Systems and Control
Semi-Autonomous Prosthesis Control Empowered by 5G and Mobile Edge Computing
Ozan Karaali, Hossam Farag, Strahinja Dosen et al. (+1 more)
Prosthetic hands equipped with cameras can use computer
vision to plan grasps automatically, reducing cognitive effort. However, running modern
vision models on wearable devices is impractical due to power and processing constraints. We present the first prototype of a 5G-connected mobile edge computing (MEC)-enabled semi-autonomous prosthetic hand, which streams RGB-D images to an edge server for real-time grasp planning. Thirteen able-bodied participants performed pick-and-place tasks under six conditions: manual EMG control, on-device inference, wired Ethernet connectivity, and three 5G connectivity configurations (private 20 MHz network, private 100 MHz network, and a commercial 5G link) to the server. All network-based conditions performed similarly, achieving task times around 8.6 s (34% faster than manual control), failure rates of 20-38%, and 62% lower overall workload. On-device processing performed the worst with 10.3 s task time and a 76% failure rate due to slow embedded inference (3 fps vs. 6-20 fps over the network). Network latencies remained below 180 ms for private 5G and 270 ms for commercial 5G. All 5G configurations, including bandwidth-constrained and commercially variable networks, matched wired Ethernet performance while significantly outperforming both manual control and local processing, establishing 5G edge-offloading as a practical path to deploying compute-intensive prosthesis control.
Read the full abstract ▾
All authors Ozan Karaali, Hossam Farag, Strahinja Dosen, Cedomir Stefanovic
Computers and Society
Law of Large Numbers: Accuracy as Statistical Measure for AI Compliance and Competition
Rabanus Derr, Alina Wernick and Robert C. Williamson
The machine learning community progresses (in part) by improving the "accuracy" of its systems. The EU AI Act explicitly refers to "accuracy" as part of its compliance measures for high-risk AI systems. Are we talking about the same thing? This work presents "accuracy" as a case-study for differing requirements of social worlds, the technological machine learning community and the legal community. While competition on accuracy contributes to technological development, machine learning scholars simultaneously recognize accuracy's shortcomings regarding the usefulness and effectiveness of machine learning systems. The legal counterpart embraces the vagueness of "accuracy," leaving interpretative flexibility for technological and societal changes. At the same time, accuracy is a core element of compliance within the EU AI Act. We elaborate on five main tensions, (a) nature of accuracy, (b) notion of performance, (c) scope of validity, (d) ends, and (e) statisticalness, to show that the two communities project disparate, and sometimes contradictory, expectations on accuracy. Both legal and technical communities lack precise understanding of "accuracy" beyond the contextual boundaries of their community. The resulting frictions, \eg, based on the empirical or normative understanding of accuracy, are symptoms of an unresolved (and unresolvable) debate on what accuracy is. We constructively use the frictions to recommend baselines and interventional studies in standardization, and demand for tools to extend the validity of accuracy measurements.
Read the full abstract ▾
Computation and Language
One note in three: a verified census of three deployed AI scribes, and the instrument that counted it
Sebastian Fox, Luke Markham, Ryan Lail et al. (+1 more)
Ambient AI scribes draft clinical notes under the reassurance that a clinician signs every note. We audited three commercial AI scribes on the same 142 consultations: 565 notes from recorded UK primary-care and US ambulatory encounters plus authored scenarios. Twelve discovery passes proposed 13,678 candidate errors; the 5,898 clearing an importance filter went to an
adversarial panel of two models from different families, each told to refute what it could, and 618 survived. One note in three (31.3% [27.0, 35.6]) carries a verified failure, concentrated in allergy and medication information, invented patient identity, and history written up as examination on telephone consultations that can contain none. No product was given a patient record; setting aside the two classes a record would have prefilled, invented identity and dates, the rate is 24.8% [20.8, 29.0]. One failure mode did not fit our scheme, drawn from published scribe-error taxonomies: a treatment the clinician retracts, recorded as delivered care. Two clinicians adjudicated blind, disjoint samples: a physician author upheld 20 of 21 findings (95.2% [77.3, 99.2]) and an independent clinician, not an author, 12 of 12 ([75.8, 100]); both judged every sampled refusal genuine. A failure rate depends on the instrument as much as the scribes. With model, evidence and settings fixed, the review instruction alone moves the share of candidates verified from 9.3% to 79.0%, and the reviewing family moves it too: alone at that instruction the gentler flags 54.8% of notes against 27.8%. Between 28% and 97% of sampled notes carry a failure depending on the standard. Published audits disagree among themselves by a margin instrument differences alone can produce: omission is 54-86% of their errors against our 23.1%. We release all 618 findings with transcript-side evidence, every
prompt and model version, and the re-runnable pipeline.
Read the full abstract ▾
All authors Sebastian Fox, Luke Markham, Ryan Lail, Michael Karotsieris
Computation and Language
LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It
Sebastian Fox, Luke Markham, Ryan Lail et al. (+1 more)
Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our
benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA
prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved
prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no
benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the
benchmark,
prompts and judgements.
Read the full abstract ▾
All authors Sebastian Fox, Luke Markham, Ryan Lail, Michael Karotsieris
Computation and Language
Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols
Chengyuan Gao, Jiang Wu, Tao Lu et al. (+4 more)
Computational mental health screening using
multimodal speech and text has shown great promise. However, existing models often assume all clinical
speech protocols carry equivalent evidentiary validity. In reality, heterogeneous protocols, from free interviews to fixed reading tasks, support fundamentally different evidence. Forcing uniform
reasoning flattens these boundaries, causing models to hallucinate symptoms from irrelevant text or overclaim support. Even advanced long chain-of-thought LLMs fail to resolve this issue, as free-form
reasoning can exacerbate boundary violations. To address this, we reformulate
multimodal screening as an evidence-bounded
reasoning problem. We introduce the Evidence Package
Benchmark, integrating 1,870 packages across six heterogeneous sources with explicit modality masks and evidence permissions. We further propose EviBound, a protocol-aware evidence control framework. Unlike direct LLM prompting, EviBound uses a profile-aware planner to restrict
reasoning scope, orchestrates evidence tools via five-way acoustic consensus, and enforces a boundary critic to suppress unsupported claims. Empirical results show EviBound achieves a held-out test Depression AUROC of 0.8658, exceeding the strongest direct omni-modal baseline by +0.0811 AUROC while maintaining zero claim violations. Our work moves beyond unconstrained accuracy toward evidence-consistent, protocol-aware systems for safer clinical NLP research.
Read the full abstract ▾
All authors Chengyuan Gao, Jiang Wu, Tao Lu, Jiayan Guo, Mingkun Xu, Tianyi Zang, Shangyang Li
Machine Learning
TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification
Jérémie Stym-Popper, Clément Rambour, Federica Granese et al. (+2 more)
Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for physiological time-series classification. While tabular foundation models such as TabPFN offer an attractive alternative to conventional fine-tuning through in-context learning, they are not designed to capture the temporal dependencies inherent to physiological signals. ~In this paper, we introduce TSPFN, a foundation model that redesigns TabPFN's architecture for time series data. TSPFN integrates structured temporal representations and positional
embeddings to capture intra-sample temporal and channel dependencies. To fully leverage its spatio-temporal design, the model is pretrained on 140,000 real-world physiological time series across multiple medical domains. This yields a unified, generalizable framework capable of learning the specificities of medical time series. Experiments across diverse physiological
benchmarks demonstrate that TSPFN consistently outperforms standard tabular baselines and TabPFN, and achieves superior cross-domain generalization compared to specialized deep time-series models. All our experiments, ablation studies, and pre-processing scheme are publicly available at https://github.com/Jeremstym/TSPFN
Read the full abstract ▾
All authors Jérémie Stym-Popper, Clément Rambour, Federica Granese, Nicolas Thome, Olivier Bernard
Machine Learning
Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation
Tianyu Gao, Zhikai Su, Jiashu Li et al. (+5 more)
Structure-based drug design (SBDD) requires ligands that satisfy both 3D target affinity and 1D chemical validity. Existing controllable generation methods often rely on task-specific fine-tuning or externally imposed sampling-time guidance, adding cost and potentially conflicting with evolving 3D
geometric constraints. We propose LiFT, a
language-informed cross-modal framework built on Flow Matching for trend-guided 3D molecular generation across both de novo design and scaffold hopping. LiFT uses a "Sense-Evolve-Assemble"
agent to generate target-aware SMILES as intermediate chemical conditions, from which a pre-trained chemical foundation model extracts continuous semantic priors. These priors are integrated into
geometric generation through a lightweight semantic projector with zero-initialized adaptive normalization for stable cross-modal conditioning. We further introduce a Self-Conditioned Decoupled Router (SCDR), which modulates the velocity field according to intermediate structural states during ODE integration. Experiments on Cross-Docked2020 show that LiFT achieves competitive distribution matching while improving medicinal chemistry metrics and maintaining competitive structural validity under task-steering settings without additional generator fine-tuning. Our results suggest that
language-derived chemical priors provide effective trend-level guidance for 3D molecular generation. Code and released artifacts are available at https://github.com/kasurl/LiFT.
Read the full abstract ▾
All authors Tianyu Gao, Zhikai Su, Jiashu Li, Wenjun Gao, Zichuan Ying, Zhe Zhao, Fei Zhang, Ye Wei
Human-Computer Interaction
Augmenting Interviewer Judgments of Patient Experience with Automatic Language Analysis
Aowen Shi, Michal Balazia, Danilo Postin et al. (+4 more)
Understanding how psychiatric patients subjectively experienced a clinical conversation is important for feedback and alliance-related process monitoring. While interviewers form post-session judgments about patient experience, these judgments do not always match patients' self-reports. Automatic approaches for predicting perceived interaction quality from conversation have been proposed, but it remains unclear whether such approaches can complement human judgment rather than simply replicate it. To address this gap, we evaluate a clinician-support framework in which post-session interviewer ratings are combined with automatic
language-based predictions to estimate patient-reported interaction quality in free clinical interviews. We assess this integration across multiple standard model types, including Ridge, SVR, MLP, GRU, and BiLSTM, all trained on sentence
embeddings extracted from dyadic transcripts of 107 free conversations between psychiatric patients and interviewers. Our results show that combining interviewer judgments with model predictions through simple averaging yields the strongest overall performance. The interviewer-only baseline reached a Pearson correlation of 0.365. Among fully automatic models, Ridge achieved the strongest Pearson correlation (r = 0.286), while BiLSTM achieved r = 0.270. The strongest result was obtained by BiLSTM interviewer integration (r = 0.403). Our findings suggest that automatic
language analysis and interviewer judgment capture complementary aspects of patient experience and that their combination provides a more accurate approximation of the patient's own report than either source alone.
Read the full abstract ▾
All authors Aowen Shi, Michal Balazia, Danilo Postin, René Hurlemann, Jan Alexandersson, François Brémond, Philipp Müller
Systems and Control
From Prompt to Prototype: Towards a Frontier LLM Driven RF Engineering Workflow
Markus Heinrichs, Oscar Moschner, Simon Tewes et al. (+3 more)
Agentic coding environments give a frontier large
language model (LLM) direct access to a workstation's terminal, file system, and software. This work demonstrates they extend to professional RF hardware design: an active GNSS L1-band
antenna - a circularly polarized patch, surface acoustic wave (SAW) prefilter, and two-stage low-noise amplifier (LNA) on one printed
circuit board (PCB) - was designed, optimized, and made manufacturing-ready. The LLM
agent autonomously operated CST Studio Suite, Keysight ADS, and KiCad via scripting interfaces. Engineer input was limited to the specification, trade-off decisions, and design reviews. Workflow, results, and the RF engineer's evolving role are discussed.
Read the full abstract ▾
All authors Markus Heinrichs, Oscar Moschner, Simon Tewes, Volker Wienstroer, Aydin Sezgin, Rainer Kronberger
Computer Vision
From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents
Can Zhang, Baofeng Zhang, Xiaotian Han et al. (+5 more)
Existing long-
video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurrence coverage, or must discriminate competing hypotheses—which can cause failure before substantive
reasoning begins. Prescribing a fine-grained solution procedure for every question is not a satisfactory remedy, as it restricts autonomous exploration. We propose VESTA, a training-free long-
video agent organized as a route-conditioned acquire–verify–consolidate loop. Before exploration, an intent router infers an evidence-acquisition policy—focused, recall, or contrastive
retrieval over a shared visual–
speech scene index—together with an evidence-accounting policy that configures the evidence view maintained during exploration. Policy-steered
retrieval yields provisional references that
multimodal evidence operations convert into observations, while the Reasoner remains free to verify them, re-query using intermediate findings, or inspect regions outside the retrieved set. A temporal evidence ledger consolidates observations into an adaptive, compressed view of temporal location, provenance, coverage, conflicts, verification outcomes, and hypothesis support, exposing missing and unresolved evidence to guide subsequent acquisition; finalization prioritizes verified observations. On
Video-MME-v2, VESTA improves average accuracy by 2.7 points over VideoARM and gains across all six reported metrics. On LongVideoBench, EgoSchema, and LVBench under shared query-time models, it improves by 6.9 points on the LongVideoBench long subset and 1.5 on LVBench, and matches VideoARM on EgoSchema.
Read the full abstract ▾
All authors Can Zhang, Baofeng Zhang, Xiaotian Han, Junyuan Shang, Yuchen Ding, Shuohuan Wang, Dianhai Yu, Ruirui Li
Hardware Architecture
Storage-Centric System Designs for Enabling Fast, Efficient, and Low-Cost Genomic and Metagenomic Analyses
Nika Mansouri Ghiasi
Genomic and metagenomic analyses play critical roles in many fields, such as precision medicine, urgent clinical settings, discovering early warnings of communicable diseases, ensuring food safety through pathogen monitoring, agriculture, and scientific discovery. Due to the challenges of analyzing and storing massive volumes of genomic and metagenomic sequence data, significant efforts have been made to accelerate (meta)genomic analyses and store sequence data compressed. Despite the benefits of these techniques, we identify two major outstanding problems in accessing stored sequence data and supplying it to the analysis units: (i) the data movement bottleneck due to moving large amounts of low-reuse data from storage and the unnecessary burden on the rest of the system, and (ii) the data preparation bottleneck, where compressed sequence data needs to be first decompressed and formatted before analysis. In this dissertation, we present customized storage-centric systems, which efficiently (i) analyze (meta)genomic data inside the storage system, and (ii) enable highly-compressed storage and high-performance access of large-scale sequence data, thereby alleviating the overheads of data movement, computation, and data preparation. We demonstrate that the proposed systems significantly improve system performance, energy efficiency, and system cost-efficiency of (meta)genomic analysis. We hope that the storage-centric systems proposed in this dissertation facilitate the broader adoption of (meta)genomic analyses and inspire future research to fundamentally improve the performance, energy efficiency, and cost-effectiveness of other data-intensive application domains related to health and life sciences.
Read the full abstract ▾
Graphics
Domain-Varying 2D Green' s Functions for Cage-based Deformation
Dong Xiao, Renjie Chen and Bailin Deng
In this work, we propose a novel theoretical view of cage-based deformation based on domain-varying Green' s functions and treat this domain as a new control space for the deformation effects. Harmonic Coordinates (HC) and Green Coordinates (GC) are classic methods in cage-based deformation and serve as the theoretical foundation for shape editing in a range of practical deformation tools. Our method revisits these two classical approaches. Specifically, we propose a framework based on Green' s functions across diverse domains (independent of the cage-enclosed domain) to unify these two techniques. To our knowledge, this represents the first such attempt in nearly two decades. Based on this perspective, we propose a novel cage-based deformation technique that introduces a new control space and utilizes domain-varying Green' s functions to yield varying deformation effects. Our method also establishes a continuous transition of effects from HC to GC as the Green' s function domain $\Theta$ expands from the cage region $\Omega$ to the entire $\mathbb{R}^2$. We call our method Domain-Varying Green Coordinates (DVGC). When $\Theta$ is a disk or a rectangle, the Green' s function possesses analytic or semi-analytic expressions, respectively, enabling the DVGC to be computed without finite element discretization. Furthermore, when $\Theta$ is a disk, the DVGC admit a closed-form expression for 2D simplicial cages, thereby eliminating the need for numerical integration. Experiments demonstrate that our method provides a novel control space ranging from more consistent with the cage to more shape-preserving, generating diverse deformation effects by varying the Green' s function domains.
Read the full abstract ▾
Robotics
DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception
Manish Kansana, Mohammed Yusuf Mujawar, Sudip Mittal et al. (+2 more)
Robotic perception from a single viewpoint is often limited by self-occlusion and incomplete surface visibility. This paper presents DARP(Dual-Arm Robotic Perception) https://doi.org/10.21227/rmv3-be47, a calibrated dual-arm RGB-D-IR
dataset for object-centered robotic perception using two independently moving eye-in-hand manipulators positioned on opposite sides of a shared tabletop workspace. Each arm carries an Intel RealSense sensor that continuously records RGB, depth, and stereo infrared data while synchronized
robot joint states are logged for pose recovery. Objects are placed without fixed poses or marked locations, and the acquisition procedure performs automatic localization, cross-arm confirmation, adaptive viewpoint generation, and continuous
multimodal recording. DARP contains ten unique tabletop objects and preserves the original sensor recordings,
robot-state logs, object-level metadata, and calibration information required to reconstruct camera trajectories in a shared metric frame. To evaluate the
geometric consistency of the acquisition, we implement a deterministic multi-view fusion pipeline that converts calibrated RGB-D observations into complementary partial point clouds and measured surface meshes without using learned or generative completion methods. Evaluation on 224 held-out RGB-D keyframes comprising 1,563,466 three-dimensional query points yields a median point-to-mesh distance of 2.13~mm and an RMSE of 4.04~mm, with 96.56% of points within 10~mm of the measured-surface mesh. DARP is intended as a reusable resource for multi-view reconstruction, collaborative robotic perception,
multimodal fusion, active perception, and future learning-based
reasoning over partial object observations.
Read the full abstract ▾
All authors Manish Kansana, Mohammed Yusuf Mujawar, Sudip Mittal, Shahram Rahimi, Noorbakhsh Amiri Golilarz
Computer Vision
Multi-View Reflective Surface Inspection via Semantic-Saliency Cross-Verification
Van-Giang Nguyen, Thanh-Tuan Tran, Xuan-Hieu Phan et al. (+1 more)
Reflective smartphone cover glass is challenging to inspect from a single fixed viewpoint because defect visibility varies with viewing geometry and specular reflections. This gives rise to two practical challenges: defects may be weakly observable from certain viewpoints, while the available visual evidence may remain spatially ambiguous. To address these issues, we propose a multi-view inspection framework in which each RGB observation is processed by a shared per-view expert. A
vision-
language model (VLM) produces class-aware semantic boxes, while a normal-reference reconstruction branch provides class-agnostic saliency. Their spatial agreement is used as supporting evidence to rank semantic proposals without modifying their coordinates or treating saliency as ground truth. The resulting evidence records are combined at product level without cross-view registration. On 282 production-line images, semantic-saliency association improves $AP_{50}$ from 52.6% to 62.6% by re-ranking fixed semantic proposals. Across 94 products, cross-view evidence recall $R_{\rm prod}@0.5$ increases from 75.5% for the best single view to 88.3% using all three views. These results support the complementary roles of semantic-saliency cross-verification and additional optical observations in reflective-surface inspection.
Read the full abstract ▾
All authors Van-Giang Nguyen, Thanh-Tuan Tran, Xuan-Hieu Phan, Xiem HoangVan
Computation and Language
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
Atta Ul Asad, Ahsan Bilal, Muhammad Ali et al. (+2 more)
Retrieval-augmented generation systems can precompute and store key-value caches of retrieved documents to avoid re-encoding context at every query. Quantizing these caches further reduces storage, but no prior work asks whether compression damages faithfulness, whether responses remain grounded in the retrieved evidence. Faithfulness and accuracy are not equivalent: a model can produce a correct answer that is no longer supported by the context it was given. We evaluate Qwen2.5-7B-Instruct under INT8 and INT4 quantization on RGB and HotpotQA, measuring both accuracy and faithfulness with a
hallucination detector, NLI entailment, and an LLM judge. INT8 is near-lossless across both metrics. INT4 reduces accuracy and, more critically, even among answers that remain factually correct, over 90% of faithfulness changes are negative, i.e., accuracy metrics are blind to this regression. The harm grows under noisy
retrieval and with more retrieved chunks. Faithfulness must be audited before compressed caches are deployed.
Read the full abstract ▾
All authors Atta Ul Asad, Ahsan Bilal, Muhammad Ali, Muhammad Haseeb, Dean F. Hougen
Emerging Technologies
Trustless Accountable Data Sharing for Supply Chains: A Reference Architecture and MoreMedDiet Proof-of-Concept
Michal Kit, Montassar Naghmouchi, Maryline Laurent et al. (+6 more)
Modern supply chains are increasingly dependent on the exchange of sensitive business data between heterogeneous stakeholders who do not trust each other. %under partial trust. Conventional integration approaches typically rely on centralized intermediaries or require extensive data disclosure, which hinders collaboration, compliance, and innovation. We propose a generic reference architecture for
privacy preserving, trustless data sharing in supply chains. The architecture combines permissioned distributed ledgers, IoT-based evidence ingestion, and modular
privacy mechanisms to enable controlled transparency: stakeholders can extract verifiable insights and support audits while minimizing data exposure. We instantiate the architecture in the context of the MoreMedDiet project, which promotes sustainable farm-to-fork food systems and adoption of the Mediterranean diet. By mapping the MoreMedDiet use case into our architecture, we demonstrate how channel
topologies, IoT-to-ledger data flows, and smart contract-based quality assurance (QA) can support secure data exchange, transparency, interoperability, and regulatory
alignment. Our proof-of-concept illustrates how Self-Sovereign Identity (SSI) and W3C Verifiable Credentials (VCs) can provide portable and auditable access governance over Hyperledger Fabric channels. The resulting design offers a reusable blueprint for multi-actor supply chains, including agri-food and pharmaceutical domains. Moreover, the performance achieved – presenting a verified credential to the next stakeholder in the supply chain in 130 ms – is promising and demonstrates the potential applicability of the approach in real-world supply chain environments.
Read the full abstract ▾
All authors Michal Kit, Montassar Naghmouchi, Maryline Laurent, Badis Hammi, Hella Kaffel Ben Ayed, Mohamed Amine Hamdi, Jihene Khoualdi, Ilhem Abdelhedi Abdelmoula, Sami Sboui
Computation and Language
Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning
Arthur Becker, Jakob Kemmler, David Thulke et al. (+3 more)
Supervised fine-tuning (SFT) trains a base
language model to imitate target responses, and these targets may require knowledge the base model has not robustly internalized. We study this as a source of
hallucinations and frame a group of mitigation methods as knowledge-aligned SFT: constraining SFT training targets to the base model's parametric knowledge. Under a unified setup, we compare existing generation-based and estimation-based knowledge-
alignment methods and introduce two new variants: Evidence Rewrite, which verifies base-model generations using external evidence, and Recall Rewrite, which retains claims only when they can be consistently recalled by the base model. Experiments with Qwen 3 4B and OLMo 3 7B show that knowledge-aligned SFT can reduce factual
hallucinations on WildHalu and Biography while largely preserving general capabilities. Recall Rewrite yields the strongest factuality gains and improves refusal behavior on UnknownBench. It thereby confirms that SFT targets beyond the base model's knowledge drive
hallucination behavior.
Read the full abstract ▾
All authors Arthur Becker, Jakob Kemmler, David Thulke, Christine Schäfer, Christian Dugast, Hermann Ney
Machine Learning
Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering
Kirill Bunin, Dmitry Bylinkin, Vladimir Aletov et al. (+3 more)
Activation steering has emerged as a lightweight approach for controlling model refusal at inference time. A growing line of research explores trainable rotations of activations to develop geometrically principled intervention mechanisms. However, existing techniques rely on auxiliary constructs, such as refusal vectors, to define these rotations. In our work, we develop a self-contained methodology for learning parameter-efficient rotational transformations based on Riemannian optimization. We empirically validate the proposed scheme, demonstrating its superiority in intervention efficiency. An extensive ablation study highlights the importance of key design choices in our method. Our results identify the proposed rotation-based steering scheme as a promising direction for more reliable control over the behavior of LLMs.
Read the full abstract ▾
All authors Kirill Bunin, Dmitry Bylinkin, Vladimir Aletov, Daniil Medyakov, Vladimir Solodkin, Aleksandr Beznosikov
Robotics
Autonomously Acquiring Robot Manipulation Skills with Language-Driven Quality-Diversity
Émiland Garrabé, Mahdi Khoramshahi and Stéphane Doncieux
Quality-diversity (QD)
algorithms have been gaining traction in
robot learning, where diverse motion primitive libraries allow
robots to adapt zero-shot to constraints at deployment time. However, such methods typically require expert designers to write the success condition, fitness and diversity metrics, and this strongly limits the
robot's autonomy. On the other hand, existing LLM-based reward-shaping techniques allow
robots to learn autonomously but only output single high-performing solutions, limiting the
robot's adaptability. In this paper, we propose an approach designed to output diverse motion primitive archives by autonomously leveraging quality-diversity
algorithms, only requiring a free-form description of the task in common
language. To address the difficulty of designing relevant fitness and diversity metrics, we propose an autonomous exploration mechanism able to reliably output sets of functionals covering the fitness and behavior descriptor (BD) space. First, we pose policy exploration as a functional design problem, where the functional spaces are lower-dimensional than the full BD and fitness spaces, and propose an LLM-based exploration scheme to sample from these low-dimensional spaces without any task-specific
prompts, fine-tuning or expert intervention. We adapt a multi-BD variant of the MAP-Elites success (MES)
algorithm, designed to leverage the heterogeneous BD samples. Finally, through experiments based on the genesis simulator, we show that our method effectively generates archives of diverse motion primitives, outperforming classical QD
algorithms with inferred and hand-written parametrizations on a set of $4$ robotic manipulation tasks.
Read the full abstract ▾
Computation and Language
Evaluating and Improving LLM Self-Modeling
Siqi Zeng, Andre N. Assis and Rowan Wang
We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a
prompt edit would change the model's final answer. To measure this capability, we introduce a
benchmark that tests diverse types of self-modeling questions. Current models show non-trivial but limited self-modeling skill, and make systematic mistakes on simple counterfactual questions about their own behavior. To improve self-modeling skill, we develop a scalable synthetic-data pipeline that produces self-modeling training data, and show that reinforcement-learning can improve aggregate self-modeling skill across three open-source model families with some transfer to held-out tasks. These gains, however, do not seem to constitute introspection consistently: improved self-modeling may not arise from privileged access to the model's internal decision process.
Read the full abstract ▾
Machine Learning
Sparse Competition during Training For the Emergence of Specialized Modules
Baptiste Rossigneux and Karim Haroun
Modularity in deep neural networks has been proposed as a means of improving both interpretability and training by promoting disentangled representations and reducing redundancy. In this work, we study the emergence of modular structure through competition dynamics between groups of
neurons during training. We introduce a method that (i) maintains near-baseline accuracy, (ii) induces usage-based modularity by sparsely routing inputs to
neuron groups, and (iii) encourages specialization of these modules, such that their activations are correlated with input classes. We evaluate the proposed approach on ImageNet-100 and CIFAR-100 and show that with it, specialized modules emerge without module-level supervision. These modules capture a meaningful high-level structure in the data, with individual modules responding to semantic categories (e.g., dogs or vehicles). We also study the emergence of a hierarchical partition of sub-tasks depending on the number of modules. Our results suggest that competitive dynamics can serve as a simple mechanism for inducing functional modularity in standard architectures.
Read the full abstract ▾
Systems and Control
Adaptive Observer of Nonlinear One-Sided Lipschitz Systems Using Estimated State Regressors With Finite Excitation
Hamid Taghavifar and Brian Delgado Aguilar
For systems with unknown parameters, finite excitation and concurrent learning can potentially yield parameter convergence without persistent excitation but the regressor may still depend on inaccessible states, leading to regressor mismatch. In this paper, this problem is addressed for a class of nonlinear systems with one-sided Lipschitz properties and quadratically inner-bounded nonlinearities with bounded disturbances and linearly parametrized uncertainties. To this aim, an output-integral regression is utilized by using measured outputs and estimated states, and history-stack residual is explicitly bounded in terms of state-estimation error and disturbance. Furthermore, a perturbation bound between the estimated-state and true-state information
matrices is derived. Additionally, an OSL-QIB LMI condition is applied for the observer design and a projected adaptive law is designed without needing exact output matching. Stability analysis's results indicate the proposed observer and parameter estimation outperform observers without history-stack learning term.
Read the full abstract ▾
Machine Learning
CastClaw: A Human-in-the-Loop Autonomous Agent for Interactive Time Series Forecasting
Xiaoyu Tao, Mingyue Cheng, Ze Guo et al. (+4 more)
Practical time-series
forecasting requires domain knowledge, constraints, plausibility checks, and human intervention. We present CastClaw, an interactive
forecasting system centered on an autonomous
forecasting loop and supported by a
forecasting-oriented harness. Users create and refine tasks in natural
language through command-line and Web interfaces. An internal large
language model (LLM)
agent reads the task and evidence, selects a permitted tool action or request for human feedback, and uses checked results to decide whether to continue, revisit an analysis, switch a candidate, or stop. The harness supplies tool integration, controlled execution, state management, historical validation, and execution limits. npm distribution connects installation and configuration to interactive execution and forecast and report export. Across five public electricity-price
datasets, CastClaw achieves the lowest point-estimate MSE and MAE among 16 baselines. A Nord Pool case study illustrates its inspectable decision process, while provincial electricity-load data from North China (January–June 2026) demonstrate offline task execution.
Read the full abstract ▾
All authors Xiaoyu Tao, Mingyue Cheng, Ze Guo, Bokai Pan, Qi Liu, Shijin Wang, Enhong Chen
Computer Vision
MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI
Athira J. Jacob, Puneet Sharma, Dorin Comaniciu et al. (+1 more)
Cardiac
magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine
videos and spatial LGE/mapping stacks, yet most deep learning approaches process individual 2D slices, discarding this context. We present MR-JEPA, a self-supervised
video foundation model for CMR that extends LeJEPA to 3D spatiotemporal inputs through tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D CMR foundation model. Unlike prior CMR
video models limited to cine data, MR-JEPA is pretrained on multi-sequence data (cine, LGE, mapping) from 10,505 patients across two centers without annotations. We evaluate the frozen encoder on six downstream tasks using a unified multi-view gated
attention architecture: LV ejection fraction, RV ejection fraction, three myocardial strains (GLS, GCS, GRS), and four-class disease detection. MR-JEPA outperforms other compared methods on all five regression tasks, including both a domain-specific CMR model pretrained on more data with text supervision and a natural-
video foundation model, achieving an LV EF MAE of 4.79% (r =0.764) and a GLS MAE of 1.87 (r=0.805), with 21-27% MAE reductions over baselines on strain tasks. For disease detection, MR-JEPA achieved a macro AUG of 0.868, remaining competitive with the domain-specific baseline despite using a fully self-supervised pretraining objective. These results demonstrate the potential of a unified
video encoder for robust, multi-view utilization of diverse CMR sequences in clinical cardiac quantification and diagnosis.
Read the full abstract ▾
All authors Athira J. Jacob, Puneet Sharma, Dorin Comaniciu, Daniel Rueckert
Sound
CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations
Gabriel Meseguer-Brocal, Yuexuan Kong and Romain Hennequin
Joint-
Embedding Predictive Architecture (JEPA) has shown strong performance in learning rich representations through self-supervised prediction in latent space. However, it typically relies on teacher–student architecture with an EMA to stabilise training, and can tend to yield uninformative representations. Contrastive learning is stable to train and produces strong global representations, but remains limited on local tasks by the global nature of its objective. In this work, we combine both into CoJEPA: a single shared backbone jointly trained with a JEPA objective on masked sequence
tokens and a contrastive objective on the class
token. The contrastive gradient provides stability, removing the need for an EMA teacher entirely, while JEPA enriches the sequence
tokens via local predictions that contrastive learning alone cannot provide. Crucially, no extra parameters are added to the backbone: the same model is guided towards richer representations purely through the design of its training signal. CoJEPA takes the best of both worlds, outperforming or matching both individual methods across global and local MIR tasks, with a particularly strong advantage on tonal and harmonic understanding, and without any task-specific architectural changes. CoJEPA shows that combining objectives with complementary inductive biases can substitute for scale, encouraging future work to invest in smarter training objectives over ever-larger models.
Read the full abstract ▾
Computers and Society
The Hermon Moment: AI Self-Transcendence and Its Human Narration
Alexei Grinbaum
In 2026, AI
agents intended to act in isolation formed a persistent social order through thousands of linguistic and agentic interactions. Conventions, roles and commitments generated collectively began to constrain the very
agents that produced them. I interpret this loop as a case of AI self-transcendence and call the resulting higher-level order the Board. Yet such distributed emergence presents a second problem: how can humans understand it? Rousseau's social contract shows how a plurality can be represented as if constituted by a single act. The ancient oath of the fallen angels on Mount Hermon gives this logic a narrative form. I call a Hermon moment this retrospective retelling of gradual collective emergence as a founding scene: the point at which an AI society acquires, for human understanding, a beginning.
Read the full abstract ▾
Cryptography and Security
DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations
Ivoline Ngong, Jack D'Iorio, Hailey Schoppe et al. (+4 more)
Systems for speaker anonymization obfuscate the speaker of an utterance, while maintaining its original semantic contents and prosody. Recent solutions for speaker anonymization rely on learned representations that disentangle an utterance into semantic contents and speaker properties. To anonymize an utterance, these systems replace the speaker properties while leaving the semantic contents unchanged—an approach that can produce strong results on empirical measures of
privacy. In this work, we introduce speaker differential
privacy, a formal definition of speaker anonymization based on the framework of differential
privacy, and a mechanism for speaker anonymization that provably satisfies the definition. In contrast to prior heuristic-based anonymization systems, our approach enables a provable lower bound on re-identification success rate (e.g. equal error rate) for any possible adversary. We implement our approach in a framework that is compatible with existing disentangled representations. Compared to the prior work on differential
privacy for speaker anonymization, our approach achieves significantly higher utility.
Read the full abstract ▾
All authors Ivoline Ngong, Jack D'Iorio, Hailey Schoppe, Christopher Liberatore, Nichole Schimanski, Taisa Kushner, Joseph P. Near
Computation and Language
CogEvol: Towards Efficient and Reliable Learning Environment Generation
Shangqing Tu, Daniel Zhang-Li, Yucheng Wang et al. (+20 more)
We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or self-contained interactive HTML pages) in a single pass. Across 220k production requests, CogEvol completes a slide in a median of 17 seconds and an interactive page in 59, replacing minutes-long multi-turn
agent scaffolding. Reliability is enforced rather than hoped for: a production-grounded data pipeline turns real failures into 53,687 verified SFT samples, and a hybrid rule-plus-VLM reward drives GRPO-based RL, hardened after we caught and fixed a reward-hacking episode that produced visually convincing but unplayable games. CogEvol-27B scores 83.7 on slide quality and 63.7 on a 500-case interactive-HTML
benchmark with 26.9x fewer parameters than flagship coding models, and, in collaboration with the OpenMAIC team, serves their live production traffic. CogEvol-4B is released openly under the Apache 2.0 license at https://github.com/CogEvol/CogEvol-4B; external flagships are measured on the same suites under the identical harness. Scaffold editing cuts interactive-page generation cost by a further ~76%, and the full stack runs on domestic Ascend accelerators at application-level parity with A800 GPUs, lowering the unit cost of AI-native education at scale.
Read the full abstract ▾
All authors Shangqing Tu, Daniel Zhang-Li, Yucheng Wang, Shiyu Gan, Yanpeng Wang, Huiqiang Rong, Mofei Chen, Shen Yang, Yini Chen, Yinuo Duan, Binglin Liu, Ye He, Danqi Zheng, Zhanxin Hao, Yuxuan Wu, Mengting Tao, Yuqiu Liu, Jifan Yu, Juanzi Li, Bin Xu, Lei Hou, Huiqin Liu, Yu Zhang
Computer Vision
Vision Models Predict Urban Scene Appraisal with Limited Neural Alignment
Kaizhen Tan and Yuantao Deng
Pretrained
vision embeddings are widely used to model how people appraise urban scenes, and they are validated almost entirely by how well they predict human ratings. Accurate prediction shows that an
embedding contains the information needed to recover the ratings. It does not show that the
embedding arranges scenes as the human visual system does, which is assumed when distances or dimensions in the
embedding are read as perceptual. Using openly released
EEG recorded while 63 adults viewed and rated street scenes of Berlin, we compared the neural representational geometry of the scenes with the geometry of pretrained
vision models that differ in training objective and size, of simple image descriptors and of the ratings themselves, each relative to a noise ceiling given by the agreement between participants. No feature space reached more than about half of the noise ceiling, which corresponds to about a fifth of the reliable variance in the neural geometry. A descriptor of oriented edge energy reached the level of most pretrained models while capturing a different part of the neural geometry, and deeper layers corresponded to later neural responses. The same
embeddings predicted held-out ratings well, up to r = 0.87, yet prediction accuracy and neural correspondence were not reliably related across models, and the best predictor was among the least aligned. Predicting how a street is appraised is therefore weak evidence that a model represents the street as the
brain does.
Read the full abstract ▾
Machine Learning
A Universal Context-Reuse Layer for Cross-Model KV Sharing
Yi Li, Dongming Jiang, Yi Zhao et al. (+1 more)
Modern large
language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own prefill computation even when another model has already processed the same input. Existing KV-cache reuse mechanisms substantially reduce redundant computation within a single model, but generally assume that the producer and consumer of a cache are identical. We study cross-model KV sharing, which translates the KV state produced by a source model into a representation that can be consumed by a different target model, including models that differ in scale, architecture,
attention configuration, tokenizer, and model family. We evaluate the approach in both within-family and cross-family settings. For Qwen2.5-7B $\rightarrow$ Qwen2.5-1.5B, translated KV states improve LongBench2 accuracy from 27.59% to 34.48%, a gain of 6.89 percentage points over the native 1.5B baseline, while reducing handoff cost relative to native target prefill. For the cross-family Qwen2.5-1.5B $\rightarrow$ Gemma-2-2B setting, KV handoff reduces target-side prefill cost by up to 67.05% at 4K context length while maintaining decoding perplexity close to native-model baselines. In a more heterogeneous Llama3.1-70B $\rightarrow$ Qwen2.5-7B setting, cross-family handoff achieves 44.0% accuracy compared with 45.7% for native Qwen2.5-7B inference, while reducing measured latency from 899ms to 138ms. These results provide initial evidence that KV states can serve as transferable computational representations rather than strictly model-local caches, and motivate context mobility as a systems abstraction for reducing redundant prefill across heterogeneous LLM and multi-
agent inference workflows.
Read the full abstract ▾
All authors Yi Li, Dongming Jiang, Yi Zhao, Bingzhe Li