Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Thursday 13 August

Computer Vision

Doomed to Re-Annotate, Forever: The ImageNet Story

Top-1 accuracy on ImageNet-1k remains the most commonly reported metric in visual recognition. Quality issues with the dataset have been repeatedly reported, yet the original 2012 noisy labels are still predominantly used. The paper presents a comprehensive effort, which goes well beyond prior correction attempts, towards obtaining accurate and complete ImageNet-1k validation set annotations. The result, ReImageNet, includes multilabel correction, object localization, revised class definitions, and semantic attributes (text-recognition, rendition, reflection, crowd, dominant). The reannotation reveals that approximately 12% of the original ImageNet-1k labels are incorrect, 33.3% of images are multilabel and 3.8% contain no object from an ImageNet-1k class. With the new labels, top-1 accuracy increases by up to 1.2% for supervised models and by 5-6% for MLLMs. We argue that annotation at ImageNet scale cannot realistically be completed in one pass, as errors and definitional issues are discovered only through annotating, and we build our pipeline around repeated refinement and error checking. We observed that human and LLM collaboration with appropriate tooling represents the current quality ceiling for annotation at this scale. ImageNet-1k issues propagate into its derivative test sets, indicating that the problem is structural rather than specific to any single benchmark. All annotations, class definitions, guidelines, and analysis code have been publicly released. Project page: https://vrg.fel.cvut.cz/reimagenet Annotations: https://huggingface.co/datasets/vrg-prague/ReImageNet Code: https://github.com/klarajanouskova/ImageNet
Read the full abstract

All authors Illia Volkov, Nikita Kisel, Tetiana Mishkina, Klara Janouskova, Jiri Matas

Computational Geometry

The Sharp Dimension Bound in the Johnson–Lindenstrauss Lemma

The Johnson–Lindenstrauss lemma asserts that every set of $n$ points in $d$-dimensional Euclidean space embeds into $O(\varepsilon^{-2}\log n)$-dimensional Euclidean space with distortion at most $1+\varepsilon$. Larsen and Nelson conjectured that the optimal target dimension throughout the full range of the parameters $n,d, \varepsilon$ is \[ \Theta\left(\min\left\{d,n-1,\frac{\log(2+\varepsilon^2n)}{\varepsilon^2}\right\}\right). \] We resolve this conjecture in the affirmative. In fact, we prove the stronger statement that the upper bound is attained by a linear map. The matching lower bound, due to Larsen–Nelson and Alon–Klartag, holds even for nonlinear embeddings.
Read the full abstract

Emerging Technologies

RIVERPlace: Repairing Interconnect Violations with Efficient Retiming and Incremental Placement for AQFP Circuits

The Adiabatic Quantum-Flux-Parametron (AQFP) offers near-Landauer-limit energy efficiency but faces significant scalability challenges due to strict path balancing and limited drive strength. To address this, we propose RIVERPlace, a framework that integrates long-wire pipelining, retiming, and incremental placement to resolve interconnect violations with minimal disruption. RIVERPlace first applies placement-aware retiming to repair violations without increasing logical depth. When depth increases are necessary, we introduce Buffer Cut Insertion (BCI), which formulates violation resolution as a constrained global edge-selection problem reducible to a maximum topological cut, thereby enabling an exact polynomial-time solution. By selectively pipelining edges across multiple rows, BCI avoids excessive buffer insertion while resolving interconnect violations. Experimental results demonstrate that RIVERPlace consistently outperforms prior AQFP placement approaches, reducing placement overhead by more than an order of magnitude in inserted buffers, 3x in placement-induced depth, and over 2x in circuit area, while also reducing runtime by more than an order of magnitude and latency by 38%. These improvements enable the first post-routing, timing-closed implementations of the complete open-source AQFP benchmark suite, including larger circuits like alu32.
Read the full abstract

All authors Robert S. Aviles, Ziyu Liu, Sasan Razmkhah, Massoud Pedram, Peter A. Beerel

Artificial Intelligence

FLARE MCMC: Fidelity-based Layer-Adaptive REcursive proposals for MCMC

Markov chain Monte Carlo (MCMC) requires only the ability to evaluate the likelihood, making it a common technique for inference in complex models. However, it can have a slow mixing rate, requiring the generation of many samples to obtain good estimates and an overall high computational cost. FLARE MCMC is a multi-fidelity layered MCMC method that exploits lower-fidelity approximations of the true likelihood calculation to improve mixing and leads to overall faster performance. Such lower-fidelity likelihoods are commonly available in scientific and engineering applications where the model involves a simulation whose resolution or accuracy can be tuned. Our technique uses recursive, layered chains with simple layer tuning; it does not require the likelihood to take any form or have any particular internal mathematical structure. We demonstrate experimentally that FLARE MCMC achieves larger effective sample sizes for the same computational time across different scientific domains including hydrology and cosmology.
Read the full abstract

All authors Harini Venkatesan, Christian Shelton, Ming-Feng Ho, Simeon Bird, Mengxuan Wu

Machine Learning

CutClean: Neural Network Pruning for Privacy-Preserving Inference

Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of representation imbalances that lead to traditional dataset biases. This poses significant privacy risks when deploying models that process sensitive attributes. In this context, we propose CutClean, a privacy-aware pruning method that allows to reduce privacy information flow through the network, while increasing its sparsity. Our approach employs auxiliary linear privacy heads placed at each network's block to quantify information leakage, and further applies increasing levels of sparsity to remove the private attribute leakage, measured in terms of the accuracy of the privacy head attached to the last block. Experiments on synthetic and real-world datasets demonstrate that our approach effectively minimizes private information flow while achieving high sparsity rates and preserving classification target accuracy.
Read the full abstract

All authors Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise, Enzo Tartaglione

Computational Engineering · Cross-listed from cond-mat.other

Rapid Kirigami Simulation using the Bar & Hinge Approach

Kirigami, the art of cutting sheets, offers unique characteristics such as shape morphing, stretchability, and adaptability, with applications in deployable and reconfigurable structures. While Finite Element (FE) approaches are widely used to analyze kirigami structures, they are computationally intensive and prone to convergence issues. On the other hand, existing simplified and theoretical models for evaluating kirigami are typically restricted to specific designs and analytical scenarios. This paper proposes a generalized, computationally efficient reduced-order model based on the bar and hinge approach for analyzing any kirigami system. The model represents the entire kirigami structure using truss bars, bending hinges, and torsional springs, capturing both the deformation and internal forces of the system. We derive stiffness expressions for kirigami structures that experience stretching and out-of-plane bending deformations, as well as for structures that experience only in-plane stretching and rotations. The accuracy and robustness of the model are validated through comparisons with FE analysis and experimental data on both single-cut kirigami designs and more complex designs with multiple cuts. Our results demonstrate less than 5% difference in deformation predictions and achieve at least a tenfold computational speedup compared to FE simulations. Additionally, we demonstrate the model's capabilities through simulating complex scenarios, including kirigami-skinned crawlers, high-throughput property-space exploration, and in-plane kirigami-inspired metamaterials. These examples demonstrate computational capabilities that enable large-deformation structural simulations and high-throughput design exploration beyond the practical limits of conventional FE methods.
Read the full abstract

All authors Raj Pradip Khawale, Elaheh Mehdizadeh, John Brigham, Evgueni T. Filipov

Computer Vision

Kolmogorov-Arnold Networks for Spatially Independent Multispectral Land Classification

Land classification from satellite imagery is important for land management, environmental monitoring, and urban planning. Machine learning methods such as random forests and multilayer perceptrons have shown strong performance on multispectral data, while the Kolmogorov-Arnold network has emerged as an alternative architecture with compact model structures. This study evaluates the Kolmogorov-Arnold network for land classification using Landsat 8 imagery and compares it with random forest and multilayer perceptron models. The models were trained and tested on data from Edmonton, Alberta and evaluated on an independent dataset from Calgary, Alberta across five land classes: agriculture, urban, water, forest, and bare ground. For the Calgary dataset, the Kolmogorov-Arnold network matched the accuracy of the random forest and outperformed the multilayer perceptron, while requiring substantially fewer trainable parameters and providing greater interpretability.
Read the full abstract

All authors Katherine L. Bauer, Teemu Harkonen, Simo Sarkka, Arturo Sanchez-Azofeifa

Artificial Intelligence

Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement

Analog IC layout design remains a labor-intensive iterative process dominated by simulation-driven refinement. Although end-to-end layout generators accelerate initial placement and routing, they still require experts to manually tune layout optimization parameters with repeated post-layout simulations for stringent design specifications. While Bayesian Optimization (BO) is widely adopted for parameter tuning in analog IC design, at the layout level it typically requires hundreds to thousands of evaluations, each involving costly parasitic extraction and post-layout simulation, which makes it impractical. Recently, Large Language Models (LLMs) have demonstrated potential in improving the sample efficiency of such simulation-driven tuning. However, their restricted access to geometric layout context and design-specific heuristics limits their ability to manipulate the layout optimization process. In this paper, we propose a simulation-aware LLM multi-agent framework that performs in-context policy improvement (ICPI) by iteratively updating layout optimization parameters exposed by an analog layout generator through an act-observe-reflect loop on compact structured layout representations. Experiments on real-world analog circuits show that, with only tens of post-layout simulations, our approach improves post-layout performance over the generator's built-in heuristics and BO-based tuning method.
Read the full abstract

All authors Bingyang Liu, Ziming Wei, Xiaohan Gao, David Z. Pan

Computer Vision

ChartProbe: A Diagnostic Study on Visual Reasoning through Perception, Grounding, and Simple Reasoning

Vision-language models (VLMs) remain unreliable on chart questions that require reasoning over visual quantities, and this weakness is usually attributed to a reasoning deficit and addressed with more reasoning supervision. We ask whether the difficulty lies in reasoning itself, or in the simpler skills that reasoning operates on: reading the plotted elements (perception), locating them and binding them to their labels (grounding), and performing single-step computations such as ranking, totals, and differences (simple reasoning). We introduce ChartProbe, a diagnostic framework whose probes are generated directly from the code that renders each chart, so every gold answer is exact by construction, needs no human annotation, and attributes each failure to a single skill. ChartProbe enables an intervention prior work does not attempt: instead of synthesizing complex-reasoning data, we withhold complex questions and reasoning traces entirely, fine-tune on one simple skill at a time, and measure transfer to held-out complex-reasoning questions. Across three open-weight VLMs, supervising the simpler skills alone produces large gains on complex-reasoning questions the model never trained on: where these skills are weak and the model can be taught to read the image, training them recovers much of complex reasoning at no reasoning-data cost. The gains hold across three out-of-distribution settings: an unseen chart type (pie charts), a human-written benchmark disjoint from our images and templates (ChartQA), and a non-chart visual domain (CLEVR). Complex visual reasoning can therefore improve without complex-reasoning supervision.
Read the full abstract

Information Theory · Cross-listed from quant-ph

Entanglement breaking in self-referential quantum feedback: a record bound and an exactly solvable loop

A feedback loop that returns a message into the process it describes defines a quantum channel on the message. We ask when such a loop preserves entanglement with a reference, that is, when its channel is not entanglement breaking. For any qubit loop, the negativity of the Choi state is at most half the fidelity between the states that the two values of the message leave in the discarded registers, in any basis. This channel analogue of the duality between fringe visibility and which-way information is attained by pure dephasing, and a perfect record of the message in the discarded registers makes the loop entanglement breaking. We then solve a three-qubit loop in which the message steers a future event, a probe reads the event, and a partial swap feeds the probe back. Every partial feedback is a strict contraction, and the loop is entanglement breaking exactly when an explicit trigonometric polynomial in its coupling angles is not positive. A partial record of the message in the future event can restore entanglement that the feedback alone destroys. Stability, a coherent fixed point, information about the future event and entanglement preservation coexist on about three quarters of the parameter space.
Read the full abstract

Logic in Computer Science

Simplicial Semantics for Belief Revision

This paper will give a definition of belief revision within simplicial semantics. Starting from the work presented in "A Semantics for Belief in Simplicial Complexes" as a baseline, this paper modifies the semantics for belief given there to allow atomic formulae to be assigned to nodes, not facets. Conceptually and philosophically, this version of the semantics is better suited if one wishes to interpret the nodes of a simplicial model of epistemic logic as a "perspective" assigned to a particular agent. If nodes are perspectives, it then follows that worlds, or the facets of a simplicial model, are composed themselves of perspectives. This allows us to say that two worlds are more similar, or "nearer", if they share more perspectives. With this conceptual notion of nearness in hand, two different formal presentations of revision are given. We conclude by exploring some conceptual pitfalls surrounding these definitions under iterated revision, and motivate a few potential solutions that involve giving the agents a "memory" of what has been announced so far.
Read the full abstract

Computation and Language

Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models

Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors? This distinction is important because reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness. We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present versus absent in a model's reasoning trace. Across 15 models and 6 benchmarks spanning text-only and vision-language reasoning, we annotate 15,282 traces with a taxonomy whose core behaviors are defined for both LLM and VLM traces. We find evidence for an Amplification-Lift Gap, in which thinking models strongly amplify self-correction, hypothesis testing, and uncertainty acknowledgment, while the highest-lift behaviors are confidence calibration, knowledge alignment, and self-awareness. Confidence calibration is among the strongest positive signals of correctness in both modalities, yet is barely amplified; uncertainty acknowledgment is amplified by 3–7$\times$, yet is weakly or negatively associated with correctness. We find that reasoning-oriented training does not preferentially amplify the highest-Lift behaviors, motivating process-level objectives that reward calibrated and grounded reasoning rather than surface form alone.
Read the full abstract

All authors Jean de Dieu Nyandwi, Leena Mathur, Yonatan Bisk, Robert Hawkins, Graham Neubig

Programming Languages

GPU Offload in Rust: Portable, Safe, and Fast

High-performance GPU programming has traditionally forced a compromise between execution efficiency and memory safety. While Rust guarantees compile-time memory safety for host CPUs via its strict ownership model, applying these constraints to massively parallel GPU execution environments has previously mandated either vendor-locked Domain-Specific Languages (DSLs) or escaping to explicit unsafe raw pointers. This paper presents a zero-overhead, multi-vendor GPU compilation framework built natively into the Rust compiler (rustc) and LLVM backends. We leverage Rust's rich type system, ownership system, and strict aliasing guarantees (noalias) to efficiently manage and optimize data transfers through LLVM's Offload infrastructure. We expose the technical challenges of cross-vendor ABI lowering mismatches between Host and Device targets and introduce a two-pass compilation pipeline capable of safely handling both manual and compiler-generated memory movements. Evaluating our framework on RAJAPerf demonstrates that our rustc-based solution can generate competitive LLVM IR for GPU kernels, achieving a solid kernel performance against native, hand-optimized CUDA and HIP C++ baselines.
Read the full abstract

All authors Manuel S. Drehwald, Marcelo Domínguez, Kevin Sala, Alán Aspuru-Guzik, Johannes Doerfert

Programming Languages

A Barrier-Free Synchronization Algorithm for Multi-Engine AI Accelerators

Multi-engine AI accelerators such as AWS Trainium comprise specialized compute engines that execute in parallel, and the compiler must synchronize the data dependencies between them. For straight-line code this is simple: each dependency reduces to waiting for a threshold count of instruction completions, which the compiler computes statically. Loops admit no such static threshold; a simple solution inserts all-engine barriers at iteration boundaries, resetting synchronization state so each loop body can be treated as straight-line, at the cost of parallelism. We present a barrier-free synchronization algorithm that instead enforces each dependency precisely across structured control flow with arbitrarily nested, dynamically bounded loops. The key idea is to compute dynamic thresholds at runtime from tracked loop iteration counts. We implemented it as a compiler backend pass at the AWS Neuron ISA level. On a suite of ML kernels, it reduces latency 10-45% relative to the barrier-based baseline, achieves a 3.3x speedup on a synchronization-bound microbenchmark, and often matches or exceeds hand-tuned manual allocation. Issuing a consumer too early violates its dependency, while issuing too late unnecessarily stalls execution. We formally characterize the minimum synchronization required for correctness and verify in the Lean proof assistant, via bisimulation, that our algorithm meets this criterion.
Read the full abstract

All authors Chungha Sung, Nikil V. Shyamsunder, Hanliang Zhang, Daniel Kroening, Joonwon Choi

Machine Learning

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint, prompts, hardware, inference engine, decoding, and quantization configuration fixed, we swap only the INT8 linear kernel (CUTLASS versus Triton) inside vLLM. At 1.7B each arm reproduces itself bit-for-bit across cold restarts, yet the arms agree on no sequence in any end-to-end comparison we ran (0/8, 0/16, and 0/64). What makes this more than a benchmark discrepancy is an integer alibi: for shared INT8 operands under a verified no-overflow bound, the INT32 dot product is exact and order-independent, so the accumulator cannot be the source of any difference. Feeding both kernels identical operands from every linear layer of Qwen3-1.7B and 8B (196 and 252 layers), we find bit-identical outputs under power-of-two scales, confirming a pinned prediction list 196/196 and 252/252 (pre-registered at 1.7B, pinned but not blind at 8B), and observed differences of at most one bfloat16 spacing under the checkpoints' real scales. This localizes the divergence to scale application and output rounding after the exact accumulator. Applied as a probe checkpoint, the same intervention restores end-to-end bitwise agreement (8/8 and 16/16 sequences). Cross-implementation FP8 GEMM shows a different signature: both the prevalence and the magnitude of differences grow with reduction depth, while the INT8 fraction stays at parts per million and within one spacing over a 64x range of K. Teacher-forced replay ties layers to tokens: flips concentrate at small logit margins, which predict flip risk with ROC-AUC 0.94 on 16,384 positions. We will release the pre-registration, per-layer predictions, manifests with kernel-selection evidence, and a conformance procedure that turns these controls into a concrete check for kernel interchangeability.
Read the full abstract

2608.13756 · 13 Aug · 10 pages (IEEEtran two-column), 3 figures, 4 tables. Pre-registered protocol with append-only amendments. Companion to arXiv:2608.11693. v2: corrects the product-bound attribution (weight side, not activation side; 16256 is exact) and distinguishes the layer-level uniform pow2 regime from the per-channel probe; no result changes. Figure count corrected from v1

Artificial Intelligence

Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation

The EU AI Act requires providers of high-risk systems to file technical documentation describing how the system reaches its decisions. Mechanistic interpretability is the obvious source of such evidence, and circuit discovery is its most developed instrument. We ask whether that evidence survives the condition under which it would be relied upon: two competent analysts, the same system, the same tool, different defensible settings. We pre-registered a crossed grid of seven analytic axes, every level taken from a published implementation, and mapped each discovered circuit through a deterministic claim map to a structured Annex IV statement. Across 15,840 pre-registered specifications on GPT-2 small and the indirect object identification task, of which 7,561 produced a claim, the derived statement flips across 73.2% of specification pairs (95% CI 0.725 to 0.738) and the modal claim commands 41.1% of the space. The evidence fails a filability criterion at every tolerance a conformity assessment body would plausibly accept. Standardising the single most influential choice, the evaluation metric, leaves the flip rate at 59.4%. Removing circuit size from the claim entirely and holding it fixed leaves 27.1% (95% CI 0.255 to 0.286), still above the pre-registered threshold. The circuits underlying these claims are structurally near-disjoint, median pairwise Jaccard overlap 4%, and functionally uncorrelated at Cohen's kappa 0.015, so the instability is not one mechanism described in different words. We give the filability criterion as a standalone protocol, and we report that one of the seven documented discovery objectives does not execute at all on the library's own canonical task. The study covers one model and one task, and whether the conclusion holds at scale is untested.
Read the full abstract

Computer Vision · Cross-listed from physics.ins-det

An Interactive, Automated 4D-STEM data acquisition and analysis routine for Scanning Electron Nanobeam Diffraction and Ptychography experiments

Modern transmission electron microscopes are versatile instruments which have become indispensable tools for understanding structure and chemical composition at the nano- and atomic scale. In the physical sciences these instruments are still largely manually controlled, requiring significant operator expertise, limiting throughput, and precluding statistical analysis of large datasets. Recent technical advances in both hardware and in control software now allow for the interaction with almost every functionality of the microscope through a programming interface. This enables better experimental design and data collection automation while also reducing operator collection bias and required expertise. In this study, we present an automated data collection routine with machine-driven decision-making to enable the collection of hundreds of 4D-STEM nanobeam diffraction and ptychography data from a large distribution of size-selectively deposited Pt nanoparticles. We present a semi-automated data analysis workflow to extract pertinent information from the large volumes of collected data. For the nanobeam diffraction data, reducing each dataset to its azimuthal variance profile and combining automated crystal orientation mapping with per-particle morphology descriptors reveals the orientation, shape and phase distributions across the ensemble, including a weak {110} texture. For the ptychographic data, an automated screening pipeline identifies on-zone-axis particles and enables atomic-resolution phase imaging and lattice-strain mapping of individual grains. Together these demonstrate how automation turns instrument throughput into statistically meaningful, atomic-scale microstructural information.
Read the full abstract

All authors Mohsen Danaie, Max England, Yiming Xu, Ruomu Zhang, Ed Darnbrough, Josh Willem De Boer, Frederick Allars, Zaeem Najeeb, Aakash Varambhia, Jinseok Ryu, Benjamin Bradnick, Damien McGrouther, Manfred E. Schuster, Christopher S. Allen

Computer Vision

CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension

Large pre-trained models have become foundational components of modern machine learning systems. Yet adapting these models to novel categories typically requires examples from the target distribution. In many domains, however, such data are unavailable. Zero-shot learning (ZSL) permits recognition under these limitations through relying on auxiliary semantic information such as textual descriptions. We introduce CAST (Closed-form Analytic Semantic Transfer), a training-free, image-free framework for extending a pre-trained classifier to previously unseen classes through weight injection. We provide a theoretical foundation for CAST and derive a finite-sample error decomposition that identifies the semantic extrapolation residual $\rho_u$. The residual is a computable, model-agnostic measure and provides a principled criterion for dataset curation and benchmark design. Experiments on standard zero-shot learning benchmarks demonstrate that CAST matches or exceeds existing image-free approaches and approaches the performance of few-shot adaptation methods, while requiring neither iterative optimization nor examples from the target distribution.
Read the full abstract

All authors William Heyden, Habib Ullah, Muhammad Salman Siddiqui, Fadi Al Machot

Artificial Intelligence · Cross-listed from q-bio.NC

Data-driven techniques for translational neuroscience and personalized neuro-health

Neurodegenexrative diseases such as Alzheimer's disease and Parkinson's disease are diagnosed most reliably only after substantial, often irreversible, neuronal loss has already occurred, creating an urgent need for quantitative tools that can detect subtle, early, and individual-specific brain changes from neuroimaging data. This review surveys a broad and rapidly evolving toolkit of data-driven techniques for translational neuroscience and personalized neuro-health, organized around four complementary methodological pillars. Throughout, we emphasize how these methodologically diverse approaches converge on a common translational goal: personalized, mechanistically grounded, and clinically actionable models of individual brain health, and we close by discussing the principal open statistical, computational, and clinical challenges that remain.
Read the full abstract

All authors Vishal Subedi, Shashipraba N. K. Rajakaruna, Pratyusha Sarkar, Subhankar Chattoraj, Anjali Khasa, Siddhartha Nandy, Hamza Farooq, Animikh Biswas, Sanjay Chaudhuri, Asim K. Dey, Karuna Joshi, Christophe Lenglet, Ansu Chatterjee

Software Engineering

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-line phrases. We ask whether grounding those specifications in ISO/IEC 25010 Quality Model, either as rich natural-language prose (NL-rich) or as structured JSON (Structured), improves code generated on HumanEval/HumanEval-ET compared to a RobuNFR-style one-line baseline (NL-simple). We evaluate four NFRs (performance, error handling, code smell, readability) with ten prompt variations per condition under a fixed model snapshot and paired non-parametric analysis. Primary finding: ISO-grounded enrichment improves static quality proxies (unreadability density falls across all four NFRs (e.g., Performance 0.88 -> 0.69 for NL-rich)) and reduces sensitivity to prompt wording, but does not reliably improve functional correctness; for error handling, extended-test pass rate decreases, suggesting tension between defensive coding patterns and exact-output benchmarks. Secondary finding: when ISO content is held constant, NL-rich and Structured differ negligibly in correctness (|delta| <= 0.023), indicating that semantic content matters more than JSON-vs-prose format. Practitioners should invest in standard-grounded NFR content rather than serialization form. A fully traceable replication package is provided.
Read the full abstract

Computation and Language

GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis

Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-conditioned generators either take caption embeddings frozen from off-the-shelf text encoders, or adapt the encoder end-to-end, letting the denoising loss shape the embeddings only as a by-product. In either case, the conditioning representation is never deliberately matched to the signal modality, leaving it ill-suited to guide generation. We address this by introducing GALA: Generation-Aware cross-modaL Alignment for text conditional time series generation. GALA is a two-stage approach that first contrastively couples a pretrained text encoder with a time-series foundation model into a shared embedding space with both encoders adapted to generation by an auxiliary generative loss, and then freezes the resulting caption embedding to drive a flow-matching generator. On TSFragment-600K, spanning four domains and three fragment lengths, GALA sets a new state of the art, ranking first in 30 of 36 metric columns and reaching an average rank of 1.08/1.08/1.42 at lengths 24/48/96 against 1.92/2.00/1.75 for the strongest baseline. We further find that generator-internal text encoders force a trade-off between fidelity and caption adherence, whereas conditioning on the aligned embedding breaks it: FID, CTTP, and JFTSD all improve at once. Ablating the auxiliary loss degrades FID, CTTP and JFTSD together, it indicates the generative term is a necessary component of the alignment rather than an add-on.
Read the full abstract

All authors Haochen Zhang, Gengwei Zhang, Laura Yao, Nicholas Konz, Tianlong Chen

Software Engineering

Building AI-Intensive Software with AI: Early Results and a Cautionary Tale on Measuring Development Cost

Empirical reports on the true cost of AI-intensive software development remain scarce, and the few that exist are easy to get wrong in ways that never surface in the final number. We report early results from an ongoing case study: a six-person student team built a full conversational onboarding assistant – RAG-based code chat, guided tours, dependency graphs, technical-debt analysis – over one academic term using pervasive AI assistance. We instrumented development with a three-layer cost model (real AI spend, self-reported human effort, human counterfactual) and initially reported a 19.4x cost ratio. A follow-up pass revealed two independent errors – inferring per-token cost under a flat-rate subscription, and pricing the counterfactual with the wrong regional labor rates – that together had inflated the ratio by roughly 2x; the corrected figure is ~9.9x. We present this correction as an early, generalizable finding in its own right: both errors are easy to make, invisible in the final number, and plausibly common in similar reports. We outline next steps toward a more robust, replicable costing methodology for AI-intensive development.
Read the full abstract

Computer Vision

Limitations of Synthetic Data Generation in Specialized Data-Scarce Domains

Advances in diffusion-based generative models have motivated the use of synthetic image generation to alleviate data scarcity in vision tasks. While this strategy has shown promise in natural image benchmarks such as ImageNet, its effectiveness in sparse, high-variance real-world domains remains unclear. In this work, we focus on domains where images differ substantially from common image datasets and additional data are expensive to obtain. Against non-generative data augmentation baselines, we evaluate the downstream classifier performance improvements yielded by two schools of generative sparse data extension: distribution modeling and sample perturbation. Across five trauma classification tasks using subject-wise train–validation splits, no generative approach consistently outperforms a strong non-generative baseline. Feature-space analysis reveals recurring failure modes: memorization or collapse, distributional drift, and generation of visually plausible but simplified canonical instances that are easier to classify than real data.
Read the full abstract

All authors Edward Zhang, Marcel Hussing, Tanay Tandon, Shenbagaraj Kannapiran, Jason Hughes, Youkang Wang, Joshua Caswell, Agelos Kratimenos, Yi Fan Li, Milan Manoj, Ethan Sanchez, Sumukh Shrote, Camillo Jose Taylor, Daniel A. Hashimoto, Eric Eaton

Sound

Architecture and Affordances of PLAUD: Performative Latents and Unsupervised DDSP

PLAUD (Performative Latents and Unsupervised DDSP) is a neural synthesizer and Max for Live instrument for live electronic music, built on NoiseBandNet and trained on small personal sound corpora. We present its architecture, combining a variational DDSP synthesis model, latent smoothing, multi-scale spectral and adversarial losses, and an optional transformer prior, alongside a set of bending operations that intervene directly in the synthesis chain: component limiting, waveshaping, and prior feedback. The Max for Live interface exposes control generation, trajectory sampling, and modulation as primary modes of interaction. Throughout, we thread an affordance analysis arguing that the system's performative character follows from architectural decisions rather than being designed on top of them. The paper contributes both a technical account of the system and a situated affordance analysis of its role in live electronic music performance.
Read the full abstract

Robotics

Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigation

Object-goal navigation requires an agent to reason over object relationships and prioritize target-relevant objects for efficient decision making in unseen environments. While existing graph-based methods incorporate target-awareness at the feature or attention level, they remain permutation-invariant and lack an explicit mechanism to control information propagation order, limiting their ability to model target-dependent importance and long-range dependencies. In contrast, Graph-Mamba highlights that node prioritization through sequence ordering is critical for effective global reasoning. In this work, we investigate the node prioritization mechanism in Graph-Mamba and study its role in object navigation. We propose Graph-MambaNav, a target-aware spatial-temporal graph encoding framework that introduces a heuristic ordering over objects based on their relevance to the target, allowing more informative objects to be processed later to aggregate richer context. Both node ordering and edge weights are initialized from LLM-derived commonsense object relationships, providing a unified prior for structured reasoning. A spatial module integrates local message passing with global GraphMamba-based selective scanning, while a temporal module applies Mamba-based sequence modeling over object-wise temporal orders, allowing selective aggregation of historical context for long-range temporal reasoning. Experiments on AI2-THOR and RoboTHOR demonstrate improved navigation performance with generalization, and additional real-world robot deployment further validates the effectiveness of our proposed approach.
Read the full abstract

All authors Leyuan Sun, Genxin Chen, Linwei Ye, Yan Zhang, Xi Kan, Yanfei Sun

Computation and Language

BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages

This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot translation pipeline from our AmericasNLP 2026 system to translate between English and eleven North-Eastern Indian languages in both directions. At inference time, BM25 retrieves the most similar parallel examples from a language-specific training bank, and Gemini 2.5 Flash translates the input conditioned on these examples. No model fine-tuning is involved. Training banks combine official WMT26 data with publicly available corpora such as Samanantar and prior WMT shared task releases. A grid search over retrieval count r and development exemplar count d across all 22 language-direction pairs selects the best configuration for each submission.
Read the full abstract

All authors Aashish Dhawan, Christopher Driggers-Ellis, Dzmitry Kasinets, Christan Grant, Daisy Zhe Wang

Machine Learning

Capacity-Dependent Effects of Data Selection for Reasoning

In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution. Recent likelihood-based response selection methods suggest that responses closer to the student distribution provide more effective supervision, motivating the hypothesis that high-likelihood responses may generally be preferable for fine-tuning. In this paper, we revisit this intuition and show that the value of likelihood-based data selection depends critically on model capacity and training duration. Through controlled experiments on mathematical reasoning, using students ranging from 1.5B to 8B parameters and supervision generated by stronger teacher models, we observe a clear capacity-dependent “{\color{SMALLCOLOR}Fast-Fit} / {\color{LARGECOLOR}Slow-Gain}” pattern. High-likelihood data provides faster and more stable early improvements, especially for smaller models, but low-likelihood data becomes increasingly beneficial for larger models when training is allowed to continue longer. To explain this phenomenon, we analyze learning dynamics, showing that small models often fail to absorb low-likelihood supervision and instead fall into shallow or repetitive behaviors, while larger models are better able to move toward the teacher distribution under such data. We further provide a capacity-constrained theoretical view of distillation that clarifies how data difficulty, data span, and student capacity jointly govern transfer. Overall, our findings show that effective data selection for reasoning should be aware of model capacity and computing budget rather than based on a single universal preference for high-likelihood supervision.
Read the full abstract

Artificial Intelligence

Coverage Aware Active Evaluation for Failure Discovery with Paired Systems

Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets. Although cheaper proxies such as simulators, lower-fidelity systems, or related policies can be sampled extensively to find failures, proxy failures often do not transfer to the real world due to sim-to-real and system-to-system gaps. The key challenge is therefore to effectively leverage proxy system information for accurate prediction of severe target system failures. We propose an adaptive failure discovery method that combines proxy evaluations with limited target system results to guide scenario selection for target system testing. Our method learns a local predictor of target risk by correcting proxy failure signals using control-variate-inspired residual modeling. To find failures that are both likely and diverse, we combine this predictor with a support-aware mutual-information objective that favors realistic, well-supported regions while expanding coverage across failure modes. Across autonomous driving, manipulation, and quadruped velocity-tracking tasks, our method discovers up to 2$\times$ as many failures as random sampling and active-learning baselines, including severe and diverse failures missed by competing methods.
Read the full abstract

All authors Anjali Parashar, Rachel Luo, Apoorva Sharma, Sushant Veer, Edward Schmerling, Carson Sobolewski, Mingxin Yu, Chuchu Fan, Marco Pavone

Computation and Language

StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition

Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlabeled audio is abundant. We present StreamHear, a semi-supervised pipeline that adapts a pretrained streaming student by fine-tuning an offline transducer teacher on the labeled training set, generating pseudo-labels on the unlabeled portion, and fine-tuning the student on the mixture. We further introduce a prior-regularized dynamic-programming realignment step that fixes chunk-level word placement using an ASR-hypothesis anchor. Across four datasets spanning financial calls, prepared read speech, and phone-quality dialogue, StreamHear consistently outperforms supervised student fine-tuning and narrows the gap to the offline teacher.
Read the full abstract

All authors Zefang Liu, Chenyang Zhu, Sangwoo Cho, Xujun Peng, Shi-Xiong Zhang, Sambit Sahu

Human-Computer Interaction

The Capturing and Logging Ecological Virtual Experiences and Reality (CLEVER) - Job Simulator Dataset

Virtual reality (VR) motion tracking and interaction data has become increasingly recognized as valuable for machine learning experiments for a variety of purposes, including predicting user identities, predicting user attributes like gender and age, predicting retention and learning, and more. However, there exist a limited number of publicly accessible VR motion datasets. In this paper, we present a new open-source dataset of 95 participants playing the SteamVR game Job Simulator. Additionally, we review existing datasets, detail our study procedure, describe our data collection process, list attributes of our dataset, and suggest future work, impact, and applications.
Read the full abstract

All authors Qidi J. Wang, Xiaozheng Wang, Akhilesh M. Anand, Veera V. Pala, Rohan V. Penmetsa, Ryan P. McMahan