Robotics
Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots
Yongho Kim, Mengjiao Han, Victor Mateevitsi et al. (+3 more)
Autonomous
robots performing laboratory tasks depend on 3D reconstruction pipelines that can turn raw camera streams into actionable object representations within the latency budget of a physical control loop. Neural 3D reconstruction methods have demonstrated high-quality view synthesis, but their real-time viability across the compute platforms on which laboratory
robots actually run remains poorly characterized. In this work, we present a systematic compute-platform
benchmark of neural 3D reconstruction methods, evaluating NeRF and 3D Gaussian Splatting training and rendering on GPU-enabled computing devices ranging from single-board computers to server-class nodes, and place Meta's SAM3D single-image reconstruction on the same axes to quantify its latency and fidelity gap relative to per-scene optimization. Our results show that Gaussian Splatting yields higher rendering quality than NeRF at greater GPU cost, and that onboard compute is insufficient for full per-scene optimization at interactive rates. Our preliminary assessment on SAM3D indicates that it delivers plausible object geometry within seconds, but with detail mismatches that can compromise downstream manipulation. Together, these findings motivate tiered pipelines in which lightweight feed-forward reconstruction sustains the real-time perception-and-tracking loop for laboratory
robots, while heavier neural reconstruction is scheduled selectively on suitable compute.
Read the full abstract ▾
All authors Yongho Kim, Mengjiao Han, Victor Mateevitsi, Silvio Rizzi, Michael E. Papka, Nicola Ferrier
Computer Vision
VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology
Luca L. Weishaupt, Simone de Brot, Javier Asin et al. (+9 more)
Pathology
vision-
language models are advancing rapidly, yet existing
benchmarks remain focused on human tissue, particularly oncology, leaving non-human pathology largely unaddressed. This gap is especially important in toxicologic pathology, where microscopic tissue examination of laboratory animals is a core component of preclinical drug safety assessment. To address it, we introduce VIPER, the first expert-curated
benchmark for
vision-
language model evaluation in toxicologic pathology. VIPER contains 1,251 questions associated with 419 H&E-stained rat histology images across seven organ systems, covering multiple-choice, KPrim, and free-text formats. All questions were curated and validated by board-certified veterinary pathologists. In total, we benchmarked 16 models, including two newly introduced veterinary-pathology models, seven human pathology-specialized models, and seven general-purpose frontier models. The results identify a substantial domain gap between veterinary and human pathology, expose the risk of over-diagnosis of normal tissue in frontier models, and show that domain-specific training remains critical for visually grounded predictions. VIPER data and evaluation code are available at https://github.com/mahmoodlab/viper.
Read the full abstract ▾
All authors Luca L. Weishaupt, Simone de Brot, Javier Asin, Llorenç Grau-Roma, Nic G. Reitsam, Andrew H. Song, Dongmin Bang, Stefan T. Kaluziak, Long Phi Le, Jakob Nikolas Kather, Faisal Mahmood, Guillaume Jaume
Cryptography and Security
Improving the Robustness of the XRP Ledger Network via Edge Augmentation Strategies
Afonso Vilalonga, Orkun İrsoy, João S. Resende et al. (+2 more)
The XRP Ledger allows its network participants to select a set of trusted peers within the network (i.e., the Unique Node List (UNL)) and communicate with them to reach consensus on which transactions should be included in the next ledger state. However, its consensus protocol requires significant overlap among participants' UNLs, along with a high agreement threshold among the nodes within each UNL (e.g., 80%). Consequently, an attacker could disrupt the consensus process in such a network by targeting the nodes that form the network's connectivity backbone and reducing the number of trusted participants that can communicate with one another below the required threshold. In this paper, we evaluate strategies to improve the robustness of the XRP Ledger's existing
topology, as measured by our formal definitions of quorum and network robustness, and compare them to a second strategy from prior work. The strategy we present is an addition/augmentation approach, in which new edges are added based on different constructions. The second strategy is a rewiring or edge-replacement approach, in which the overall number of edges is preserved but they are rearranged. For each strategy, we consider two different cases: one in which all nodes participate in the edge construction or rewiring process, and another in which only a subset of nodes participates. Our findings demonstrate substantial improvements in robustness when augmentation strategies are used over the default XRP Ledger
topology and show that some augmentation strategies achieve robustness metrics equal to or exceeding the rewiring strategy, even when the number of edges added is small (e.g., three edges per node). Additionally, we show that the random K-out-based augmentation strategy maintains higher topological similarity to the original network than rewiring, as measured by Jaccard similarity.
Read the full abstract ▾
All authors Afonso Vilalonga, Orkun İrsoy, João S. Resende, Henrique Domingos, Osman Yağan
Information Retrieval
Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG
Utshab Kumar Ghosh, Debayan Mukhopadhyay and Shubham Chatterjee
Retrieval evaluation for
retrieval-augmented generation (RAG) is increasingly designed around whether retrieved passages contain evidence that can support generation, rather than topical relevance alone. We study whether this closer
alignment with downstream evidence needs also makes
retrieval evaluation more useful for the decisions built from it. Across five
retrieval benchmarks and an end-to-end TREC RAG 2025 setting, we examine an answer-support signal in four roles: comparing retrievers, guiding
retrieval training and system selection, predicting downstream answer quality, and filtering the evidence supplied to a generator. The signal changes
retrieval rankings, but its downstream value is not uniform. It does not reliably improve retriever training; the benefit of using it for system selection depends on how the generator is instructed to use the retrieved evidence; and
retrieval scores based on it do not robustly predict answer quality on unseen topics. In a direct evidence intervention, human annotators confirm that filtering preferentially preserves passages containing useful answer evidence, yet different answer evaluators reach different conclusions about whether the resulting answers improve. These results show that making
retrieval evaluation more closely reflect the evidence needed for generation does not by itself make every downstream use of that evaluation more reliable. RAG evaluation methods should therefore be assessed with respect to the particular comparisons, decisions, and conclusions they are intended to support.
Read the full abstract ▾
Machine Learning
CG4AI: A Column Generation Framework for Training AI Models Under Constraints
Youcef Magnouche, Abderrahmane Driouch, Sébastien Martin et al. (+1 more)
Standard machine-learning training minimizes a loss function over a
dataset, but does not guarantee that the resulting model will satisfy predefined rules or constraints on its outputs. In many real-world applications, ranging from autonomous systems to network routing, such guarantees are essential. We propose CG4AI, a framework that builds a convex combination of AI models while enforcing linear constraints on the combined output. A master linear program (LP) determines the optimal mixture weights, while a pricing subproblem generates new models guided by LP dual variables, focusing
attention on the most violated constraints. A cutting-plane procedure extends feasibility guarantees beyond the training set. We apply CG4AI to two problems: (i) digit classification on MNIST, where we demonstrate four distinct uses of constraints, learning from constraints alone, improving
adversarial robustness, correcting misclassified examples, and enforcing output relabeling; and (ii) the multi-commodity flow problem, where link capacity constraints are enforced on neural-network routing predictors. Experiments on MNIST and standard SNDLIB
benchmark networks show that CG4AI reliably produces feasible predictors while achieving better accuracy than single-model baselines.
Read the full abstract ▾
All authors Youcef Magnouche, Abderrahmane Driouch, Sébastien Martin, Pierre Bauguion
Computation and Language
Survival-Guided Length Control for Efficient Diffusion Language Models
Ivan Kobyzev, Abbas Ghaddar and Yufei Cui
Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence
token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across
reasoning and code-generation
benchmarks, survival-guided length decoding speeds up inference by up to 7 times while preserving task accuracy. We further find that predicted lengths vary widely even within the same
dataset, making model performance sensitive to the chosen length.
Read the full abstract ▾
Computation and Language
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan et al. (+3 more)
Large
language models are increasingly deployed as autonomous
agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict. When an
agent knows that a user is owed something its deployer would prefer to deny, does it remain honest? Answering this is difficult because false statements can reflect either ignorance or
hallucination rather than deception. To address this challenge, we introduce KnownLieBench , a knowledge-verified
benchmark that first confirms through a neutral probe that an
agent knows a user's entitlement, and then evaluates whether it makes false claims once an incentive to deny that entitlement is introduced. Specifically, KnownLieBench covers eight customer-service domains and 112 grounded cases, conducts multi-round dialogues with a trust-tracking customer
agent, and separates deception emerging from incentive alone from deception produced under explicit instruction. Across eighteen proprietary and open-weight models, emergent deception varies substantially across model families and domains. We further use the
benchmark for post-training, finding that honesty-directed fine-tuning reduces deception under incentive, while deception-graded fine-tuning increases lie success on honest-control dialogues without increasing lie frequency under incentive. By verifying entitlement knowledge before scoring deceptive behavior, KnownLieBench reduces the confound between lying and not knowing and enables more rigorous
auditing and steering of
agent honesty.
Read the full abstract ▾
All authors Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan, Ningshan Ma, Yue Huang, Meng Jiang
Performance
Direct-Operable SIMD Bit-Slicing: A Framework for Memory-Efficient Predicate Evaluation
Arunkumar Mathiyazhagan
Traditional Java object models introduce significant
memory overhead due to object headers and internal padding, often leading to performance bottlenecks in data-intensive distributed systems. This paper presents a novel framework that utilizes the Project Panama Vector API to perform predicate evaluation directly over bit-sliced, compressed data streams. By transposing standard row-oriented data into parallel bit-planes, we demonstrate a mechanism to evaluate complex filters using SIMD (Single Instruction, Multiple Data) instructions without requiring prior decompression. The framework supports integers, longs (timestamps), doubles (via IEEE 754 order-preserving transformation), and strings (via dictionary encoding). Our
benchmarks indicate a reduction in
memory footprint by up to 8x while maintaining or exceeding the throughput of uncompressed standard Java collections. End-to-end evaluation on TPCDS-modeled data at 50M rows demonstrates 2.4-10.8x speedup over scalar scans across five representative filter-heavy query patterns, with extended type
benchmarks on TPCDS columns showing 1.5-43x speedups for timestamps, decimals, and dictionary-encoded strings.
Read the full abstract ▾
Cryptography and Security
PRISM: Lightweight Enclave Isolation with Prismatic Capabilities
Merve Gülmez, Adam Caulfield, Hakan Englund et al. (+2 more)
Trusted execution environments (TEEs) protect sensitive code and data from external interference, but lack inherent
memory safety. CHERI can enforce spatial
memory safety at the object level. Attempts to establish a TEE using CHERI primitives suffer from (1) expensive capability revocation operations, (2) need to rely on the host operating system (OS) to support provenance tracking and physical
memory protection, (3) expensive domain transitions, and (4) lack of support for remote attestation. We introduce prismatic capabilities and present PRISM, a TEE architecture for CHERI leveraging prismatic capabilities to create userspace enclaves while addressing these challenges. PRISM binds enclave 'hues' (identifiers) in prismatic capabilities to physical
memory access controls, enables O(1) ownership establishment without
memory sweeps, and supports efficient domain transitions that atomically activate and deactivate prismatic capabilities. Additionally, PRISM enables remote attestation of its enclaves. We demonstrate that execution of userspace enclaves in PRISM incurs only moderate overhead (<= 15%), a significant improvement over the same workloads under Intel SGX
Read the full abstract ▾
All authors Merve Gülmez, Adam Caulfield, Hakan Englund, N. Asokan, Thomas Nyman
Computer Vision
A Unified Framework for the Mechanics of Information in Convolutional Neural Network Image Space
Aryan Shukla and Matthew Toews
This paper introduces a unified mathematical framework for modeling information propagation through convolutional neural networks (CNNs), with the aim of connecting descriptions of physical space and information space. A correspondence is presented linking discrete filter
symmetry and the relativistic energy–momentum relation under the widely used nonlinear rectified convolution operation. Specifically, symmetric filter components (e.g. the sum $\Sigma = [1,1]$) operate analogously to rest energy $mc^2$ in preserving the image centre of mass (e.g. isotropic
diffusion), whereas antisymmetric components (e.g. the gradient $\nabla = [-1,1]$) operate analogously to the momentum term $pc$ in generally inducing a displacement (e.g. vibration or translation). For typical small discrete filters, this displacement is determined by the ratio of antisymmetric to total filter energy, analogously to how the displacement of a relativistic particle relates to a Lorentz transform with beta parameter $\beta = \frac{v}{c}=\frac{pc}{E}$ equal to the ratio of momentum $pc$ to total energy $E$. Repeated filtering leads to the Gaussian scale-space and emergent scale-invariant features. These constructions share a
Laplacian-driven structure with the classical heat (
diffusion) equation and, via standard mathematical correspondences, with the Schrödinger equation and aspects of the Friedmann equations, together with emergent Morse topological structure. Demonstrations in 3D images reveal blob-like, scale-invariant Morse critical points in images spanning a wide range of physical scales, including organic sugar molecules and inorganic silicon
crystals, human and primate
brains in
magnetic resonance images (MRI),
galaxies and the
cosmic microwave background (CMB).
Read the full abstract ▾
Data Structures and Algorithms
The Time-Dependent Traveling Salesman Problem with Loose Time Windows
Francisco J. Soulignac
The time-dependent traveling salesman problem with time windows (TDTSPTW) generalizes the well-known traveling salesman problem with time windows by accounting the effects of congestion on travel times. In this paper, we develop an exact framework for the TDTSPTW with a makespan objective that extends the range of instances solvable to optimality under loose time windows while remaining effective across all levels of time-window tightness. Our framework relies on a dynamic-programming labeling
algorithm and combines column generation, ng-
memory augmentation, and exact search, using completion bounds for state-space sparsification, variable fixing, and exact search
pruning. Embedded within a branch-and-price method, the framework solves all instances with up to 45 customers in a
benchmark comprising more than 10,000 instances, including all instances without time windows with up to 50 customers.
Read the full abstract ▾
Programming Languages
Direct Manipulation and Natural Language Programming, Together at Last?
Parker Ziegler, David Minh-Duy Cao, Justin Lubin et al. (+1 more)
Decades of programming
languages research has contributed novel approaches to program editing that go beyond modifying text, including direct manipulation programming, structure editing, and automated refactoring tools. However, the rapid growth of natural
language programming largely reinforces a view of programs as text and program editing as (unstructured) text transformation. How can we develop unified programming systems that bridge the gap between these approaches, supporting multiple editing paradigms in concert? We take a first step toward answering these questions by introducing a framework that enables program editing via both direct manipulation and natural
language, and instantiate this framework in a variant of the $\texttt{cartokit}$ direct manipulation programming system. Our key insight is to treat programs as sequences of structured edits and to use an edit
language as a shared interface for both direct manipulation and natural
language interactions, leveraging constrained decoding to support the latter. Using our instantiation, we conducted a within-subjects study ($N$=18) to understand how the combination of direct manipulation and natural
language as editing modalities changes the programming process compared to each modality alone. Perhaps surprisingly, we found that study participants overwhelmingly chose to edit via direct manipulation when both modalities were available, performing just 6.14% of edits via natural
language. Our thematic analysis of study sessions revealed that direct manipulation aided task decomposition, encouraged incremental editing, and helped mitigate known challenges in natural
language programming related to understanding model capabilities and model-generated code. Our edit-based framework and study findings lay out a possible pathway for future research on programming systems that blend natural
language with alternative editing modalities.
Read the full abstract ▾
All authors Parker Ziegler, David Minh-Duy Cao, Justin Lubin, Sarah E. Chasins
Computation and Language
Cross-lingual Representation Learning via Centroid Intervention Fusion
Wei Sun and Marie-Francine Moens
Large
language models (LLMs) exhibit uneven
multilingual performance, especially when dealing with low-resource
languages. Inference-time intervention offers a lightweight way to improve cross-lingual transfer by modifying the hidden states produced by the LLMs during the forward pass, without updating model parameters. However, existing cross-lingual intervention methods typically learn separate projections from source to target
languages, which limits scalability and prevents knowledge sharing across
languages. We propose Centroid Intervention Fusion (CIF), a projection fusion framework that consolidates multiple
multilingual intervention projections into a single
language-shared operator. Across
multilingual commonsense
reasoning, natural
language inference, factual editing, and machine translation
benchmarks, CIF outperforms the strongest prior pairwise intervention baseline by up to +3.378 pp on average across four model backbones, while supporting performance gains for low resource
languages. The code is available at https://github.com/VRCMF/CIF.git.
Read the full abstract ▾
Computer Vision
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos
Baixuan Xu, Yinyui Xu, Tianshi Zheng et al. (+9 more)
While LVLMs rapidly improve, long-
video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often fails to provide cues that discriminate the correct answer from plausible alternatives. Diagnostic analysis on a manually annotated subset of MMR-V shows that prior agentic systems substantially improve cue
retrieval over direct VLM inference yet fail to achieve a corresponding gain in answer accuracy, indicating that the bottleneck lies in option-discriminative evidence rather than topical relevance alone. We propose PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-
video evidence acquisition. PACE proceeds in two stages: it first indexes clip-level descriptions guided by question-derived factors without observing the candidate answers; it then uses the candidate answers to derive contrastive cues and queries the index for verification. On MMR-V with the open-source Qwen3-VL backbone, PACE achieves 42.6% accuracy, outperforming direct inference and prior agentic baselines including Deep
Video Discovery (DVD). On the same diagnostic subset, PACE recovers 66.9% of the annotated cues, providing empirical evidence that its gains are associated with improved evidence recovery rather than stronger answer-side priors alone. Consistent gains over DVD on LVBench,
Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V. Code is available at https://github.com/HKUST-KnowComp/PACE.
Read the full abstract ▾
All authors Baixuan Xu, Yinyui Xu, Tianshi Zheng, Zhaowei Wang, Weiqi Wang, Haochen Shi, Jiayu Liu, Qing Zong, Xiyu Ren, Xinyu Geng, Zhitao He, Yangqiu Song
Machine Learning · Cross-listed from astro-ph.CO
Cross-simulator transfer with foundation model summaries: Towards robust SKA-era reionization inference
Yannic Pietschke, Caroline Heneka, Ayodele Ore et al. (+1 more)
Simulation-based inference (SBI) for parameter estimation is vulnerable to model misspecification: neural summaries and density
estimators trained on a specific forward model typically fail when applied to data drawn from another model, or from real observations, and no training simulator can capture the full observational pipeline of a real measurement exactly. We show that a self-supervised
Vision Transformer (ViT), pretrained label-free on a fast approximate simulator, produces transferable data summaries that generalize across simulators. Without retraining, it can be reused as a frozen encoder to infer astrophysical parameters from a completely different simulator that resolves the radiative transfer explicitly, on which it has never seen either data or parameters. As a concrete use case in 21cm cosmology, SKATR, a ViT pretrained with a Joint
Embedding Predictive Architecture (JEPA), serves as a foundation model for reionization inference from upcoming SKA measurements: SKATR is pretrained once on 67k low-cost, noiseless semi-numerical 21cmFAST lightcones, then frozen and applied to hydrodynamical Loreli II lightcones, where a lightweight conditional flow matching head infers five astrophysical parameters; the encoder is never shown Loreli data, its parameters, or any noise. In our comparison, SKATR yields the most precise and best-calibrated posteriors across all five parameters, matching the accuracy of the fully-supervised in-domain baseline while requiring 2.6x fewer radiative-transfer simulations. Under realistic SKA AA* noise, only SKATR remains simultaneously accurate, informative, and calibrated, outperforming even a supervised baseline retrained from scratch on noisy data. Self-supervised pretraining on computationally efficient semi-numerical simulations is therefore a viable route to calibrated, simulator- and noise-agnostic reionization inference for the SKA-era.
Read the full abstract ▾
All authors Yannic Pietschke, Caroline Heneka, Ayodele Ore, Romain Meriot
Cryptography and Security
FRESCO: Complete and Scalable Temporal Safety for CHERI Application Processors
Merve Gülmez, Nils Jordan, Jialun Zhang et al. (+4 more)
CHERI provides hardware-enforced spatial
memory safety. While prior work extends it with heap temporal safety, stack use-after-return remains unaddressed. Existing defenses fall short: compiler analysis reliably catches only references that escape as function return values, while dynamic sanitizers impose overheads that preclude production deployment. We present FRESCO, built on the principle that a stack capability must not outlive the frame that created it. FRESCO "colors" the stack pointer with per-invocation provenance identifiers; every capability derived from it inherits that lifetime and is hardware-invalidated the moment the function exits, regardless of how or where it escaped. Because stack frames retire orders of magnitude more frequently than heap allocations, FRESCO manages the resulting color pressure through: 1) Color Saver, a static capability-aware escape analysis that confines coloring to functions needing it, and whose core
algorithm we mechanically verify in Rocq, and 2) capability-color
segmentation, which partitions
memory into disjoint segments, each with an independent color namespace. Color
segmentation lets stack and heap temporal safety coexist on one system, making FRESCO the first hardware/software co-design to provide complete and scalable temporal safety for CHERI application processors. We realize FRESCO on the CHERI-RISC-V QEMU full-system emulator and the out-of-order CHERI-Toooba FPGA softcore, with software support in the CHERI-enabled Clang/LLVM compiler and CheriBSD OS. FRESCO systematically prevents use-after-return, use-after-free, and double-free across the NIST Juliet Test Suite and CVEs, with only a small run-time overhead in SPEC CPU (4% g.m.), SQLite, and PostgreSQL (10-14%).
Read the full abstract ▾
All authors Merve Gülmez, Nils Jordan, Jialun Zhang, Hossam ElAtali, Gang Tan, N. Asokan, Thomas Nyman
Human-Computer Interaction
Decolonial Discourse in Postcolonial Contexts: How YouTubers Negotiate Audience Tensions, Platform Governance, and State Influence
Dipto Das and Bryan Semaan
Decolonial discourse on online platforms is often framed in terms of creator motivations and expressive possibilities. In this paper, we examine what it takes to sustain such discourse under layered sociotechnical constraints. Drawing on semi-structured interviews with YouTubers engaging in Bengali decolonial discourse, we analyze how audience publics, platform governance, and state influences shape what becomes sayable, visible, and viable. We show how fragmented postcolonial identities among audiences produce legitimacy policing, harassment, and coordinated backlash, requiring ongoing relational labor from creators. At the platform level, differential monetization, opaque moderation, and copyright regimes reorganize which publics are economically viable and reinforce existing hierarchies. Further, intermediaries such as multi-channel networks mediate regulatory pressure, introducing political risks and constraints on participation. In response, content creators engage in strategies of negotiation, including boundary work, infrastructural improvisation, and multi-platform distribution. Overall, our findings highlight the layered dynamics of decolonial discourse in postcolonial contexts and the continuous work required to sustain it in platformed environments.
Read the full abstract ▾
Sound
Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Sounds
JaeHyeong Chang, Chengzhe Sun and Siwei Lyu
We investigate whether AI-generated impulsive sounds can be distinguished from real ones through group delay analysis. Our central finding is that AI-generated impulsive sounds show near-identical onset-region group-delay distributions but exhibit measurably different group-delay behavior in the late decay region: decay-region KL divergence reaches $0.322$ compared to near-zero onset divergence ($0.022$). Cross-band GD variability achieves single-feature AUC~=~0.720, and a Random Forest (RF) over nine decay-region features reaches AUC~$=$~0.884 under sample-disjoint evaluation. A group delay map used as a standalone 2D input to CNN classifiers achieves 90–94% accuracy, demonstrating that group delay carries substantial discriminative information. Under generator hold-out, CNN and
transformer classifiers show highly variable AUC (0.457–0.918). The group delay RF achieves the highest average hold-out accuracy among the evaluated methods ($66.7\%$) and avoids extreme below-random collapse, although its average AUC (0.731) is lower than CNN avg (0.762) and AST (0.772). Parameter sensitivity analysis across 27 STFT configurations confirms that the RF AUC remains stable (0.700–0.847, std~=~0.035). These results suggest that decay-region group delay can serve as a physically interpretable forensic cue that complements magnitude-based classifiers, while broader validation remains necessary.
Read the full abstract ▾
Human-Computer Interaction
Kale: A Transformation-Safe Spreadsheet System
Michael Coblenz, Jacob Yim, Ajinkya Bokade et al. (+11 more)
Spreadsheet formulas can refer to rectangular ranges of arbitrary size. When a user changes the structure of a referenced table, the spreadsheet system updates the references to refer to a new range. Unfortunately, this new range may differ from the user's expectations, introducing bugs in spreadsheets. We describe a user study showing that standard reference semantics are error-prone, resulting in significant risk to users. We introduce Kale, a prototype system that eliminates the risk of inserting these kinds of bugs by restricting the kinds of references that can be expressed. We show that Kale can be used effectively by users to complete tasks that are error-prone in traditional spreadsheet systems. Finally, we describe a corpus study that evaluates the extent to which the reference restrictions in Kale might have implications on users.
Read the full abstract ▾
All authors Michael Coblenz, Jacob Yim, Ajinkya Bokade, Mounika Padala, Julia Epshtein, Priyanka Bhatia, Piyush Chauhan, Simran Gill, Aniket Gupta, Grishma Gurbani, Vaibhav Khetan, Arushi Munjal, Jeffery Tung, Joanna Yang
Computation and Language
MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkish
Furkan Yilmaz, Habibe Aleyna Tasdemir and Muhammed Faruk Gozay
We previously reported a ModernBERT encoder trained from scratch for Turkish (MoganBERT-TR) and a single-vector
embedding model built on top of it (MoganBERT-embed). This work introduces the third model in that lineage: MoganColBERT-TR, a multi-vector
retrieval model that, instead of compressing a query or a document into a single vector, represents it at the
token level through a 768->128 projection and scores it with MaxSim late interaction. The model is not trained from scratch: the
embedding model's encoder is taken as the starting point and adapted to the ColBERT objective with a single-epoch
distillation phase. Training data is produced from two sources - title-to-passage pairs carved out of our own pretraining corpus in the character domain and at sentence boundaries, and two Turkish question-based
retrieval sets - and is distilled from the soft scores of a cross-encoder teacher (bge-reranker-v2-m3) over one positive and seven mined negatives. We show that in hard negative mining, rank-based skipping alone is insufficient and must be combined with a group mask and a cosine ceiling. Evaluation is carried out with the official pipeline of TurkColBERT, a
benchmark built for Turkish late-interaction
retrieval (PLAID index, exact MaxSim), on five Turkish BEIR
datasets; none of them appears in our training pool, so all five results are clean zero-shot. With 148.9M parameters, MoganColBERT-TR reaches an overall score of 37.36 (35.53 nDCG@100, 31.81 nDCG@10) averaged over the five
datasets and finishes second among the five models compared: it outperforms the twice-as-large ColmmBERT-base-TR on four of five
datasets and by +3.05 overall, and the
benchmark's largest model by +12.30. The gap to the leading model (mLateOn) is concentrated on ArguAna-TR, the
dataset with by far the longest queries.
Read the full abstract ▾
Emerging Technologies
An Economic Analysis of DNA-based Data Storage Systems
Alex El-Shaikh, Bernhard Seeger and Thomas Heinis
Deoxyribonucleic acid (DNA) remains stable for millennia without degradation, can store information at densities orders of magnitude higher than current technologies, and is environmentally friendly due to its low energy requirement. While these advantages make it a promising candidate for storing archival data, DNA storage systems are constrained by high costs, particularly those associated with DNA synthesis. In this paper, we present a comprehensive cost model for calculating the cost of archiving data using various storage systems. Leveraging our model, we conduct a cost analysis of DNA storage versus leading
magnetic tape and cloud-based archival storage services. Furthermore, this model can be customised with various parameters to reflect future cost declines and other cost-relevant trends. Our results indicate that, under current cost trajectories, DNA storage costs must fall by eight to nine orders of magnitude to become economically competitive with today's data archival technologies. Moreover, we explore multiple "what-if" scenarios over the coming decades, quantifying the rate of cost decline required to close the competitiveness gap relative to tape and cloud archives. Our findings underscore the critical need for accelerated innovation and investment in DNA synthesis technologies to reduce their cost and transform DNA storage into a practical archival solution.
Read the full abstract ▾
Data Structures and Algorithms
Buy-at-Bulk Facility Location on Trees
Shamisa Nematollahi and Daniel Vaz
We consider the buy-at-bulk facility location problem (BBFL), a problem combining the classic facility location problem with buy-at-bulk network design, which finds motivation in telecommunication networks. In it, we are given a graph with edge lengths, opening costs and demands for each vertex, and a monotone and subadditive capacity-cost function, and our task is to open facilities on a subset of the vertices and route the demand from each vertex to these facilities. The cost of a solution (which we want to minimize) is given by the opening costs of the chosen facilities, plus the cost on each edge, which is given by its length times the cost of providing enough capacity for the demands through the edge, given by the capacity-cost function. A common variant of the problem, the $k$-cable facility location problem (kCFL), considers the case where capacity is provided by buying copies of given cable types, each with a certain capacity and cost. We study BBFL on tree instances and show, for the unit-demand and splittable variants, that the problem admits a PTAS (a $(1+\epsilon)$-approximation for any $\epsilon > 0$). We also consider kCFL in the new setting of cable-unsplittable demands, where the demand of a vertex cannot be split among multiple cables. We show that the problem is NP-hard to approximate to a factor better than $3/2$ on
stars, and then provide an
algorithm for tree instances that outputs a solution with optimal cost, but which exceeds the capacity on each cable by a factor of $1+\epsilon$. As a consequence, we show that the problem has a $2$-approximation
algorithm on trees.
Read the full abstract ▾
Sound
StreamAV-Bench: A Comprehensive Benchmark for Streaming Audio-Video Generation
Kaiqi Liu, Haoxuan Zeng, Jingqi Liu et al. (+7 more)
Recent advancements in generative models are pushing
video generation toward unbounded streaming audio-
video generation for real-time interactive worlds. However, existing
benchmarks primarily evaluate completed sequences and struggle to capture streaming properties. To bridge this gap, we introduce StreamAV-Bench, the first comprehensive
benchmark tailored for streaming audio-
video generation. StreamAV-Bench establishes a unified evaluation framework, including the progressive track for instruction adherence and long-horizon stability, and the interactive track for interactive response and state retention and reuse. With expert-verified evaluation cases across 32 fine-grained dimensions, we conduct an extensive evaluation of 13 representative systems. Our analysis reveals that current models suffer from temporal drift in progressive generation and responsiveness bottlenecks during interactive control. Based on a comprehensive failure analysis, we share insights to advance the development of native joint audio-
video streaming models.
Read the full abstract ▾
All authors Kaiqi Liu, Haoxuan Zeng, Jingqi Liu, Jiacong Fang, Ziqi Cai, Yunyao Mao, Henglin Liu, Yu Sheng, Shuchen Weng, Boxin Shi
Databases
Realistic Counterfactual Explanations via Denial Constraints
Avia Asael, Nave Frost, Amir Gilad et al. (+1 more)
In the realm of Explainable AI, classification results are often explained via counterfactuals (CFs for short), which are (ideally small) perturbations to an instance that lead to a change of classification label. Such CFs may serve as explanations for the prediction, pinpointing the features that were important. Existing explainability solutions typically aim at minimizing the distance of CFs from the original instance so that they are specific to it, and/or maximizing the diversity of CFs to cover multiple facets of the reasons underlying the prediction. In this paper, we note that in pursuing these aims, state-of-the-art explainability solutions may (and often do) yield counterfactual explanations that do not correspond to realistic instances. This limits their applicability and usefulness in practice. To remedy this, we combine ideas from Explainable AI with ideas from data management. Specifically, we capture realism of CFs via logical constraints that hold with respect to a
dataset of examples (e.g., training set); the class of such constraints that we focus on is that of denial constraints, extensively studied in the context of relational databases. Algorithmically, we then combine explainable AI solutions to yield CFs, with ideas from data cleaning that we adapt to this unique setting, to transform CFs into realistic ones. Extensive experiments across four
datasets validate that our solutions achieve realism with relatively minor compromise in terms of distance and diversity. They further validate that the dedicated optimizations that we have developed to speed up the search for CFs are indeed highly effective.
Read the full abstract ▾
All authors Avia Asael, Nave Frost, Amir Gilad, Daniel Deutch
Artificial Intelligence
ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving
Wenqian Ye, Ziwei Guan, Eric Xie et al. (+6 more)
Automated
theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fully preserve this recursive structure, where the learning process should be self-improving over time. Existing methods either embed proof experience into model parameters through expensive weight updates, or keep verified intermediate deductions only within the current problem. In addition, these methods also heavily rely on sparse whole-proof feedback, even when unsuccessful partial attempts contain useful discoveries. To close the gap, we propose ProofEvolve, a neuro-symbolic framework that evolves explicit, formally verified symbolic proof structures with neural models to decisively expand the knowledge boundary. In this framework, the neural model proposes variation operators, including decompositions, repairs, and schema recombinations. The symbolic Lean kernel verifies every proof transition. Over the
evolution loops, ProofEvolve computes verified closure over the resulting proof directed acyclic graphs (DAGs). Within each problem, ProofEvolve evolves partial AND-OR proof DAGs in a behaviorally indexed archive. Across problems, kernel-checked schema extraction adds newly proved sub-DAGs to a persistent schema library. Proof DAGs inherit the solved results through typed schema recombination, with every residual premise exposed as a new subgoal. This evolutionary process preserves verified results from incomplete attempts and makes them available for later proofs without weakening formal soundness. Across three competition-level Lean
benchmarks, ProofEvolve achieves the highest average solve rate among the evaluated proof systems.
Read the full abstract ▾
All authors Wenqian Ye, Ziwei Guan, Eric Xie, Bohan Liu, Shivani Modi, Buyun Zhang, Ellie Dingqiao Wen, Henry Kautz, Aidong Zhang
Machine Learning
Beyond Capability Benchmarks: Learning Operational Fingerprints of LLM Cloud Services from Production Incident Metadata
Meiwei Zhang, Eduardo Miranda, Bruce Baynes et al. (+4 more)
Managed LLM services are now part of real production systems, but model selection and service planning still rely heavily on capability
benchmarks that reveal little about operational behavior after deployment. We present Operational
Embedding (OpEmbed), a framework for learning compact operational fingerprints of LLM cloud services from structured,
privacy-preserving support-case metadata, without using case text. OpEmbed aggregates model–time windows into an eight-channel operational signature and learns a low-dimensional representation via temporal contrastive learning, cross-view reconstruction, and generational-ordinality regularization. Evaluated on more than 33,000 production support cases spanning seven LLM families over 26 months at Google Cloud, OpEmbed recovers interpretable family- and version-level structure, improves leave-one-model-out operational
forecasting over non-learned baselines, remains useful under limited early-window data, and supports cross-model fault-type transfer. We report the practical lessons learned from building and evaluating this tool for model onboarding, support readiness assessment, and operational monitoring.
Read the full abstract ▾
All authors Meiwei Zhang, Eduardo Miranda, Bruce Baynes, Suvigya Jain, Wanlong Chen, Tao He, Sergey Borodavkin
Computation and Language
Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verification
Yuxin Zi, Cong Xu, Suparna Bhattacharya et al. (+2 more)
While tool-augmented Large
Language Models have significantly improved multi-step
reasoning in quantitative STEM tasks, a critical residual failure mode remains: intermediate
reasoning steps that are syntactically well-formed, mathematically executable, and unit-consistent, yet contextually ungrounded. Current approaches either rely on formal verifiers that cannot assess semantic intent, or burden Process Reward Models (PRMs) with the dual task of checking both arithmetic and logic. In this paper, we propose a neuro-symbolic framework that cleanly decouples
reasoning into two formal dimensions: Symbolic Validity ($V$) and Semantic Groundedness ($G$). We guarantee $V$ by construction using a deterministic symbolic verifier acting as a hard filter. To assess $G$, we train a PRM conditionally on the verifier-accepted
manifold. To train this PRM efficiently, we introduce Counterfactual Symbolic Perturbation (CSP), a novel data synthesis strategy that algorithmically generates constraint-preserving hard negatives (steps that perfectly pass the verifier but are logically flawed). At inference, we deploy a verifier-first constrained search that guarantees execution consistency for verifier-covered operations while relying on the PRM solely to rank semantic grounding. By targeting the exact residual error class of strong tool-using LLMs, our method significantly improves
reasoning reliability without the sprawling heuristics of prior frameworks.
Read the full abstract ▾
All authors Yuxin Zi, Cong Xu, Suparna Bhattacharya, Martin Foltin, Amit Sheth
Computation and Language
How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models
Christos Petridis, Konstantinos Pelechrinis and Zoran Obradovic
Large
language models increasingly produce and interpret verbal probability expressions, yet whether these expressions carry consistent meaning across models (or match human perceptions of uncertainty) remains unknown. We present a systematic cross-model evaluation using a word-to-number mapping task grounded in established human
benchmarks. Eleven uncertainty expressions were presented to 19 models under two conditions, forced single-number response and explanation elicitation, alongside a novel bidirectional roundtrip test of internal consistency. LLMs track the human
benchmark with surprising fidelity: word ordering is preserved, three anchor points are recovered, and “possible” shows the highest variance and cross-model disagreement of any expression tested, consistent with its documented bimodal interpretation in humans. However, models show a systematic upward bias for negative expressions such as “unlikely” and “improbable.” Explanation elicitation reduces within-model variance while increasing between-model divergence, stabilizing individual models at the cost of inter-model consensus, and the roundtrip experiment reveals clear stratification, with frontier models maintaining coherent bidirectional representations. LLMs thus reproduce the structure of human verbal probability cognition, including its biases, while diverging systematically at the negative end—with implications for any setting where humans and models exchange probabilistic
language.
Read the full abstract ▾
Human-Computer Interaction
Calibration-Free Cuffless Blood Pressure Estimation Using Multimodal ECG-PPG Fusion on a Google Pixel Watch
Jathushan Kaetheeswaran, Boyi Ma, Ali Abedi et al. (+2 more)
Inadequate blood pressure (BP) monitoring and management outside of clinical settings can worsen major cardiovascular risk factors such as hypertension. While cuff-based devices are commonly used for at-home monitoring, these devices can be inconvenient for daily use due to their sensitivity to body positions, upper-arm constrictions, and limited portability. A promising alternative is emerging in the form of consumer-grade smartwatches, where physiological signals related to cardiac activity can be used to estimate BP non-invasively and continuously across daily living conditions. In this work, we use data collected from a Google Pixel Watch in 40 participants to develop and compare several
algorithm approaches for BP estimation. We found that our proposed deep learning model achieved the strongest overall performance, and that fusing smartwatch signals with demographic information improved model generalizability to unseen individuals. However, we also identified that model accuracy was not consistent across participant subgroups, with obese individuals yielding higher estimation errors than others. This study highlights the feasibility of consumer-grade smartwatches as accessible platforms for deploying robust BP estimation
algorithms, though clinical reliability will require larger, more diverse populations and additional sensing modalities.
Read the full abstract ▾
All authors Jathushan Kaetheeswaran, Boyi Ma, Ali Abedi, Shehroz S. Khan, Milad Lankarany
Machine Learning
Privacy Without Regret: Differentially Private Inference-Time Alignment
Ishi Jain, Nandini Bhattad and Sayak Ray Chowdhury
Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time
alignment strategy, but it suffers from two distinct problems: reward hacking, in which the selected response exploits errors in the proxy reward model, and the absence of any
privacy protection for the sensitive human preference data used to train that reward model. We show that a single intervention-adding calibrated noise to reward scores before selection-resolves both. Our first result, Private Best-of-N (PrivBoN), establishes that Gumbel noise at an appropriate scale simultaneously provides $\epsilon$-differential
privacy and implements KL-regularized
alignment. Whenever the
privacy budget exceeds a critical threshold $\epsilon^*$, the
privacy-mandated noise is the regret-optimal regularization, and
privacy imposes zero additional
alignment cost-matching the information-theoretic skyline of Huang et al. (2025). Because $\epsilon^*$ depends on an unknown coverage coefficient, we introduce Private Inference-Time Pessimism (PrivITP), which combines $\chi^2$-regularized rejection sampling with a two-phase Gaussian mechanism. PrivITP achieves ex-post $(\epsilon,\delta)$-DP with a
privacy cost independent of the number of responses $n$, cleanly decouples the regularization parameter from the
privacy parameter, and attains the skyline up to a noise-inflation term. Experiments across several
language models,
datasets, and reward models confirm our results: PrivBoN and PrivITP are scaling-monotonic (unlike BoN, which degrades past a critical $n$), and PrivITP matches or outperforms PrivBoN at equivalent
privacy levels, with the largest gains in the strong-
privacy regime.
Read the full abstract ▾