict, but also how the target emotion should be expressed through color, lighting, brushwork, composition, line, and layout. This creates a control gap between the available test prompt and the fine-grained conditions needed for emotion-aware artistic generation. To bridge this gap, we propose EmoStyle, a Z-Image-based framework that converts the input prompt into a structured generation state. An LLM reasoner first predicts affective cues (valence-arousal, dominant emotion, and therapeutic-effect labels) and an aspect-ratio decision. Instead of using these predictions only as additional prompt text, we encode the affective fields into an affective condition vector and inject it into the denoising blocks through AdaLN-style modulation. This allows the inferred control variables to directly guide the generation of intermediate features. Since emotional expression is also style-dependent, we further train a dedicated LoRA adapter for each artistic style bucket and select the corresponding expert during inference, enabling the same affective cues to be rendered with bucket-specific priors for color, texture, brushwork, and composition. Finally, a lightweight VLM-guided candidate selection step ranks the generated images based on prompt alignment, style consistency, emotional expression, and visual quality. In Track 1 of the AffectiveArt Challenge 2026, our USTC\_PI\_LAB\_TEAM submission achieved first place. △ Less

Submitted 11 July, 2026; originally announced July 2026.

Impedance-Guided Programmable Transmission of Localized Deformation in Modular Soft Metamaterials

Authors: Weiyun Xu, Daewon Hong, Zhi Zhao, Rahul Dev Kundu, Xiaojia Shelly Zhang

Abstract: Soft metamaterials provide a promising platform for robotics, biomedical devices, and flexible electronics. The localized mechanical responses by nonuniform excitation are ubiquitous in soft materials, yet their controlled transmission across assemblies remains largely overlooked in metamaterial design, which critically constrains nontrivial functionalities with end-to-end and long-range deformati… ▽ More Soft metamaterials provide a promising platform for robotics, biomedical devices, and flexible electronics. The localized mechanical responses by nonuniform excitation are ubiquitous in soft materials, yet their controlled transmission across assemblies remains largely overlooked in metamaterial design, which critically constrains nontrivial functionalities with end-to-end and long-range deformation transmission. Here, we introduce an impedance-guided design framework that enables programmable transmission of localized deformation in modular soft metamaterials, achieving behaviors unattainable by intuitive design. By establishing a nonlinear model considering position-dependent interactions and integrating the concept of mechanical impedance within metamaterials, we regulate assembly-level transmission solely through unit-cell topology optimization. The resulting framework enables effective synthesis of module families, allowing both homogeneous and heterogeneous assemblies to be custom-built with markedly enhanced transmission characteristics. Leveraging the highly combinatorial and extensible design space, we physically realize diverse on-demand displacement manipulation architectures, including obstacle-bypassing modular soft-metamaterial assemblies, defect-tolerant soft gripping, and embodied signal processing. Beyond deformation programming, the reconfigurability and reassemblability of these soft modules can embed electric logic signals, enabling energy-efficient and low-latency information processing through compliant-switch-controlled mechanical LED displays and wearable finger-motion-sensing controllers. Our method provides fundamental insights into localized deformation transmission in modular soft metamaterials and establishes a scalable route toward embodied-intelligence material systems, particularly for soft-metamaterial-centric actuation, sensing, and collective computing. △ Less

Submitted 9 July, 2026; originally announced July 2026.

From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills

Authors: David Boram Hong, Aaron Imani, Iftekhar Ahmed

Abstract: Agent Skills provide on-demand domain knowledge to LLM agents without requiring model retraining. Each Agent Skill is defined by a mandatory SKILL$.$md file containing metadata and an unstructured Markdown body whose contents are left entirely to the skill author. Despite the rapid adoption of Agent Skills, little is known about how these files are authored or whether existing authoring guidelines… ▽ More Agent Skills provide on-demand domain knowledge to LLM agents without requiring model retraining. Each Agent Skill is defined by a mandatory SKILL$.$md file containing metadata and an unstructured Markdown body whose contents are left entirely to the skill author. Despite the rapid adoption of Agent Skills, little is known about how these files are authored or whether existing authoring guidelines are followed in practice. In this paper, we present the first systematic study of SKILL$.$md files as a software artifact. We qualitatively analyze 238 real-world skills and derive a taxonomy of 13 higher-level and 44 lower-level semantic components. We then conduct a multivocal literature review of 29 sources to identify best practices for authoring SKILL$.$md files and introduce skill smells as violations of these practices. Finally, we develop an automated detector and apply it to real-world skills, finding that over 99% of SKILL$.$md files contain at least one skill smell, and once introduced, skill smells rarely disappear as skills evolve. These findings reveal a substantial gap between recommended and actual authoring practices, motivating the development of automated techniques to remediate skill smells while increasing developer awareness of this emerging quality issue. △ Less

Submitted 3 July, 2026; v1 submitted 1 July, 2026; originally announced July 2026.

ATRIA: Adaptive Traceable ECG Reporting with Iterative Agents

Authors: Donggyun Hong, Kyuhwan Lee, Junmyung Kwon, Yong-Yeon Jo

Abstract: Existing ECG report generation is tightly coupled -- interpretation and reporting fused end-to-end, so errors propagate without stage-level recourse -- while agent-based systems decouple tasks but remain single-pass, never revisiting earlier outputs. Clinical ECG reporting instead unfolds iteratively, requiring progressive context integration and bidirectional editing. We present \textsc{ATRIA}, a… ▽ More Existing ECG report generation is tightly coupled -- interpretation and reporting fused end-to-end, so errors propagate without stage-level recourse -- while agent-based systems decouple tasks but remain single-pass, never revisiting earlier outputs. Clinical ECG reporting instead unfolds iteratively, requiring progressive context integration and bidirectional editing. We present \textsc{ATRIA}, a multi-agent ECG reporting system that mirrors the clinician's iterative workflow: it binds every report claim to its supporting evidence, flags statements unsupported by that evidence, incorporates additional context mid-session, and lets clinicians verify and revise individual findings rather than accept one opaque output. Because its agents use ECG analysis models already in clinical use, the underlying findings are clinically trustworthy; and as a cloud-based web service, \textsc{ATRIA} is ready for immediate deployment. We demonstrate \textsc{ATRIA} through four interaction cases, with a live demo and video available. △ Less

Submitted 30 June, 2026; v1 submitted 23 June, 2026; originally announced June 2026.

Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models

Authors: Dongbin Na, Chanwoo Kim, Soonbin Rho, Giyun Choi, Gangbok Lee, Dooyoung Hong

Abstract: This work addresses spatial question answering for service robots traversing long egocentric routes. Given a query such as "where can I find a dry cleaner on the way back home?", the system returns a metric coordinate that downstream navigation components can act on. Prior Spatial Question Answering approaches leverage retrieval-augmented agents built on closed-source models such as GPT-4o for pat… ▽ More This work addresses spatial question answering for service robots traversing long egocentric routes. Given a query such as "where can I find a dry cleaner on the way back home?", the system returns a metric coordinate that downstream navigation components can act on. Prior Spatial Question Answering approaches leverage retrieval-augmented agents built on closed-source models such as GPT-4o for path exploration. However, robots operating in the real world often cannot reliably depend on online closed-source models due to network instability, communication latency, and deployment cost. It creates a need for open-source based Spatial Question Answering approaches that can run onboard the robot, yet prior research in this direction remains limited. This work proposes BinTrack, a simple yet effective, fully open-source spatial-localization agent that leverages the temporal ordering of a robot's trajectory. BinTrack performs a binary search over the trajectory segments between two anchor landmarks identified from a query. It improves overall accuracy by up to 22.8% over other open-source implementations and even matches the reported closed-source model result on the global category of the SpaceLocQA benchmark, the most challenging setting that has so far required strong reasoning agents such as GPT-4o. Furthermore, its optimized inference strategy consistently yields more than a 1.5x inference speedup over previous approaches. Finally, this work releases GangnamLoop, a novel and practical multi-trip outdoor benchmark collected by deploying a real quadruped robot on public streets with the anonymization policy. It revisits the same locations under different outdoor conditions and pairs the robot's low viewpoint with the human owner's. The source codes and datasets are publicly available at https://github.com/ndb796/BinaryTracking △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: 21 pages, 4 figures, 15 tables. Project page: https://ndb796.github.io/BinaryTracking ; Code and dataset: https://github.com/ndb796/BinaryTracking

ACM Class: I.2.9; I.2.10; I.2.7

Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization

Authors: Dongbin Na, Chanwoo Kim, Giyun Choi, Dooyoung Hong

Abstract: Detecting unanswerable user queries remains essential for the reliable deployment of real-world embodied agents. However, modern vision-language models (VLMs) often generate overly confident answers even when the available visual memory cannot support the query. Such overconfidence poses various task-dependent risks. The agent may provide misleading information to the user in Embodied Question Ans… ▽ More Detecting unanswerable user queries remains essential for the reliable deployment of real-world embodied agents. However, modern vision-language models (VLMs) often generate overly confident answers even when the available visual memory cannot support the query. Such overconfidence poses various task-dependent risks. The agent may provide misleading information to the user in Embodied Question Answering and select an arbitrary coordinate and physically guide the user there in spatial reasoning for navigation. Despite these high stakes, only a few prior studies directly address when and how an embodied VLM should respond with "I do not know." This work proposes Semantic Flip, a simple yet effective framework that synthesizes auxiliary out-of-distribution (OOD) samples for embodied refusal without requiring external OOD annotations. The key idea is to independently transform the query and video memory to construct auxiliary OOD pairs that lack sufficient visual grounding. These synthesized pairs enable training a lightweight rejection module on top of a frozen pretrained VLM. The module attaches to any existing VLM-based pipeline without retraining the underlying model. Across two complementary benchmarks, Semantic Flip consistently outperforms strong prompting baselines. This work also introduces SpaceReject, a new refusal benchmark for spatial localization with deliberately unanswerable queries over long video memory, where Semantic Flip achieves an $F_1$ score of 0.9559. The source codes and datasets are publicly available at https://github.com/ndb796/SemanticFlip. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: 18 pages, 3 figures. Code and data: https://github.com/ndb796/SemanticFlip ; project page: https://ndb796.github.io/SemanticFlip

ACM Class: I.2.9; I.2.10; I.2.7; I.2.6

Resonant scattering in two-flavored Sp(4) lattice gauge theories

Authors: Ed Bennett, Yannick Dengler, Deog Ki Hong, Ho Hsiao, Jong-Wan Lee, C. -J. David Lin, Biagio Lucini, Axel Maas, Maurizio Piai, Davide Vadacchino, Fabian Zierler

Abstract: We apply Lüscher's method to the vector channel of the scattering amplitude of Pseudo-Nambu-Goldstone-Bosons (PNGBs), in the $Sp(4)$ lattice gauge theory coupled to $N_f=2$ flavors of Wilson-Dirac fundamental fermions. We generalize existing algorithms and numerical implementations of the method, to adapt them to this prominent candidate for the completion of proposed extensions of the Standard Mo… ▽ More We apply Lüscher's method to the vector channel of the scattering amplitude of Pseudo-Nambu-Goldstone-Bosons (PNGBs), in the $Sp(4)$ lattice gauge theory coupled to $N_f=2$ flavors of Wilson-Dirac fundamental fermions. We generalize existing algorithms and numerical implementations of the method, to adapt them to this prominent candidate for the completion of proposed extensions of the Standard Model (SM). We present the first ab initio measurements of key properties of the vector resonances in the theory, including the coupling to the PNGBs, that are relevant to direct and indirect new physics searches, both for composite Higgs models (CHMs), as well as for strongly interacting massive particle (SIMP) realizations of dark matter. We also present a global update of the spectroscopy of the mesons in the theory, improving both the statistics and analysis systematics in respect to previous lattice measurements reported in the literature. △ Less

Submitted 12 June, 2026; originally announced June 2026.

Comments: 43 pages, 14 figures, 12 tables

Report number: CTPU-PTC-26-13, TUM-EFT 218/26

Revisiting the Axial Anomaly and Chiral Magnetic Effect in Dense Matter, with Applications to Axion Dark Matter

Authors: Deog Ki Hong

Abstract: We explicitly compute the axial anomaly in dense matter and show that its form remains unchanged from that in vacuum, even in the massless limit. This result follows from a subtle cancellation in the anomalous Ward identity between the medium-induced contributions to the divergence of the axial current and to the pseudoscalar density. We then revisit the chiral magnetic effect in a fermionic mediu… ▽ More We explicitly compute the axial anomaly in dense matter and show that its form remains unchanged from that in vacuum, even in the massless limit. This result follows from a subtle cancellation in the anomalous Ward identity between the medium-induced contributions to the divergence of the axial current and to the pseudoscalar density. We then revisit the chiral magnetic effect in a fermionic medium coupled to an axial chemical potential under an external magnetic field. We show that the medium supports a persistent, conserved anomalous current carried by fermions. The current is determined by the axial chemical potential and suppressed by the Fermi velocity, in agreement with anomalous axial-current correlation functions. We finally discuss applications to axion physics, where axion dark matter acts as an effective axial chemical potential. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Comments: 26 pages, 4 figures

Report number: PNUTP-26/A01

Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual Captioning

Authors: Zihan Meng, Dexiang Hong, Weidong Chen, Ziyu Zhou, Bo Hu, Zhendong Mao

Abstract: Audio-visual captioning generates natural language descriptions from video and audio content. Multimodal LLMs have advanced this task, but both modalities contribute many tokens to the LLM input, where prefill self-attention scales quadratically. Existing token-pruning methods usually retain tokens by attention, saliency, or cross-entropy loss, yet the hard threshold selection makes it difficult t… ▽ More Audio-visual captioning generates natural language descriptions from video and audio content. Multimodal LLMs have advanced this task, but both modalities contribute many tokens to the LLM input, where prefill self-attention scales quadratically. Existing token-pruning methods usually retain tokens by attention, saliency, or cross-entropy loss, yet the hard threshold selection makes it difficult to retain tokens that are truly valuable, especially for high-confusing tokens near the decision boundary. To this end, we propose a AVEX-Prune, an RL-based audio-visual dynamic token pruning method in this work. In our AVEX-Prune, an audio-visual token exchange strategy is proposed to select truly valuable tokens by replacing low-confidence retained tokens with high-confidence candidate tokens from the same or the other modality, and measuring the differences in caption generation from token swaps. AVEX-Prune preserves full-token quality at a 40% retention ratio on both VILA 1.5-8B (54.5 vs. 54.6) and VideoLLaMA 2 (57.0 vs. 56.8). △ Less

Submitted 9 June, 2026; originally announced June 2026.

Constrained Paraphrase Consistency for LLM Hallucination Detection

Authors: Shanshan Lin, Dongsheng Hong, Sibo Ju, Chao Chen, Xi Zhang, Xiangwen Liao

Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors. Prior work largely enlarges training sets via synthesis or new annotations, introducing increasing cost and potential bias while underusing the consistency implied by semantically equivalent paraphrases. We propose Consistency-Constrained Hallucination Detector (CCHD),… ▽ More Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors. Prior work largely enlarges training sets via synthesis or new annotations, introducing increasing cost and potential bias while underusing the consistency implied by semantically equivalent paraphrases. We propose Consistency-Constrained Hallucination Detector (CCHD), which formulates training as a constrained optimization problem. The standard cross-entropy on original document-claim pairs is complemented by (i) paraphrase-consistency constraints bounding divergence across paraphrased views, and (ii) label-preservation constraints tying paraphrases to ground truth. We solve the problem by gradient descent-ascent over model parameters and per-view Lagrange multipliers, adding only a few scalar dual variables and no inference-time overhead. With DeBERTa and Flan-T5 backbones, CCHD consistently outperforms strong baselines (FactCG, MiniCheck, and AlignScore) on standard factuality benchmarks, demonstrating its superiority on hallucination detection. △ Less

Submitted 6 June, 2026; originally announced June 2026.

Comments: Accepted to ICASSP 2026

Cross Paraphrastic Invariance Learning for Hallucination Detection

Authors: Shanshan Lin, Dongsheng Hong, Sibo Ju, Chao Chen, Sihong Xie, Xiangwen Liao

Abstract: Large language models (LLMs) frequently generate hallucinations, which are unsupported by a source document. To avoid costly LLM-as-evaluator pipelines and the heavy annotation demands of existing classifiers, we propose CPIL (Cross Paraphrastic Invariance Learning), a two-stage Siamese framework that maximizes the utility of existing labeled data. Concretely, CPIL constructs informative training… ▽ More Large language models (LLMs) frequently generate hallucinations, which are unsupported by a source document. To avoid costly LLM-as-evaluator pipelines and the heavy annotation demands of existing classifiers, we propose CPIL (Cross Paraphrastic Invariance Learning), a two-stage Siamese framework that maximizes the utility of existing labeled data. Concretely, CPIL constructs informative training pairs by: (i) generating paraphrastic views of each document-claim example as positives, and explicitly aligning their representations to enforce invariance to surface form; and (ii) mining same-document, opposite-label pairs as hard negatives to sharpen document-sensitive decision boundaries. Then CPIL conduct a two-stage model training: Stage 1 performs contrastive pretraining to learn a paraphrase-invariant, grounding-aware embedding space; and Stage 2 attaches a lightweight classifier for binary groundedness. On the LLM-AggreFact benchmark (11 tasks), CPIL surpasses strong baselines concerning F1 scores with only ~1% labeled data, showing its prediction superiority and label efficiency. △ Less

Submitted 6 June, 2026; originally announced June 2026.

Comments: Accepted to ICASSP 2026

Rapid co-design of Buoyancy-assisted robots for Challenging Locomotion using Gaussian Evolutionary Specialists

Authors: Ankit Sinha, Nitish Sontakke, Dennis Hong, Yusuke Tanaka, Sehoon Ha

Abstract: Designing high-performance legged robots requires jointly optimizing morphology and control. Model-free Reinforcement Learning (RL) offers an alternative to model-predictive control for developing robust controllers without explicitly specifying robot dynamics. Thus, we have seen theuse of RL to train controllers and evaluate designs for robot morphology optimization. While RL has shown success in… ▽ More Designing high-performance legged robots requires jointly optimizing morphology and control. Model-free Reinforcement Learning (RL) offers an alternative to model-predictive control for developing robust controllers without explicitly specifying robot dynamics. Thus, we have seen theuse of RL to train controllers and evaluate designs for robot morphology optimization. While RL has shown success inlocomotion, using it in the co-design inner loop is expensive due to repeated policy training. Universal policies conditioned on morphology offer a promising alternative, but suffer from behavioral diversity collapse, converging to a single strategy that performs sub-optimally across designs. On the other hand, end-to-end Mixture-of-Experts (MoE) architectures fail due to a collapse in its representation. We propose Gaussian Evolutionary Specialists (GES), a framework that decouples design-space partitioning from policy learning to capture diverse behaviors explicitly. GES assigns specialist policies to evolving Gaussian regions and iteratively refines them via training, probing, and territory expansion. The resulting specialists are integrated into a design sampling loop, replacing costly re-training with direct evaluation. When tested on the Buoyancy-Assisted Light Legged Unit (BALLU), GES discovers designs with 5 - 25% higher performance than naive universal policies. On hardware, a GES optimized design overcomes a 24 cm tall obstacle - 3x improvement over the baseline BALLU design. Moreover, GES curtails design optimization time by 37%. △ Less

Submitted 5 June, 2026; originally announced June 2026.

Comments: Submitted to RA-L

MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment

Authors: Dang Nguyen Hong, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham

Abstract: Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse. To address this, we introduce MIC, a framework that optimizes the geometric landscape of multi-granular embeddings through isotropic subspace alignment. MIC employs Soft Collapse Regularization (SCR) to mitigate redundancy between pref… ▽ More Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse. To address this, we introduce MIC, a framework that optimizes the geometric landscape of multi-granular embeddings through isotropic subspace alignment. MIC employs Soft Collapse Regularization (SCR) to mitigate redundancy between prefix and residual subspaces via cross-correlation penalties, alongside Spectral Isotropy Regularization (SIR) to ensure hyper-spherical uniformity in low-dimensional prefixes. By unifying these strategies through a self-distillation objective, MIC generates semantically dense representations that maintain high discriminative power. Our experiments demonstrate that MIC significantly outperforms standard baselines, particularly in high-compression scenarios where maintaining informational capacity is most critical. △ Less

Submitted 31 May, 2026; v1 submitted 28 May, 2026; originally announced May 2026.

Comments: Accepted at the GlobalSouthML Workshop at ICML 2026. 8 pages, 2 figures

EVL-ECG: Efficient ECG Interpretation With Multi-Aspect Heterogeneous Knowledge Distillation

Authors: Dang Nguyen Hong, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham

Abstract: High-fidelity ECG interpretation is increasingly reliant on massive foundation models, yet their deployment in clinical edge-care remains hindered by extreme computational demands. While knowledge distillation (KD) is a promising solution, traditional methods fail to capture the complex spatio-temporal dependencies of ECG signals when transferring knowledge across heterogeneous architectures. In t… ▽ More High-fidelity ECG interpretation is increasingly reliant on massive foundation models, yet their deployment in clinical edge-care remains hindered by extreme computational demands. While knowledge distillation (KD) is a promising solution, traditional methods fail to capture the complex spatio-temporal dependencies of ECG signals when transferring knowledge across heterogeneous architectures. In this paper, we propose EVL-ECG, a framework specifically designed for cross-architecture distillation of cardiac diagnostic logic. EVL-ECG introduces three ECG-aware innovations: (1) Multi-Head Cross-Attention Alignment, which harmonizes architectural discrepancies to preserve fine-grained morphological features; (2) Optimal Transport-based Visual Feature Matching, utilizing optimal transport to maintain global structural relationships across ECG leads despite mismatched token representations; and (3) Geometric Intra-Architecture Relation Matching, which distills the latent diagnostic reasoning of the teacher model. Evaluations across ECG benchmarks demonstrate that EVL-ECG yields improvements of up to 2.4% AUC and 1.1% clinical accuracy over existing baselines. Notably, EVL-ECG establishes an efficient 2B-parameter ECG foundation model, suitable for resource-constrained clinical environments. △ Less

Submitted 31 May, 2026; v1 submitted 28 May, 2026; originally announced May 2026.

Comments: 7Accepted at the SD4H Workshop at ICML 2026. 7 pages, 3 figures

TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering

Authors: Liying Han, Kang Yang, Oliver Wang, Jason Wu, Pengrui Quan, Gaofeng Dong, Ozan Baris Mulayim, Sizhe Ma, Yuyang Yuan, Dezhi Hong, Mario Berges, Mani Srivastava

Abstract: Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-only QA, TSQA requires models to ground answers in temporal signals whose patterns may occur at different scales, specific time locations, or across separated intervals. However, existing benchmarks are typically organized by task types or high-level r… ▽ More Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-only QA, TSQA requires models to ground answers in temporal signals whose patterns may occur at different scales, specific time locations, or across separated intervals. However, existing benchmarks are typically organized by task types or high-level reasoning categories, making it difficult to diagnose the underlying signal-level capabilities driving model performance. We introduce TS-Skill, a controlled benchmark for evaluating three composable analytical skills in TSQA: temporal scale selection (SK1), temporal localization (SK2), and cross-interval integration (SK3). TS-Skill provides timestamp-aware questions, broad domain coverage, and human-validated QA quality. To construct the benchmark at scale, we develop SKEvol, a skill-guided agentic framework that combines domain-aware time-series seed generation, skill-controlled question generation, metadata- and code-assisted answer construction, multi-phase signal-grounded verification, and human-in-the-loop curation. Experiments on ten state-of-the-art LLMs and TSLMs reveal substantial and uneven capability gaps across SK1-SK3. In particular, SK3 remains consistently challenging for non-agent models, whereas tool-augmented agents show a selective advantage on standalone SK3. These findings demonstrate that skill-level evaluation can uncover temporal reasoning failures that are obscured by aggregate TSQA scores. △ Less

Submitted 23 May, 2026; originally announced May 2026.

CLUE: Adaptively Prioritized Contextual Cues by Leveraging a Unified Semantic Map for Effective Zero-Shot Object-Goal Navigation

Authors: Taeyun Kim, Alvin Jinsung Choi, Dasol Hong, Hyun Myung

Abstract: Zero-shot object-goal navigation (ZSON) is a challenging problem in robotics that requires a comprehensive understanding of both language and visual observations. Contextual cues from rooms and objects are critical, but their relative importance depends on the target: some objects are strongly tied to specific room types, while others are better predicted by nearby co-located objects. Existing met… ▽ More Zero-shot object-goal navigation (ZSON) is a challenging problem in robotics that requires a comprehensive understanding of both language and visual observations. Contextual cues from rooms and objects are critical, but their relative importance depends on the target: some objects are strongly tied to specific room types, while others are better predicted by nearby co-located objects. Existing methods overlook this distinction, leading to inefficient and inaccurate exploration. We present CLUE, a novel navigation framework that adaptively balances the use of contextual rooms and objects by leveraging commonsense knowledge extracted from an offline large language model (LLM). By estimating a target's association with room types using LLM, the agent prioritizes room cues for predictable objects and object cues for those with weak room associations. Our framework constructs a unified semantic value map that integrates both types of contextual information, adaptively weighted by the target's ambiguity to guide exploration. Combined with multi-viewpoint verification and an exploration strategy informed by contextual cues, CLUE achieves robust and efficient navigation. Extensive experiments in simulation and real-world deployments show that our method consistently outperforms state-of-the-art baselines in both success rate (SR) and success weighted by path length (SPL), demonstrating its effectiveness and practicality for real-world navigation tasks. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: 8 pages, 5 figures

CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers

Authors: Weidong Chen, Dexiang Hong, Zhendong Mao, Yutao Cheng, Xinyan Liu, Lei Zhang, Yongdong Zhang

Abstract: Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing graphic design parsing methods typically rely on multi-stage pipelines combining layout prediction, matting, and inpainting, which suffer from error accumulation… ▽ More Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing graphic design parsing methods typically rely on multi-stage pipelines combining layout prediction, matting, and inpainting, which suffer from error accumulation and limited controllability. We propose a hybrid generative framework for raster-to-layer graphic design parsing that decomposes a design image into editable text, background, and sticker layers. Text regions are parsed using a vision-language model into a text rendering protocol, enabling faithful reconstruction and flexible re-editing, while background and sticker layers are generated using a multi-branch diffusion architecture with RGBA support. We further introduce ParserReward and integrate it with Group Relative Policy Optimization to align generation quality with human design preferences. Extensive experiments on two challenging datasets, \emph{i.e.,} the Parser-40K and Crello datasets, demonstrate superior performance over existing methods, \emph{eg.,} achieving an overall average improvement of 23.7\% across all metrics. △ Less

Submitted 14 July, 2026; v1 submitted 21 April, 2026; originally announced April 2026.

English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training

Authors: Mehak Dhaliwal, Shashwat Chaurasia, Yao Qin, Dezhi Hong, Thomas Butler

Abstract: Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of the interplay between training language coverage, model scale, and task domain, based on 220 supervised fine-tuning runs on parallel translated multilingual data… ▽ More Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of the interplay between training language coverage, model scale, and task domain, based on 220 supervised fine-tuning runs on parallel translated multilingual data mixtures spanning mathematical reasoning and API calling tasks, with models up to 8B parameters. We find that increasing language coverage during post-training is largely beneficial across tasks and model scales, with low-resource languages benefiting the most and high-resource languages plateauing rather than degrading. Even minimal multilinguality helps: incorporating a single non-English language improves both English performance and cross-lingual generalization, making English-only post-training largely suboptimal. Moreover, at sufficient language diversity, zero-shot cross-lingual transfer can match or exceed the effects of direct language inclusion in a low-diversity setting, although gains remain limited for typologically distant, low-resource languages. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks

Authors: Yuangang Li, Justin Tian Jin Chen, Ethan Yu, David Hong, Iftekhar Ahmed

Abstract: Large language models (LLMs) increasingly rely on explicit reasoning to solve coding tasks, yet evaluating the quality of this reasoning remains challenging. Existing reasoning evaluators are not designed for coding, and current benchmarks focus primarily on code generation, leaving other coding tasks largely unexplored. We introduce CodeRQ-Bench, the first benchmark for evaluating LLM reasoning q… ▽ More Large language models (LLMs) increasingly rely on explicit reasoning to solve coding tasks, yet evaluating the quality of this reasoning remains challenging. Existing reasoning evaluators are not designed for coding, and current benchmarks focus primarily on code generation, leaving other coding tasks largely unexplored. We introduce CodeRQ-Bench, the first benchmark for evaluating LLM reasoning quality across three coding task categories: generation, summarization, and classification. Using this benchmark, we analyze 1,069 mismatch cases from existing evaluators, identify five recurring limitations, and derive four design insights for reasoning evaluation in coding tasks. Guided by these insights, we propose VERA, a two-stage evaluator that combines evidence-grounded verification with ambiguity-aware score correction. Experiments on CodeRQ-Bench show that VERA consistently outperforms strong baselines across four datasets, improving AUCROC by up to 0.26 and AUPRC by up to 0.21. We release CodeRQ-Bench at https://github.com/MrLYG/CodeRQ-Bench, supporting future investigations. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization

Authors: Yizhe Chi, Deyao Hong, Dapeng Jiang, Tianwei Luo, Kaisen Yang, Boshi Zhang, Zhe Cao, Xiaoyan Fan, Bingxiang He, Han Hao, Weiyang Jin, Dianqiao Lei, Qingle Liu, Houde Qian, Bowen Wang, Situ Wang, Youjie Zheng, Yifan Zhou, Calvin Xiao, Eren Cai, Qinhuai Na

Abstract: Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization -- an iterative propose-execute-ev… ▽ More Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization -- an iterative propose-execute-evaluate loop in which an agent generates candidate artifacts, receives executable verifier feedback, and revises them under a fixed interaction budget -- spanning $47$ tasks across five broad engineering categories. Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers that provide continuous reward signals and enforce hard feasibility constraints under constrained budgets. We evaluate eight frontier language models using representative search frameworks, finding that while GPT 5.4 achieves the most robust performance, the benchmark remains challenging for all models. Our analysis suggests a dual power-law decay in improvement frequency ($\sim$ 1/iteration) and magnitude ($\sim$ 1/improvement count). We further show that although width improves parallelism and diversity, depth remains crucial for hard-won improvements under a fixed budget. Frontier-Eng establishes a new standard for assessing the capacity of AI agents to integrate domain knowledge with executable feedback to solve complex, open-ended engineering problems. △ Less

Submitted 27 April, 2026; v1 submitted 14 April, 2026; originally announced April 2026.

Symetra: Visual Analytics for the Parameter Tuning Process of Symbolic Execution Engines

Authors: Donghee Hong, Minjong Kim, Sooyoung Cha, Jaemin Jo

Abstract: Symbolic execution engines such as KLEE automatically generate test cases to maximize branch coverage, but their numerous parameters make it difficult to understand the parameters' impact, leading the user to rely on suboptimal default configurations. While automated tuners have shown promising results, they provide limited insights into why certain configurations work well, motivating the need fo… ▽ More Symbolic execution engines such as KLEE automatically generate test cases to maximize branch coverage, but their numerous parameters make it difficult to understand the parameters' impact, leading the user to rely on suboptimal default configurations. While automated tuners have shown promising results, they provide limited insights into why certain configurations work well, motivating the need for Human-in-the-Loop approaches. In this work, we present a visual analytics system, Symetra, designed to support Human-in-the-Loop parameter tuning of symbolic execution engines. To handle a large number of parameters and their configurations, we provide two complementary overviews of their impact on branch coverage values and patterns. Building on these overviews, our system enables collective analysis, allowing the user to contrast groups of configurations and identify differences that may affect branch coverage. We also report on case studies and a Human-in-the-Loop tuning process, demonstrating that experts not only interpreted parameter impacts and identified complementary configurations, but also improved upon fully automated approaches in both branch coverage and tuning efficiency. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Lattice studies of chimera baryons in Sp(4) gauge theory

Authors: Jong-Wan Lee, Ed Bennett, Luigi Del Debbio, Niccolò Forzano, Ryan C. Hill, Deog Ki Hong, Ho Hsiao, C. -J. David Lin, Biagio Lucini, Alessandro Lupo, Maurizio Piai, Davide Vadacchino, Fabian Zierler

Abstract: We study chimera baryons, fermion bound states composed of two (hyper)quarks transforming in the fundamental and one in the antisymmetric representation of a non-Abelian gauge group. While in QCD they coincide with ordinary baryons, in composite Higgs models (CHMs) with top partial compositeness, spin-1/2 chimera baryons serve as partners of the top quark and are responsible for its large mass. We… ▽ More We study chimera baryons, fermion bound states composed of two (hyper)quarks transforming in the fundamental and one in the antisymmetric representation of a non-Abelian gauge group. While in QCD they coincide with ordinary baryons, in composite Higgs models (CHMs) with top partial compositeness, spin-1/2 chimera baryons serve as partners of the top quark and are responsible for its large mass. We perform non-perturbative lattice calculations of the low-lying spectrum of the chimera baryons, in a specific realization of CHMs based on a Sp(4) gauge theory. In the quenched approximation, we present the numerical results in the continuum and massless limits. Then, for dynamical fermions, we measure the spectrum and matrix elements by employing a newly developed spectral density analysis for several choices of the lattice parameters. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Comments: 4 pages, 4 figures, Proceedings of the 2025 International Conference on the Structure of Baryons (Baryons 2025), 10-14 Nov. 2025, Jeju, South Korea

Report number: CTPU-PTC-26-12, TUM-EFT 211/26

Smart Transfer: Leveraging Vision Foundation Model for Rapid Building Damage Mapping with Post-Earthquake VHR Imagery

Authors: Hao Li, Liwei Zou, Wenping Yin, Gulsen Taskin, Naoto Yokoya, Danfeng Hong, Wufan Zhao

Abstract: Living in a changing climate, human society now faces more frequent and severe natural disasters than ever before. As a consequence, rapid disaster response during the "Golden 72 Hours" of search and rescue becomes a vital humanitarian necessity and community concern. However, traditional disaster damage surveys routinely fail to generalize across distinct urban morphologies and new disaster event… ▽ More Living in a changing climate, human society now faces more frequent and severe natural disasters than ever before. As a consequence, rapid disaster response during the "Golden 72 Hours" of search and rescue becomes a vital humanitarian necessity and community concern. However, traditional disaster damage surveys routinely fail to generalize across distinct urban morphologies and new disaster events. Effective damage mapping typically requires exhaustive and time-consuming manual data annotation. To address this issue, we introduce Smart Transfer, a novel Geospatial Artificial Intelligence (GeoAI) framework, leveraging state-of-the-art vision Foundation Models (FMs) for rapid building damage mapping with post-earthquake Very High Resolution (VHR) imagery. Specifically, we design two novel model transfer strategies: first, Pixel-wise Clustering (PC), ensuring robust prototype-level global feature alignment; second, a Distance-Penalized Triplet (DPT), integrating patch-level spatial autocorrelation patterns by assigning stronger penalties to semantically inconsistent yet spatially adjacent patches. Extensive experiments and ablations from the recent 2023 Turkiye-Syria earthquake show promising performance in multiple cross-region transfer settings, namely Leave One Domain Out (LODO) and Specific Source Domain Combination (SSDC). Moreover, Smart Transfer provides a scalable, automated GeoAI solution to accelerate building damage mapping and support rapid disaster response, offering new opportunities to enhance disaster resilience in climate-vulnerable regions and communities. The data and code are publicly available at https://github.com/ai4city-hkust/SmartTransfer. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Adapt as You Say: Online Interactive Bimanual Skill Adaptation via Human Language Feedback

Authors: Zhuo Li, Dianxi Li, Tao Teng, Quentin Rouxel, Zhipeng Dong, Dennis Hong, Darwin Caldwell, Fei Chen

Abstract: Developing general-purpose robots capable of autonomously operating in human living environments requires the ability to adapt to continuously evolving task conditions. However, adapting high-dimensional coordinated bimanual skills to novel task variations at deployment remains a fundamental challenge. In this work, we present BiSAIL (Bimanual Skill Adaptation via Interactive Language), a novel fr… ▽ More Developing general-purpose robots capable of autonomously operating in human living environments requires the ability to adapt to continuously evolving task conditions. However, adapting high-dimensional coordinated bimanual skills to novel task variations at deployment remains a fundamental challenge. In this work, we present BiSAIL (Bimanual Skill Adaptation via Interactive Language), a novel framework that enables zero-shot online adaptation of offline-learned bimanual skills through interactive language feedback. The key idea of BiSAIL is to adopt a hierarchical reason-then-modulate paradigm, which first infers generalized adaptation objectives from multimodal task variations, and then adapts bimanual motions via diffusion modulation to achieve the inferred objectives. Extensive real-robot experiments across six bimanual tasks and two dual-arm platforms demonstrate that BiSAIL significantly outperforms existing methods in human-in-the-loop adaptability, task generalization and cross-embodiment scalability. This work enables the development of adaptive bimanual assistants that can be flexibly customized by non-expert users via intuitive verbal corrections. Experimental videos and code are available at https://rip4kobe.github.io/BiSAIL/. △ Less

Submitted 27 March, 2026; originally announced March 2026.

Comments: 11 pages, 15 figures, submitted to IEEE TMECH

Locating isolas in nonlinear oscillator systems using uncertainty quantification

Authors: Dongxiao Hong, David A. W. Barton, Simon A. Neild

Abstract: Parametric uncertainty in nonlinear dynamical systems can fundamentally alter bifurcation behaviour, leading to qualitative response changes. Predicting operating margins/envelopes under such uncertainties is critical but challenging: conventional uncertainty quantification (UQ) methods struggle to efficiently propagate uncertainties across bifurcation boundaries, where response gradients become s… ▽ More Parametric uncertainty in nonlinear dynamical systems can fundamentally alter bifurcation behaviour, leading to qualitative response changes. Predicting operating margins/envelopes under such uncertainties is critical but challenging: conventional uncertainty quantification (UQ) methods struggle to efficiently propagate uncertainties across bifurcation boundaries, where response gradients become singular and solution branches emerge/vanish. We present a general UQ framework for bifurcation analysis of nonlinear dynamical systems with proportional parametric uncertainty, which systematically integrates continuation methods with parametric sensitivities and extremal conditions. The approach uses a two-step scheme: first, the loci of extremal response points are traced as the uncertainty domain is expanded from a deterministic reference point; second, these extremal points are tracked as the bifurcation parameter varies, thus determining the maximum and minimum response margins throughout. The continuation problem scales linearly with the number of uncertain parameters, enabling efficient analysis. The method is demonstrated on a two-degree-of-freedom nonlinear oscillator exhibiting a range of bifurcation phenomena, including multiple solutions, modal interactions, and symmetry breaking. In all cases, the framework efficiently captures uncertainty-induced shifts in bifurcation boundaries and response margins. Notably, the method reveals that parametric uncertainty induces topological changes in the bifurcation structure, including the emergence of an isolated response branch that is absent in the deterministic system with the reference parameters. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Comments: 20 pages, 9 figures, to be published in the Proceedings of the Royal Society A

Beam Test Characterization of Silicon Microstrip Detector Flight-Model Ladders for the AMS-02 Upgrade

Authors: Dexing Miao, Giovanni Ambrosi, Mattia Barbanera, Baasansuren Batsukh, Hengyi Cai, Mengke Cai, Xudong Cai, Yuman Cai, Yuan-Hann Chang, Shanzhen Chen, Hsin-Yi Chou, Xingzhu Cui, Mingyi Dong, Matteo Duranti, Ke Gong, Mingjie Feng, Valerio Formato, Yisheng Fu, Daojin Hong, Maria Ionica, Xiaojie Jiang, Yaozu Jiang, Liangchenglong Jin, Shengjie Jin, Vladimir Koutsenko , et al. (34 additional authors not shown)

Abstract: The AMS-02 experiment plans to install a new silicon microstrip tracker layer (Layer-0) on top of the existing detector, increasing the cosmic-ray acceptance by a factor of 3. Layer-0 employs a design in which multiple silicon microstrip detectors (SSDs) are connected in series to form long detector ladders. We present a detailed performance study of the flight-model ladders using a 350~GeV mixed… ▽ More The AMS-02 experiment plans to install a new silicon microstrip tracker layer (Layer-0) on top of the existing detector, increasing the cosmic-ray acceptance by a factor of 3. Layer-0 employs a design in which multiple silicon microstrip detectors (SSDs) are connected in series to form long detector ladders. We present a detailed performance study of the flight-model ladders using a 350~GeV mixed hadron beam at the CERN SPS. The study focuses on the following aspects: (i) the performance of ladders with different numbers of SSDs, for which the intrinsic spatial resolution at normal incidence varies from $9.5~μ\mathrm{m}$ to $11.4~μ\mathrm{m}$ for ladders composed of 8 to 12 SSDs; (ii) the response consistency for particles impacting on the \emph{Head} and \emph{Tail} regions of the ladder; and (iii) the dependence of the detector performance on the particle incidence angle. △ Less

Submitted 26 March, 2026; originally announced March 2026.

A Telescope System for Charge and Position Measurement of High Energy Nuclei

Authors: Dexing Miao, Zhiyu Xiang, Giovanni Ambrosi, Mattia Barbanera, Baasansuren Batsukh, Mengke Cai, Xudong Cai, Yuan-Hann Chang, Shanzhen Chen, Hsin-Yi Chou, Xingzhu Cui, Mingyi Dong, Matteo Duranti, Ke Gong, Mingjie Feng, Valerio Formato, Daojin Hong, Maria Ionica, Xiaojie Jiang, Yaozu Jiang, Liangchenglong Jin, Shengjie Jin, Vladimir Koutsenko, Tiange Li, Zuhao Li , et al. (21 additional authors not shown)

Abstract: A high-granularity telescope system with a large sensitive area and low material budget has been developed for high-energy heavy ion beam tests. The telescope consists of nine layers of silicon microstrip detectors (SSDs), whose performance was validated through a heavy ion beam test at the CERN SPS. A hybrid machine learning algorithm is proposed to address the challenges of nuclear charge measur… ▽ More A high-granularity telescope system with a large sensitive area and low material budget has been developed for high-energy heavy ion beam tests. The telescope consists of nine layers of silicon microstrip detectors (SSDs), whose performance was validated through a heavy ion beam test at the CERN SPS. A hybrid machine learning algorithm is proposed to address the challenges of nuclear charge measurement with SSDs. The system achieves a spatial resolution of $\mathcal{O}(1) \,$\SI{}{\micro\metre} and a charge resolution better than 0.16 charge units for nuclei from $Z = 1$ to $Z = 29$, with a sensitive area of $8 \times 8 \, \mathrm{cm}^2$. To the best of our knowledge, this represents the most precise charge and spatial resolution simultaneously achieved by a silicon telescope to date. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Vector-channel scattering of dark particles in a Sp(4) gauge theory

Authors: Jong-Wan Lee, Ed Bennett, Yannick Dengler, Deog Ki Hong, Ho Hsiao, C. -J. David Lin, Biagio Lucini, Axel Maas, Maurizio Piai, Davide Vadacchino, Fabian Zierler

Abstract: We report new results obtained in our lattice studies of the $Sp(4)$ gauge theory coupled to two fundamental Dirac fermions. This theory provides a candidate for the dynamical origin of dark matter models within the strongly interacting massive particle paradigm. We employ Lüscher's formalism to analyse finite-volume energy levels and study the scattering amplitude of two pseudoscalar states in th… ▽ More We report new results obtained in our lattice studies of the $Sp(4)$ gauge theory coupled to two fundamental Dirac fermions. This theory provides a candidate for the dynamical origin of dark matter models within the strongly interacting massive particle paradigm. We employ Lüscher's formalism to analyse finite-volume energy levels and study the scattering amplitude of two pseudoscalar states in the spin-1 channel. We present our preliminary findings for a set of ensembles generated within a broad range of (Wilson) fermion masses. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: 10 pages, 3 figures, 1 table, Proceedings of the 42nd International Symposium on Lattice Field Theory (LATTICE2025), 2-8 Nov. 2025, Mumbai, India

Report number: CTPU-PTC-26-08, TUM-EFT 206/26

MOSS-TTS Technical Report

Authors: Yitian Gong, Botian Jiang, Yiwei Zhao, Yucheng Yuan, Kuangwei Chen, Yaozhou Jiang, Cheng Chang, Dong Hong, Mingshu Chen, Ruixiao Li, Yiyang Zhang, Yang Gao, Hanfu Chen, Ke Chen, Songlin Wang, Xiaogui Yang, Yuqian Zhang, Kexin Huang, ZhengYuan Lin, Kang Yu, Ziqi Chen, Jin Wang, Zhaoye Fei, Qinyuan Cheng, Shimin Li , et al. (1 additional authors not shown)

Abstract: This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators:… ▽ More This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models. △ Less

Submitted 20 March, 2026; v1 submitted 18 March, 2026; originally announced March 2026.

Comments: Project page: https://github.com/OpenMOSS/MOSS-TTS

DexEXO: A Wearability-First Dexterous Exoskeleton for Operator-Agnostic Demonstration and Learning

Authors: Alvin Zhu, Mingzhang Zhu, Beom Jun Kim, Jose Victor S. H. Ramos, Yike Shi, Yufeng Wu, Raayan Dhar, Fuyi Yang, Ruochen Hou, Hanzhang Fang, Quanyou Wang, Yuchen Cui, Dennis W. Hong

Abstract: Scaling dexterous robot learning is constrained by the difficulty of collecting high-quality demonstrations across diverse operators. Existing wearable interfaces often trade comfort and cross-user adaptability for kinematic fidelity, while embodiment mismatch between demonstration and deployment requires visual post-processing before policy training. We present DexEXO, a wearability-first hand ex… ▽ More Scaling dexterous robot learning is constrained by the difficulty of collecting high-quality demonstrations across diverse operators. Existing wearable interfaces often trade comfort and cross-user adaptability for kinematic fidelity, while embodiment mismatch between demonstration and deployment requires visual post-processing before policy training. We present DexEXO, a wearability-first hand exoskeleton that aligns visual appearance, contact geometry, and kinematics at the hardware level. DexEXO features a pose-tolerant thumb mechanism and a slider-based finger interface analytically modeled to support hand lengths from 140~mm to 217~mm, reducing operator-specific fitting and enabling scalable cross-operator data collection. A passive hand visually matches the deployed robot, allowing direct policy training from raw wrist-mounted RGB observations. User studies demonstrate improved comfort and usability compared to prior wearable systems. Using visually aligned observations alone, we train diffusion policies that achieve competitive performance while substantially simplifying the end-to-end pipeline. These results show that prioritizing wearability and hardware-level embodiment alignment reduces both human and algorithmic bottlenecks without sacrificing task performance. Project Page: https://dexexo-research.github.io/ △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: https://dexexo-research.github.io/

E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction

Authors: Yunsoo Kim, Changki Sung, Dasol Hong, Hyun Myung

Abstract: The emergence of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS) has advanced novel view synthesis (NVS). These methods, however, require high-quality RGB inputs and accurate corresponding poses, limiting robustness under real-world conditions such as fast camera motion or adverse lighting. Event cameras, which capture brightness changes at each pixel with high temporal resolution a… ▽ More The emergence of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS) has advanced novel view synthesis (NVS). These methods, however, require high-quality RGB inputs and accurate corresponding poses, limiting robustness under real-world conditions such as fast camera motion or adverse lighting. Event cameras, which capture brightness changes at each pixel with high temporal resolution and wide dynamic range, enable precise sensing of dynamic scenes and offer a promising solution. However, existing event-based NVS methods either assume known poses or rely on depth estimation models that are bounded by their initial observations, failing to generalize as the camera traverses previously unseen regions. We present E2EGS, a pose-free framework operating solely on event streams. Our key insight is that edge information provides rich structural cues essential for accurate trajectory estimation and high-quality NVS. To extract edges from noisy event streams, we exploit the distinct spatio-temporal characteristics of edges and non-edge regions. The event camera's movement induces consistent events along edges, while non-edge regions produce sparse noise. We leverage this through a patch-based temporal coherence analysis that measures local variance to extract edges while robustly suppressing noise. The extracted edges guide structure-aware Gaussian initialization and enable edge-weighted losses throughout initialization, tracking, and bundle adjustment. Extensive experiments on both synthetic and real datasets demonstrate that E2EGS achieves superior reconstruction quality and trajectory accuracy, establishing a fully pose-free paradigm for event-based 3D reconstruction. △ Less

Submitted 15 March, 2026; originally announced March 2026.

Comments: 10 pages, 6 figures, accepted to CVPR 2026

VIRD: View-Invariant Representation through Dual-Axis Transformation for Cross-View Pose Estimation

Authors: Juhye Park, Wooju Lee, Dasol Hong, Changki Sung, Youngwoo Seo, Dongwan Kang, Hyun Myung

Abstract: Accurate global localization is critical for autonomous driving and robotics, but GNSS-based approaches often degrade due to occlusion and multipath effects. As an emerging alternative, cross-view pose estimation predicts the 3-DoF camera pose corresponding to a ground-view image with respect to a geo-referenced satellite image. However, existing methods struggle to bridge the significant viewpoin… ▽ More Accurate global localization is critical for autonomous driving and robotics, but GNSS-based approaches often degrade due to occlusion and multipath effects. As an emerging alternative, cross-view pose estimation predicts the 3-DoF camera pose corresponding to a ground-view image with respect to a geo-referenced satellite image. However, existing methods struggle to bridge the significant viewpoint gap between the ground and satellite views mainly due to limited spatial correspondences. We propose a novel cross-view pose estimation method that constructs view-invariant representations through dual-axis transformation (VIRD). VIRD first applies a polar transformation to the satellite view to facilitate horizontal correspondence, then uses context-enhanced positional attention on the ground and polar-transformed satellite features to mitigate vertical misalignment, explicitly bridging the viewpoint gap. To further strengthen view invariance, we introduce a view-reconstruction loss that encourages the derived representations to reconstruct the original and cross-view images. Experiments on the KITTI and VIGOR datasets demonstrate that VIRD outperforms the state-of-the-art methods without orientation priors, reducing median position and orientation errors by 50.7% and 76.5% on KITTI, and 18.0% and 46.8% on VIGOR, respectively. △ Less

Submitted 22 March, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

Comments: Accepted to CVPR 2026

MiNI-Q: A Miniature, Wire-Free Quadruped with Unbounded, Independently Actuated Leg Joints

Authors: Daniel Koh, Suraj Shah, Yufeng Wu, Dennis Hong

Abstract: Physical joint limits are common in legged robots and can restrict workspace, constrain gait design, and increase the risk of hardware damage. This paper introduces MiNI-Q^2, a miniature, wire-free quadruped robot with independently actuated, mechanically unbounded 2-DOF leg joints. We present the mechanical design, kinematic analysis, and experimental validation of the proposed robot. The leg mec… ▽ More Physical joint limits are common in legged robots and can restrict workspace, constrain gait design, and increase the risk of hardware damage. This paper introduces MiNI-Q^2, a miniature, wire-free quadruped robot with independently actuated, mechanically unbounded 2-DOF leg joints. We present the mechanical design, kinematic analysis, and experimental validation of the proposed robot. The leg mechanism enables both oscillatory gaits and rotary locomotion while allowing the robot to fold to a minimum height of 2.5 cm. Experimentally, MiNI-Q achieves speeds up to 0.46 m/s and demonstrates low-clearance crawling, stair climbing, inverted locomotion, jumping, and backflipping. The wire-free architecture extends our previous Q8bot design, improving assembly reliability at miniature scale. All mechanical and electrical design files are released open source to support reproducibility and further research. △ Less

Submitted 31 May, 2026; v1 submitted 12 March, 2026; originally announced March 2026.

Comments: 7 pages, 11 figures. Submitted to the IEEE RAS Conference on Ubiquitous Robots (UR 2026)

Timing-Aware Satellite Association for Multi-LEO Direct-to-Handset Communications

Authors: Hyunwoo Lee, Incheol Hwang, Daesik Hong

Abstract: The rapid deployment of large-scale low Earth orbit (LEO) satellite constellations has positioned direct-to-handset (D2H) communications as a key enabler of future non-terrestrial networks. However, the limited link budget of handheld devices makes broadband service delivery challenging, and multi-satellite cooperative transmission is often required to provide sufficient power gain. In practice, s… ▽ More The rapid deployment of large-scale low Earth orbit (LEO) satellite constellations has positioned direct-to-handset (D2H) communications as a key enabler of future non-terrestrial networks. However, the limited link budget of handheld devices makes broadband service delivery challenging, and multi-satellite cooperative transmission is often required to provide sufficient power gain. In practice, such cooperation is severely hindered by asynchronous reception across satellites. This paper analyzes the received-signal model under the 3rd Generation Partnership Project (3GPP) transmitter structure and shows that satellite-dependent propagation delays prevent simultaneous timing alignment for multiple user terminals (UTs). This timing mismatch induces severe inter-carrier interference (ICI) and inter-symbol interference (ISI), even from the intended signals, which fundamentally constrains the achievable cooperative gain. To address this issue, we propose a timing-aware satellite association strategy that enables cooperation only with satellites expected to satisfy a UT-side timing tolerance, thereby avoiding dominant asynchronous interference by design. Simulation results demonstrate that the proposed strategy improves throughput performance compared to single-satellite transmission and fully connected multi-satellite baselines. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Comments: 13 pages, 10 figures, 1 table

BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop

Authors: Chao Chen, Xujia Li, Dongsheng Hong, Shanshan Lin, Xiangwen Liao, Chuanyi Liu, Lei Chen

Abstract: The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient due to the extensive expert knowledge required to annotate graph data. In this context, Few-Shot Graph Learning (FSGL) approaches have been developed over the years. Through sophisticated neural architectures and customize… ▽ More The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient due to the extensive expert knowledge required to annotate graph data. In this context, Few-Shot Graph Learning (FSGL) approaches have been developed over the years. Through sophisticated neural architectures and customized training pipelines, these approaches enhance model adaptability to new label distributions. However, compromises in \textcolor{black}{the model's} robustness and interpretability can result in overfitting to noise in labeled data and degraded performance. This paper introduces the first explanation-in-the-loop framework for the FSGL problem, called BAED. We novelly employ the belief propagation algorithm to facilitate label augmentation on graphs. Then, leveraging an auxiliary graph neural network and the gradient backpropagation method, our framework effectively extracts explanatory subgraphs surrounding target nodes. The final predictions are based on these informative subgraphs while mitigating the influence of redundant information from neighboring nodes. Extensive experiments on seven benchmark datasets demonstrate superior prediction accuracy, training efficiency, and explanation quality of BAED. As a pioneer, this work highlights the potential of the explanation-based research paradigm in FSGL. △ Less

Submitted 2 March, 2026; originally announced March 2026.

Comments: Accepted to Neural Networks 2026