Computer Vision
SeMoCo: A Semantic-First Motion Codec for Motion Language Modeling
Tianlv Huang, Hetian Guo, Ziyi Cai et al. (+6 more)
Discrete motion representations have substantially advanced autoregressive text-to-motion generation. However, most motion tokenizers are optimized for reconstruction and do not explicitly allocate capacity according to semantic role. Action-level meaning and fine-grained kinematic detail must therefore be encoded through the same reconstruction-driven hierarchy. We introduce SeMoCo, a semantic-first motion codec, together with a dual-axis motion generator for
language-conditioned motion generation. Each motion
token contains one semantic
token and a residual sequence of kinematic
tokens. The generator models semantic progression across time and autoregressively refines the residual entries. We also construct $\Omega$-MotionVerse, a large-scale, multi-source human-motion
dataset unified under the SOMA representation. Across the reported comparisons, SeMoCo achieves the best reconstruction accuracy among the compared codecs, while strong text-to-motion results demonstrate the effectiveness of its motion
tokens for downstream generation.
Read the full abstract ▾
All authors Tianlv Huang, Hetian Guo, Ziyi Cai, Song Wang, Yanping Zhang, Zipei Fan, Xuan Song, Guangming Wu, Xin Zheng
Human-Computer Interaction
How Do Professional Editors Evaluate the Editing Quality of AI-Generated Cinematic Video Ads?
Po-Ming Law, Weizhi Li and Arpit Narechania
On social media, we often encounter short-form
video ads that employ cinematic editing techniques to evoke an emotional response. While AI tools are beginning to generate such cinematic ads automatically, we lack a fine-grained framework for evaluating these ads. In this paper, we first characterize social media
video ad formats and identify cinematic ads as a recurring format in our corpus. We then analyze the duration, shot structure, audio and text elements, and editing techniques of cinematic ads to inform a two-stage generation pipeline in which an LLM first generates a shot plan and a
video generation model renders the
video. Using this pipeline, we generated 70 cinematic ads for 35 real brands and recruited professional
video editors to critique their editing choices. From their critiques, we derive six dimensions of editing quality: narrative progression, audiovisual coordination and sound design, visual composition and graphics, shot-to-shot continuity, message and brand coherence, and temporal rhythm and pacing. We discuss how these dimensions can guide editing-aware generation, human evaluation, and automated evaluation of AI-generated cinematic ads.
Read the full abstract ▾
Machine Learning
A Structural FHMM for Interpretable Disease Trajectories in T2DM
Alessandro Mari, Ekaterina Krymova, Guillaume Obozinski et al. (+3 more)
In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the analysis of disease trajectories in patients with Type 2 diabetes mellitus (T2DM). The model represents a patient's latent health state as a combination of multiple independent, simultaneously evolving components, associated with comorbidities and lab results. This structured latent representation facilitates the identification of clinically meaningful patient states and clustering of common disease trajectories. We evaluate the proposed approach using The IQVIA Medical Research Data incorporating data from THIN, a Cegedim database of anonymized electronic health records (EHR), identifying patients with a first-ever prescription for a non-insulin antidiabetic drug (NIAD) between January 2006 and December 2019. The model identifies multiple clinically coherent latent components corresponding to known patterns of diabetes-related complications and reveals heterogeneous progression pathways, including distinct microvascular-dominant and multi-organ trajectories associated with elevated comorbidity burden and mortality. These results demonstrate that the proposed framework captures meaningful longitudinal structure in EHR data and provides interpretable insights into the
evolution of T2DM and its comorbidities.
Read the full abstract ▾
All authors Alessandro Mari, Ekaterina Krymova, Guillaume Obozinski, Maria Luisa Marques de Sa Faquetti, Adrian Martinez de la Torre, Andrea Burden
Computation and Language
Speech-to-SOAP: End-to-End Summarization of Medical Dialogues: KIT@BeTraC 2026
Enes Yavuz Ugan, Fabian Retkowski, Yuka Ko et al. (+4 more)
With the advent of Large
Language Models and its instruction following capabilities a promising application is the task of summarization. Within this domain of task the extractive sub-task of clinical protocolling has emerged as a topic of particular interest as it can significantly reduce the downtime and protocolling burden of health-care workers thus enabling them to focus on their core work helping humans. A further step towards automation is the direct generation of clinical notes from
speech without intermediate transcripts, reducing processing time while preserving information such as coughing or other paralinguistic cues that may be lost in transcript-based systems. To this end, we present KIT's submission to this years BeTraC challenge in the lightweight track. Our main contribution is a scalable data augmentation pipeline that unifies heterogeneous medical dialogue
datasets through synthetic
speech generation and automatically generated SOAP supervision, enabling robust adaptation of a
speech foundation model for end-to-end
speech-to-SOAP generation.
Read the full abstract ▾
All authors Enes Yavuz Ugan, Fabian Retkowski, Yuka Ko, Thai-Binh Nguyen, Maike Züfle, Jan Niehues, Alexander Waibel
Artificial Intelligence
SonarLLM: A Native Sonar–Optical Multimodal Large Language Model for Underwater Perception
Cong Su, longxuan ma, Ling Dong et al. (+4 more)
Reliable
underwater perception requires complementary sensing under variable visibility. Optical cameras capture appearance and semantics but degrade rapidly with turbidity, whereas imaging sonar preserves geometry while exhibiting distinct range-azimuth structure and acoustic artifacts. Existing MLLMs, built primarily on optical encoders, are therefore ill-suited to model sonar or adaptively exploit sonar-optical complementarity. We propose SonarLLM, a sonar-optical MLLM that treats sonar as a native perceptual modality. It combines a sonar-specific encoder, modality-specific physics-aware feature enhancement, and reliability-aware hierarchical fusion to align acoustic structure with optical semantics and dynamically adjust their contributions as sensing quality changes. We also introduce SonarBench, a paired
benchmark that spans four tasks: recognition, counting, visual question answering, and captioning; and, across the
benchmark, three input settings: sonar-only, optical-only, and fusion. By fixing the scene and sonar observation while varying optical degradation, SonarBench enables controlled measurement of cross-modal complementarity. SonarLLM achieves 72.0% macro accuracy across sonar-only recognition, counting, and VQA, outperforming the strongest baseline by 34.4 percentage points, and 68.7% under fusion, exceeding the best baseline by 25.1 points. For recognition and counting, the fusion-over-optical gain grows from 6.0 to 36.0 points as turbidity increases, indicating the increasing complementary value of sonar under controlled optical degradation. Together, these results show that robust heterogeneous perception depends not only on adding sonar, but on representing and weighting it according to its sensing characteristics.
Read the full abstract ▾
All authors Cong Su, longxuan ma, Ling Dong, Guofeng Tang, Weijie Yin, Haohui Chen, Zhengtao Yu
Logic in Computer Science
QisMC: A Model Checker for QISKIT Program Debugging
Aochu Dai and Mingsheng Ying
We present QisMC, the first
quantum model checker dedicated to debugging Qiskit programs. On the theoretical side, we introduce the notion of
quantum-classical transition system and a
quantum computation tree logic (qCTL) grounded in Birkhoff-von Neumann logic for modeling the behaviors and specifying the properties of Qiskit programs, respectively. On the implementation side, QisMC provides an end-to-end framework encompassing transition system generation, logical formula representation, and model checking
algorithms, and it efficiently performs image computation based on decision diagrams. These methods and design principles give QisMC advantages over previous Qiskit program debuggers, including a unified property specification
language, a fully automated and exhaustive verification process, and the ability to generate counterexamples. Extensive illustrative examples and
benchmark evaluations demonstrate the practicality, efficiency, and scalability of QisMC in verifying realistic
quantum programs.
Read the full abstract ▾
Artificial Intelligence
Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control
Francisco M. Arrabal-Campos, Ignacio Fernandez, Francisco G. Montoya et al. (+1 more)
An intelligent system does not merely reason: it governs its own
reasoning - how much to compute, when to stop, which module to activate. Can that role be played by a dynamic internal field - a low-dimensional homeostatic state with explicit physics and certified stability - that modulates cognition without performing it? Ours is a field on the module graph governed by a family of PDEs on the graph
Laplacian, advancing with an adaptive-depth reasoner. We certify the stability of the integrator of the whole family - an integrator certificate, not a closed-loop one. New, and proved here: a discrete Schur-Cohn criterion for Verlet with velocity coupling, necessary and sufficient per latent root, with no commutation hypothesis. The answer is threefold: substance no, structure only in part, certifiability yes. The type of the field's physics is irrelevant for accuracy: wave,
diffusion, gated mixtures and a 2D Navier-Stokes substrate tie. A twenty-seed preregistered deconfounding campaign bounds the structural claim: at equalized caps the second-order effect is strong in one family (+0.087 [+0.042, +0.132], t=4.0) but is not detected in the other (+0.014 [-0.013, +0.040], n.s.), so part of the original contrast was capacity, not order; and a matched-interface GRU is indistinguishable in the first and nominally exceeds the field in the second (-0.035 [-0.067, -0.002]). What distinguishes the field is not capability but that its one-step operator admits an exact runtime stability check - a difference of kind, not of existence: learned recurrences carry certificates too, sufficient and conservative ones. A kill-gate with a positive control finds no evidence for the field as evidence accumulator (Delta AUC +0.0007 [-0.0065, +0.0079] vs a 0.03 threshold). A dynamic internal field is a viable, certifiable compute governor, but not an enhancer of cognition: it modulates, it does not think.
Read the full abstract ▾
All authors Francisco M. Arrabal-Campos, Ignacio Fernandez, Francisco G. Montoya, Alfredo Alcayde
Artificial Intelligence
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
Anupam Purwar, Shashank Singh and Kritika Srivastava
Evaluating conversational voice
agents at scale re- quires reliable assessment methods that capture both observ- able interaction quality and the contextual judgment typically provided by human evaluators. We investigate LLM-as-a-Judge evaluation by comparing human judgments with GPT-4.1 and GPT-5 on telecom and retail voice-
agent conversations, across conversational quality and safety dimensions. The same interac- tions are scored under three evaluation configurations, p0, p1, and p2, to test whether automated judgments are sensitive to the evaluation setup and whether observed patterns generalize across configurations and judge models. Beyond aggregate agreement, we examine metric-level correlations, evaluator consistency, and systematic human-LLM disagreement to identify which conver- sational attributes can be judged reliably by automation and which remain sensitive to interpretation and context. Effective voice-
agent evaluation is also shaped by pipeline-level factors such as
speech generation, streaming, and error propagation across ASR,
reasoning, and tool-calling stages, motivating our focus on comparing how human and LLM judges score the same interactions end to end. Our results show that LLM- based evaluation can serve as an effective component of large- scale voice-
agent assessment, but that its reliability is metric- and configuration-dependent rather than uniform. This pro- vides an empirical framework for identifying which metrics suit automated evaluation and supports hybrid pipelines in which LLM judges handle scalable assessment while human evaluators remain engaged for metrics that demand contextual interpretation and higher-confidence judgment.
Read the full abstract ▾
Numerical Analysis
A High-Accuracy Numerical Homogenization Method for Quasiperiodic Hamilton–Jacobi Equations
Kai Jiang, Meng Li, Juan Zhang et al. (+1 more)
In this work, we develop an accurate numerical homogenization method for computing effective
Hamiltonians of quasiperiodic Hamilton–Jacobi equations (QHJEs) with convex
Hamiltonians of the form $H(x,p) = |p|^k/{k}-f(x), ~k>1$, where $f$ is quasiperiodic. Computing effective
Hamiltonians in the quasiperiodic setting requires solving QHJEs posed on the whole space. Their solutions generally possess neither translational
symmetry nor decay and may exhibit low regularity. These features pose substantial challenges for numerical computation. To address these difficulties, we introduce a quasiperiodic boundary condition, which allows the original whole-space problem to be treated on a bounded domain while preserving quasiperiodicity at the boundary. We then propose an SL–FPR scheme that combines a semi-Lagrangian (SL) approximation with the finite points recovery (FPR) method and establish stability and error estimates for the resulting scheme. We also extend the quasiperiodic homogenization result from the quadratic case to general $k>1$ and apply the proposed method to accurately approximate the corresponding effective
Hamiltonians. Numerical experiments illustrate the convergence and applicability of the method and validate the extended homogenization results.
Read the full abstract ▾
All authors Kai Jiang, Meng Li, Juan Zhang, Lei Zhang
Artificial Intelligence
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
Qinglin Ye, Zhiyuan Gu, Jingjie Xia et al. (+6 more)
Search-augmented
reasoning remains difficult for small
language models. On-policy
distillation (OPD) from trained teachers offers a promising direction, but suffers from two issues: (1) high-quality multi-turn search trajectories depend on dynamic retriever responses, making SFT data prohibitively expensive to collect at scale; (2) task-specifically trained teachers incur substantial training cost, while directly applying OPD with an off-the-shelf teacher without task-specific fine-tuning constrains the student to the teacher's performance ceiling and suffers from severe training instability. We propose OPDSearch+, the first
distillation paradigm that requires no teacher fine-tuning for search-augmented
reasoning. We investigate the role of a frozen off-the-shelf instruct model as the teacher in on-policy
distillation, and reveal a key insight: the teacher reshapes the student's policy distribution so that subsequent RL converges to a superior solution that RL alone cannot reach. In stage one, the student interacts with a live search engine and is distilled via a per-position forward KL objective, transferring
reasoning decomposition and evidence integration skills without any task-specific teacher training. In stage two, RL refines the distilled student from a richer behavioral foundation, achieving performance that RL alone cannot reach from scratch. Across seven QA
benchmarks, OPDSearch+ with a 3B model consistently outperforms all prior 3B RL baselines, achieving gains of 13.1% on HotpotQA and 8.5% on 2WikiMultihopQA.
Read the full abstract ▾
All authors Qinglin Ye, Zhiyuan Gu, Jingjie Xia, Yiheng Zhang, Kaiyan Zhao, Shunchao Zheng, Yuhang Mu, Wenchao Du, Yiming Wang
Distributed Computing
An HPC Approach to Accelerate Tensor Decompositions
Markus Hellgren, Erna Begovic Kovac, Hans O. Karlsson et al. (+1 more)
Quantum systems grow in complexity so rapidly that even modest models become difficult to simulate, creating a strong need for methods that can handle high-dimensional data, also known as tensors. In this work, we investigate a novel Jacobi-type tensor
algorithm for tensor decomposition and develop a CUDA-based
algorithm that supports tensors of arbitrary order on a single GPU. We test the implementation on NVIDIA H100 GPUs and show that the
algorithm converges correctly for diagonalizable tensors up to nine dimensions, with runtime scaling in a predictable way as tensor order grows. Finally, our general
algorithm outperforms the original MATLAB reference by more than two orders of magnitude.
Read the full abstract ▾
All authors Markus Hellgren, Erna Begovic Kovac, Hans O. Karlsson, Roman Iakymchuk
Computation and Language
Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research
Eran Hirsch, David Wan, Han Wang et al. (+3 more)
Deep research (DR) systems produce long-form cited reports by orchestrating multiple
agents that search and synthesize information from the web. Citations are the primary mechanism for evaluating the faithfulness of these reports, yet current DR systems exhibit poor citation recall. Moreover, improving citation recall is challenging because DR systems are complex multi-
agent architectures where information passes through
agents like a telephone game, and both content and citations can get corrupted along the way. We propose an evaluation method that pinpoints which
agent introduced each error by locally testing
agent invocations for faithfulness and verifiability relative to their own inputs. Furthermore, we propose a four-type taxonomy to categorize the discovered errors:
hallucination, uncited input reliance, uncited output, or insufficient citations. Applying our method to three top-ranked open-source DR systems, we obtain actionable diagnostics. Almost every
agent makes a lot of mistakes with the exception being those that summarize a single document. We find that the dominant error type varies systematically across
agents, where the orchestrator mistakes are mostly citation-related. We find that 84.7% of final-report errors in AI-Q originate at the orchestrator, roughly 31% of them
hallucinations and the rest citation mistakes. Guided by these insights, we demonstrate that two simple interventions raise citation recall by 5% without degrading output quality.
Read the full abstract ▾
All authors Eran Hirsch, David Wan, Han Wang, Elias Stengel-Eskin, Mohit Bansal, Ido Dagan
Computation and Language
SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling
Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios et al. (+2 more)
Recent controllable text generation (CTG) for sentiment control has largely focused on decoder-based large
language models, making causal
attention the dominant paradigm. While effective for fluent generation, these models still struggle to satisfy complex constraints and follow fine-grained sentiment signals specified by users. Existing sentiment-aware CTG methods typically simplify the problem by treating sentiment either as a coarse categorical label (e.g., positive or negative) or as a single fine-grained control signal applied to an entire document. Consequently, more challenging settings such as sentence-level sentiment control within long-form text remain underexplored. To address these limitations, we introduce SenseShift , an encoder-based framework for fine-grained sentence-level CTG. Unlike standard decoder architectures, SenseShift leverages bidirectional
attention, quantized sentiment signals, and iterative mask infilling to generate local sentences conditioned on target sentiment intensity. Empirical evaluations on story and review generation demonstrate that SenseShift achieves stronger sentiment controllability while maintaining text quality and robustness to out-of-domain generation compared to larger decoder-based baselines.
Read the full abstract ▾
All authors Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios, Navid Rekabsaz, Markus Schedl
Machine Learning
Causal Analysis for Time Series Foundation Models
Mathis Jander, Wouter van Heeswijk and Martijn Mes
Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially high-risk,
forecasting applications are exposed to the same biases and failure modes of a single time series foundation model. At the same time, this centralization allows for economies of scale in model development and validation. In this study we investigate how biases and failure modes of time series foundation models can be identified before deployment. We propose a causal analysis framework to investigate the ability of a time series foundation model to preserve time series patterns. To achieve this, we intervene on parameterized synthetic time series generators and measure the corresponding change in model output under ceteris paribus conditions. We apply our causal analysis framework to Chronos-2 and TimesFM-2.5 and test them across six distinct time series patterns. We find safe configurations for trend and harmonic oscillation patterns. The results also indicate a bias in both models towards overestimating persistence, sudden failures for both models against the regime switch pattern and failure for TimesFM-2.5 against the energy-release pattern. Our review of the original works for both models indicates that the findings might be explained by the data used for pretraining. We conclude our study with suggestions for further model development, recommendations for application-specific model selection, and a discussion of limitations and further research directions.
Read the full abstract ▾
Artificial Intelligence
VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models
Guoyang Xu and Hao Chen
Long-
video understanding depends not only on the capability of a
vision-
language model (VLM), but also on how its limited context is constructed from a much longer
video. Existing systems typically introduce hand-designed sampling,
retrieval,
memory, or agentic control strategies, making the context-construction program itself difficult to study as an independent optimization target. We introduce VideoHarness-RSI, a controlled framework that recursively searches executable context constructors around a frozen VLM while keeping the answering model and interface fixed. We study this baseline under complementary weak- and strong-initialization regimes. From a weak uniform constructor, recursive search progressively discovers more structured context-construction programs; from a stronger AKS harness, the same process further advances an already competitive hand-crafted frontier. The resulting harness retains its advantage under a matched cumulative visual-
token control and transfers directly to additional long-
video benchmarks without further search. Together, these results establish executable context construction as a distinct optimization layer and provide an auditable baseline for studying harness discovery, transfer, and efficiency around frozen VLMs.
Read the full abstract ▾
Machine Learning
Contrastive Branch Policy Optimization
Ying Wang, Changlin Qiu, Bang Lin et al. (+4 more)
Reinforcement learning with verifiable rewards (RLVR) enables
language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal for identifying which intermediate decisions are responsible for success. Branch sampling induces local comparisons among alternative continuations, but existing methods tend to conflate two distinct problems: allocating a fixed rollout budget and translating branch outcomes into
token-level credit. We introduce Contrastive Branch Policy Optimization (CBPO), which disentangles these two problems and assigns a dedicated mechanism to each. Generation
entropy screens candidate branch positions across the entire response, while path-level and node-level decay distribute a fixed budget across trajectories and positions to prevent exploration from collapsing onto a few paths or adjacent
tokens. A parent trajectory together with the branches that share an identical
token prefix forms an exact-prefix group, and the reward variation within this controlled group defines the Contrastive Branch Value (CBV), an outcome-based estimate of local decision sensitivity that rescales continuation advantages without altering their sign. When multiple nodes are selected along the same trajectory, CBPO partitions it into non-overlapping credit segments, thereby avoiding duplicated gradients on shared
tokens. Requiring only outcome rewards and no process-level annotation, CBPO provides a practical solution for fine-grained credit assignment in tool-integrated
agent training. Extensive experiments on ten
benchmarks, including five for mathematical
reasoning and five for knowledge-intensive search, show that CBPO consistently outperforms state-of-the-art policy-optimization and branch-based methods, attaining the highest macro-average accuracy in both domains and across two model scales.
Read the full abstract ▾
All authors Ying Wang, Changlin Qiu, Bang Lin, Linbo Jin, Wen Jiang, Zhe Sun, Jingli Yang
Human-Computer Interaction
When AI "Works," When Does Help Begin?: Intergenerational Support Around Older Adults' LLM Usage
Hyehyun Chu, Yuri Lee, Yeon Su Park et al. (+2 more)
LLMs are becoming part of everyday life, including for older adults (OAs). OAs often learn digital technologies with younger family members, who have traditionally served as "warm experts" providing trusted and personalized operational help. LLMs expand this role: family supporters may also help OAs judge appropriate uses, consider what information to disclose, assess the credibility of outputs, and decide when AI-generated advice is safe to act on. We conducted a formative qualitative study with six OAs and seven younger adults (YAs), using semi-structured interviews and scenario-based think-aloud activities. OA participants described using LLMs to lighten their recurring reliance on family, while preserving family as a selectively invoked support channel. However, because LLMs rarely produced visible operational breakdowns, YAs had limited signals for when support was actually needed. Instead, YAs relied on OAs' partial disclosures and negotiated intervention through general warnings and self-imposed action boundaries. As a result, family support often solved an immediate problem without leaving reusable calibration knowledge for future use. Based on these findings, we propose design implications for intergenerational LLM support (e.g., consentful help requests, learning-oriented family support that preserves OA task ownership).
Read the full abstract ▾
All authors Hyehyun Chu, Yuri Lee, Yeon Su Park, Saelyne Yang, Juho Kim
Systems and Control
Electric Vehicle Charging Right Trading: Concept, Mechanism, and Methodology
Ruike Lyu, Yuxuan Gu and Qixin Chen
With the increasing penetration of electric vehicles (EVs), uncoordinated EV charging and the resulting chaos, disorder, and long waiting times at EV charging stations (EVCSs) will no longer be tolerable. An EV charging right (CR) is the right to reserve a predefined charging service. By purchasing CRs, EVs can reduce their charging waiting time, and the price of CRs can guide EVs toward optimized charging behaviors. In this article, we define CR, propose the CR trading mechanism (CRM), and analyze the effect of CRM on reducing waiting times and mitigating congestion in EV charging. In the proposed CRM, EVs can purchase CRs in advance, and the CRs are used to estimate the waiting time and update the price of charging. Queue theory is utilized in the waiting time estimation, in which the impact of disclosing queue states at EVCSs is considered for the first time. The simulation results verify the accuracy of the waiting time estimation and the effect of the proposed mechanism.
Read the full abstract ▾
Information Retrieval
RecGPT-Mobile-V2 Technical Report
Lingqing Zhang, Bin Zhang, Weipeng Huang et al. (+25 more)
Personalized Query prediction maps implicit behavioral signals—clicks, favorites, purchases, and post-purchase exploration—to explicit
retrieval intent. On-device deployment makes this task particularly challenging: behavioral trajectories are noisy and multi-scale, multiple Queries may be valid for a single trajectory, and a uniform
reasoning policy either expends unnecessary computation on simple instances or allocates insufficient capacity to complex ones. We introduce RecGPT-Mobile-V2, an end-to-end framework that treats intent quality and execution efficiency as coupled objectives within a staged design. The framework transforms heterogeneous interactions into an evidence-preserving trajectory, establishes a recommendation-native foundation through domain adaptation and supervised
alignment, and applies
reasoning-cost optimization only after grouped rollouts meet grounding and utility criteria. The resulting teacher is distilled into a compact student deployed with low-bit execution, structured compression, and budget-aware device–cloud routing. In an aligned CoT ablation, an evidence-focused short rationale increases ROUGE-L from 0.228 to 0.315 and Jaccard from 0.174 to 0.248, while slightly outperforming the full five-stage rationale. In the controlled RL comparison, the complete reward formulation improves Query quality from 73.2% under quality-only RL to 78.6%, lowers the hard-failure rate from 3.6% to 1.6%, and reduces the median CoT length from 62 to 14
tokens. Online
retrieval analysis further indicates that the Query recall channel retrieves inventory complementary to that surfaced by established recall channels. Collectively, these findings support sufficiency-oriented rather than uniformly short
reasoning: retain decision-relevant evidence and allocate additional computation only when it is likely to improve the predicted Query.
Read the full abstract ▾
All authors Lingqing Zhang, Bin Zhang, Weipeng Huang, Chengfei Lv, Chengyu Lai, Chuxin Chen, Dimin Wang, Han Zhu, Hongtao Cheng, Jialin Zhu, Jian Wang, Jiuning Lin, Junqing Wu, Li Chen, Qichao Ma, Ruiquan Lan, Shuai Zhong, Tao Wang, Xiaodong Zhu, Yinjiang Cai, Yinnan Song, Yipeng Yu, Yuan Liu, Yuning Jiang, Zhaode Wang, Zhibo Xiao, Zhixin Ma, Zihong Huang
Computer Vision
Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation
Yeonkyeong Lee, Hyunsung Go, Jongmin Kim et al. (+2 more)
Latent
diffusion models have emerged as a dominant framework for high-fidelity image and
video synthesis, operating in compact latent spaces with variational autoencoders (VAEs) to enhance computational efficiency without compromising visual quality. However, conventional VAEs are suboptimal for
video data as they employ fixed compression ratios that cannot adapt to the varying complexity of spatio-temporal content. We present KATok (Keep-or-Drop? Adaptive Tokenizer for Compact
Video Representation), a
transformer-based VAE that incorporates an adaptive
token selector which is jointly learned with latent
tokens. By evaluating each
token's content-richness as keep-or-drop probability, the
token selector effectively discards uninformative
tokens, naturally allowing data-dependent compression. Applying adaptive tokenization to
diffusion models may cause spatial misalignment, as
token dropping can disturb the original spatio-temporal structure. To alleviate this issue, we propose two position-prediction strategies: cascaded and joint generation, to ensure spatial consistency. We empirically show that our model achieves strong reconstruction and generation quality at a state-of-the-art compression ratio. Further analysis on
video data reveals that this improvement is primarily achieved by reducing spatio-temporal redundancy and removing uninformative
tokens, as supported by both quantitative and qualitative results.
Read the full abstract ▾
All authors Yeonkyeong Lee, Hyunsung Go, Jongmin Kim, Sewoong Lim, Donghoon Lee
Artificial Intelligence
ReproAgent: Contract-Guided Paper-to-Code Reproduction
Xue Hu, Zewei Pan, Zhongyuan Wang et al. (+3 more)
Paper-to-code reproduction asks scientific AI
agents to turn research papers into executable repositories that preserve the paper's method, protocol and artifacts. This is difficult because the specification is split: explicit paper content such as
algorithms, metrics and artifacts is often lost across long
agent trajectories, while implicit details such as framework defaults and conventions inherited from related work are absent from the paper. We introduce ReproAgent, a four-stage Prepare–Plan–Generate–Repair pipeline built around a persistent implementation contract with two channels: an implementation-requirement channel that turns paper snippets into code obligations, and a reference-evidence channel that retrieves content and structure evidence from related repositories. Both are bound to work packages, projected into file-level contracts, and consumed across generation and repair. On PaperBench Code-Dev, ReproAgent reaches the highest mean score among same-backbone scaffolds under both Claude-Sonnet-4.5 and Gemini-3-Flash. End-to-end channel ablations and per-paper cases support the contribution of both channels. Code and experimental artifacts are publicly available.
Read the full abstract ▾
All authors Xue Hu, Zewei Pan, Zhongyuan Wang, Zhou Liu, Zeli Su, Wentao Zhang
Numerical Analysis · Cross-listed from math.AP
Nonlinear Modal Reduction for Subwavelength Dielectric Scattering
Habib Ammari, Ioan Gorea and Bowen Li
We study three-dimensional wave scattering by high-index dielectric resonators with Kerr-type nonlinearity under plane-wave incidence, together with the associated nonlinear dielectric scattering resonances, through a nonlinear Lippmann-Schwinger equation. Using a Lyapunov-Schmidt reduction near a simple eigenmode of the Newtonian potential, we obtain a local decomposition of the scattered wave into a resonant contribution and a controlled remainder and derive an explicit nonlinear equation for the resonant modal coefficient for sufficiently small contrast parameter and locally small resonant amplitude and incident field. A second reduction covers the regime of incident fields of order one and weak nonlinearity. Our results extend for the first time the linear modal decomposition to nonlinear wave-scattering problems. We complement them by developing a numerical framework based on Nyström discretization, real Newton iteration, and pseudo-arclength continuation. For single resonators of several geometries, our computations confirm the predicted high-contrast resonance scaling and the nonlinear modal approximation, and exhibit the multivalued incident-wave response. For a mirror-symmetric resonator dimer, we track symmetric, antisymmetric, and
symmetry-broken resonance branches over a broad range of separations. Our computations show that the
symmetry-breaking threshold increases as the gap between the resonators decreases, in agreement with the leading-order bifurcation theory.
Read the full abstract ▾
Systems and Control
Cognitive Energy Management: Concept,Framework, and Demonstration in Smart Port Energy Systems
Hafiz Majid Hussain, Wajiha Samer and Juhaa Haakana
Modern energy management systems, even within advanced energy internet (EI) infrastructures, remain fundamentally reactive, optimization-bound, and incapable of
reasoning about context, intent, or uncertainty. While the EI paradigm has established a powerful cyber-physical architecture for interconnecting distributed energy resources via software-defined packetized networks, the question of how such systems should think, adapt, and govern energy decisions intelligently remains an open challenge. This paper introduces cognitive energy management (CEM); a new conceptual framework that addresses this gap by redefining how energy systems perceive, reason, learn, and act within complex operational environments. Grounded in the EI cyber-physical foundation, CEM extends beyond conventional optimization by
embedding goal-directed
reasoning and continuous adaptation into the energy management loop, positioning itself as the cognitive governance layer of EI-based infrastructures. We formally define CEM, distinguish it from rule-based and optimization-based paradigms through structured comparison, and articulate its core architectural layers. To demonstrate the framework's practical value, we develop a toy problem grounded in smart port energy management; one of the most operationally demanding EI node environments in modern infrastructure. Specifically, we model a predictive vessel turnaround scenario in which a CEM-enabled system plans energy procurement, storage pre-charging, and load scheduling across a six-hour operational horizon. The demonstration illustrates how CEM moves the EI beyond feasibility-seeking toward intelligent, anticipatory energy governance.
Read the full abstract ▾
Numerical Analysis
Samplet compression for conditionally positive definite kernels and universal Kriging
Sara Avesani, Rüdiger Kempf, Michael Multerer et al. (+1 more)
We present a samplet-based framework for the efficient numerical solution of saddle-point systems arising from conditionally positive definite (CPD) kernel approximation in general and universal Kriging in particular. The vanishing moment property of samplets as well as the particular structure of the associated scaling distributions, which correspond to discrete orthogonal
polynomials, allow for a numerically favorable representation of these saddle-point systems. Concretely, they enable a natural null-space reduction of the indefinite saddle-point system to a (large) linear system for the detail coefficients and a small triangular system for the
polynomial coefficients. We derive error bounds for the approximation by polyharmonic splines in Beppo-Levi spaces and show that the detail coefficients span precisely the subspace on which the CPD kernel is positive definite, rendering the reduced block symmetric positive definite. In view of the quasi-sparsity of the samplet-transformed kernel
matrix for asymptotically smooth kernels, the resulting method achieves O(N log N) cost for the assembly and the storage of the saddle-point system. The reduced system can efficiently be solved by a sparse Cholesky factorization. We illustrate the framework with three applications, namely Gaussian process regression with generalized covariances, landmark-based image registration via samplet-compressed thin plate splines, and three-dimensional mesh deformation.
Read the full abstract ▾
All authors Sara Avesani, Rüdiger Kempf, Michael Multerer, Holger Wendland
Computer Vision
CARE: Camera-Residual Reserves for First Sightings in Adaptive LiDAR Sensing
Jiachen Gong, Yun Li, Ehsan Javanmardi et al. (+2 more)
Adaptive
LiDAR scanning concentrates a limited sensing budget on regions of interest predicted from past object tracks, lowering data volume in autonomous driving while maintaining detection accuracy. However, existing scanning policies face three challenges. First, history-driven approaches depend on past tracks, so unseen objects are detected late or missed. Second, random or uniform sampling outside the predicted regions has no awareness of where new objects appear. Third, camera-guided alternatives spend budget on all camera detections, resampling objects already covered, costing recall in crowded scenes and range when budgets are scarce. This paper introduces the CAmera-REsidual reserve (CARE), a training-free allocation rule that reserves part of a fixed ray budget for the directions of current camera detections that the track forecasts cannot explain; the rest follows the base history policy, and unused reserve returns to a random floor. The paper makes three contributions. First, a leakage-free ray-budget evaluation on nuScenes (150 scenes, 4,148 events) measuring the first-sighting loss of history-driven scanning, with a strict-causal variant using the preceding keyframe. Second, CARE raises first-sighting recall by 5.2, 5.2, and 4.3 points at 10%, 20%, and 35% budgets over the history policy, with paired intervals excluding zero; the camera cue drives this gain, and the first-sighting versus overall trade-off is a budget-dependent Pareto choice. Third, a safety-bounded forgetting module that releases budget from receding or static tracks beyond a speed-dependent guard distance; at tight budgets, forgetting without the guard significantly harms near-field recall, so the guard is what keeps it safe. The pipeline runs end to end on a real vehicle and, in closed-loop simulation, detects an occluded pedestrian earlier and brakes more reliably than history-driven scanning.
Read the full abstract ▾
All authors Jiachen Gong, Yun Li, Ehsan Javanmardi, Wencan Mao, Manabu Tsukada
Computer Vision
Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR
Sheethal Bhat, Bogdan Georgescu, Awais Mansoor et al. (+5 more)
Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this,
Vision-
Language (VL) object detection methods leverage grounding text information to enable powerful zero-shot and few-shot object detectors in the natural image domain [1, 2, 3, 4]. However, transferring these methods to the medical domain is challenging due to the absence of comparable quality and quantity of the grounding data. Regardless, significant contextual and non-imaging information exists in medical images that remains underutilized. Few-shot learning (FSL) techniques partially address this limitation but struggle to general ize to unseen medical findings and require extensive retraining when new findings are introduced [5, 6]. To overcome these challenges, we extend our prior EM-DETR framework [7] and introduce a scalable FS detection approach designed for efficient abnormality detection in Chest X-Ray (CXR) images under minimal supervision. The proposed architecture incorporates exemplar-based feature generation and domain-aware contrastive optimization, enabling effective adaptation to novel disease findings without exhaustive retraining. Our method achieves near state-of-the-art (SOTA) detection performance using less than 10% of the annotated data, demonstrating its potential for practical, annotation-efficient clinical deployment across both proprietary and public CXR
datasets.
Read the full abstract ▾
All authors Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Mathias Zinnen, Pranjal Sahu, Florin C. Ghesu, Sasa Grbic, Andreas Maier
Systems and Control
The Flat Earth Error: Differential Geometry in Vehicle Dynamics
David J. N. Limebeer and Charl van de Merwe
The widespread idealization of road surfaces as horizontal planes can introduce significant inaccuracies into vehicle dynamics simulations, a phenomenon termed the “Flat Earth Error.” This article provides an expository guide to the use of classical differential geometry to model vehicular motion on curved surfaces. The influence of road
curvature is characterized using the metric tensor, the second fundamental form, the shape operator, and the Christoffel symbols. Reproducible MATLAB scripts using an
elliptic cone as a
benchmark example illustrate the construction of geodesic curves and the simulation of particle dynamics on curved surfaces. The resulting
geometric structures are integrated into a single-track vehicle-and-track model within a pseudospectral optimal control framework. Trajectory optimization results over a high-density mobile
LiDAR profile of Darlington Raceway are used to generate a high-fidelity road-surface model. This model is used within an hp-adaptive collocation framework to investigate minimum lap time optimal control vehicular trajectories. These computations capture the non-smooth traction saturation limits of the tyres alongside position-dependent variations in gravitational forcing. Integrating differential geometry, multibody mechanics, and optimal control is essential for high-fidelity driven and autonomous vehicle-dynamics simulations. The optimized velocity and tyre slip profiles show that real-world racing track geometries induce dynamically significant three-dimensional effects. These results are particularly relevant to performance-limited simulations on highly banked track surfaces such as NASCAR ovals.
Read the full abstract ▾
Networking
LEMONS: Leveraging Model-Based Techniques to Enable Non-Intrusive Semantic Enrichment in Wireless Sensor Networks
Jan Novacek, Arthur Kühlwein, Sebastian Reiter et al. (+3 more)
The paper presents an efficient approach to the semantic enrichment of measured sensor data in Wireless Sensor Networks (WSNs), by bridging techniques from Model-driven Software Development (MDSD) and Semantic Web Technology (SWT). Our approach reinforces data interoperability, fostering data sharing and reuse, by utilizing SWT. Model-based and type-agnostic configuration reduces the overall effort for WSN setup and maintenance, which are traditionally complex and time-consuming tasks. The presented approach addresses the problem of large-scale WSN management through the application of SWT in WSN configuration and management without requiring expert knowledge. Additionally, we present a generic architecture and an implementation which is also supplemented by hands-on descriptions of an illustrative use case. Our experimental results demonstrate that our model-based approach provides non-intrusive semantic enrichment with sub-millisecond computational overhead, as well as partially automated configuration of WSNs.
Read the full abstract ▾
All authors Jan Novacek, Arthur Kühlwein, Sebastian Reiter, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel
Artificial Intelligence
RePolicy: Learning to Select and Apply Safety Policies for Agent Safeguards
Houcheng Jiang, Boxuan Zhang, Qiyong Zhong et al. (+3 more)
Agent safeguards must determine whether an
agent's behavior violates the safety rules of the current task, environment, and user. Because these rules vary across contexts, a safeguard needs to select the relevant policy before judging the behavior. Existing policy-aware safeguards can apply a supplied policy, but generally assume that the correct policy is already known. They therefore do not learn how to select a policy from a library, even though an incorrect choice can lead to an incorrect safety judgment. We introduce RePolicy, a safeguard that jointly learns policy selection and safety assessment. Given an
agent trajectory and a set of candidate policies, RePolicy selects the policy that best matches the situation, applies its requirements, and predicts whether the behavior is safe. We construct PolicyTraj-20K, a
dataset of more than 20,000
agent trajectories annotated with applicable policies, safety labels, and explanations. We train RePolicy with supervised demonstrations followed by reinforcement learning, while randomizing policy order, identifiers, and distractors to reduce shortcut learning. Across six
agent-safety
benchmarks and 19 baselines, RePolicy-4B achieves leading overall safety-detection performance and improves policy-selection accuracy. These results show that safeguards can learn which safety requirements to use for assessing
agent behavior.
Read the full abstract ▾
All authors Houcheng Jiang, Boxuan Zhang, Qiyong Zhong, Junfeng Fang, Xiang Wang, Xiangnan He
Artificial Intelligence
Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making Modeling
Ying Jin, Weiqing Min, Mingyu Huang et al. (+1 more)
A sustainable diet represents a multi-dimensional synergy among four essential pillars: nutrition adequacy, economic affordability, cultural acceptability, and environmental respect. Despite the prevalence of population-level sustainability modeling, practical implementation relies on effective individual-level adoption. This transition is often hindered by inter-individual heterogeneity, posing a formidable challenge in aligning sustainable diet requirements with individual preferences. To address this issue, we propose a personalized sustainable diet recommendation model based on a constraint-aware decision-making mechanism, where sustainability is incorporated through learnable constraints rather than modeled as user preferences. To systematically evaluate the proposed approach, we construct a sustainable diet
dataset named SusDiet with about 150k recipes, characterized by broad coverage of sustainability indicators. Experimental results on this
dataset show that our method promotes more sustainable choices without compromising individual preference. This work establishes a framework for aligning individual dietary choices with planetary health, offering quantitative evidence to guide future sustainable diet interventions and policy-making for sustainable development.
Read the full abstract ▾
All authors Ying Jin, Weiqing Min, Mingyu Huang, Shuqiang Jiang