Papers

Semantic query engines ask a large language model (LLM) to judge individual rows, and benchmarks compare these engines on the quality of a few executions at temperature 0. We measure how much another execution changes. We re-execute the text and tabular workloads of SemBench, LRO-Bench, and UDA-Bench through their own harnesses, log every one of 1.2 million model calls, and reanalyze SemBench's published executions. At temperature 0, between 0.07% and 10.2% of rows change their operator output over five executions, depending on the model, and up to 24.0% on one task. Plans amplify these changes exponentially in the number of rows an answer exposes, as a possible-worlds model predicts: on UDA-Bench, a few percent of extracted values change, but about two thirds of the answers do. In SemBench's published results, 21% of text results change quality between executions, including on engines whose plans are deterministic. Several per-query system comparisons, and 16 of 28 tests of LRO-Bench's implementation recommendations, are not settled by the executions the benchmarks run. Changing rows are rows on which models disagree with each other; identical requests within one execution disagree as often as across executions; and one execution's decision margin or reasoning length predicts which rows change. Voting reduces the variance but does not remove it, and a calibrated cascade keeps its guarantee while the rows it returns change. We derive reporting rules for benchmarks and design rules for engines.

A useful language model should know when to answer and when to say "I don't know." Can we improve that decision by training the model itself or by training a separate component to check its answers? We study both approaches on Qwen3-14B for factual questions, using a score that rewards correct answers, penalizes mistakes, and allows abstention. Across three training seeds and two held-out confidence thresholds, a learned answer selector improves threshold-averaged utility over the original model's calibrated confidence filter. On TriviaQA, mean coverage increases from 20.2% to 30.9%, while the pooled error rate among scored answers decreases from 23.0% to 14.5% under exact-match grading. The tested reinforcement-learning changes do not establish consistent gains. On NQ-Open, the selector improves threshold-averaged utility over the filter but still performs worse than always abstaining. A partial human-reviewed audit preserves the TriviaQA finding. Our results support learning to select answers in this setting while showing that reliable abstention across datasets remains unresolved.

In clinical practice, experts often begin by converting raw inputs into a set of expert features before making a decision. While black-box models trained on raw input can outperform models trained on expert views, it remains unclear what predictive signal the raw model exploits beyond what the expert view captures. We introduce an audit framework to quantify this gap using Shared Canonical Component Removal (SCCR). Unlike standard residualization or concept erasure, SCCR selectively removes only those directions strongly shared between learned raw and expert embeddings. Evaluations on synthetic data, coronary artery disease (CAD) detection, antidepressant treatment dropout prediction, and skin lesion classification using SkinCon annotations show that SCCR identifies the ways in which expert views are insufficient and recovers residual predictive signal while minimizing redundancy with the expert view.

Representations of supervised datasets support higher-level machine-learning tasks such as dataset retrieval and distribution-shift monitoring. However, existing approaches typically rely either on hand-crafted meta-features or on dataset encoders trained specifically for representation learning. We introduce TabMF, a framework that repurposes pretrained tabular foundation models (TFMs) as encoders of supervised datasets. TabMF equips a predictive TFM with an architecture-aware dataset-level readout and adapts the model end-to-end using contrastive post-training on stochastic views of synthetic supervised datasets. We instantiate TabMF on TabICLv2 and TabPFN-2.5 and evaluate the resulting representations across six tasks on unseen real datasets. Simple frozen TFM readouts yield competitive representations, indicating that predictive pretraining already induces substantial dataset-level structure. The two TabMF encoders obtain the strongest aggregate performance among the evaluated learned and classical dataset representations, with particularly strong results in dataset retrieval, compact benchmark construction, and distribution-shift severity assessment.

Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy. When tasks arrive sequentially, both approaches suffer from catastrophic forgetting. Fine-tuning on a task degrades prior tasks, and steering only shifts forgetting to the shared steering module. We propose Dream to Remember (D2R), which continually steers a frozen generalist policy toward new tasks, while retaining its earlier skills. As the steering module learns a new task, a frozen pretrained world model rehearses prior tasks through imagined rollouts, anchoring the module to its earlier behavior without a replay buffer or new data. When the world model is faithful enough, D2R learns the new task entirely in imagination. Otherwise, it learns the task in the environment while using the world model only to rehearse prior tasks. On CALVIN, D2R improves eight tasks in sequence entirely in imagination, raising average success from 63.7% to 74.8%, while LoRA fine-tuning on the same sequence drops it to 11.7%. With a frozen off-the-shelf generalist policy and world model, $\pi_0$ and A2World, D2R learns unseen LIBERO-90 tasks in the environment while keeping $\pi_0$'s performance on the LIBERO suites it was fine-tuned on, even though the world model is not accurate enough for policy optimization. Finally, on a real Franka robot, D2R improves three tasks in sequence entirely in imagination while retaining the earlier improvements.

Flow-matching and diffusion models are increasingly used as priors for linear inverse problems, however, most methods are bespoke to one class of trajectory prior. Plug-and-play methods have been proposed, however these implicitly decorrelate the guided trajectory, resulting in broad priors that can struggle when data is sparse. This work proposes $\beta$-Flow: a general plug-and-play method indexed by a correlation parameter $\beta$ that generalises over flow, diffusion, and decorrelated priors, and a confidence parameter $\kappa$ that controls how strongly the path distribution is enforced. Each step requires only one forward evaluation of a denoising network, followed by a Gaussian conditioning step. This step is an exact Kalman update that is not dependent on network gradients. We show that many existing guided samplers can be interpreted as instances or approximations of our method, each implicitly using a different trajectory prior and operator in place of the Kalman gain. From this viewpoint, we provide a qualitative comparison of methods in terms of their implicit biases and assumptions. We demonstrate consistently state-of-the-art level performance across 7 inverse problems over 4 datasets in terms of PSNR and SSIM. Moreover, we demonstrate the utility of this prior control, by showing that confident high correlations (strict priors) work best when observations are less informative, while low correlation is preferred when observations are more informative, reflecting the complementary roles of the prior and likelihood in Bayesian inference.

Large language models (LLMs) have shown strong results in classical code generation and are increasingly used to write the unit tests that safeguard that code. Whether they can do the same for quantum software is less clear, because quantum programs are probabilistic, depend on numerical tolerances, and are judged by domain-specific checkers, so a well-formed test can still disagree with the benchmark's verdict. Existing quantum benchmarks measure whether a model produces a correct solution, but not whether its tests can distinguish correct implementations from faulty ones. We introduce QTestBench, a framework that evaluates LLM-generated quantum test suites against independent benchmark checkers, never treating the tests themselves as ground truth. For each task, QTestBench prompts models to produce syntactic, semantic, and behavioral tests, injects candidate solutions at runtime, and compares each test verdict with the checker's label under three validation cohorts, each answering a distinct diagnostic question. We benchmark five LLMs on eight PennyLane QHack challenges and ten Qiskit HumanEval tasks. Generated suites almost always execute, but discrimination lags behind: the best generator reaches a test quality of 0.71 on QHack and 0.34 on Qiskit HumanEval, so executability alone overstates test quality. Oracle-verified synthetic mutants stabilize bug-detection estimates when natural faulty solutions are scarce, as on three of ten Qiskit tasks that yield none. QTestBench offers a reproducible, cross-framework benchmark for the trustworthiness of LLM-generated quantum tests.

Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic terms that add ranking noise and can hurt strong retrievers. Existing remedies such as corpus grounding, mutual verification and preference alignment treat hallucinated terms as an undifferentiated nuisance to be filtered by agreement heuristics, without a mechanistic account of why a given term appears or a principled criterion for how many terms to keep. We propose Subsequence-Association Filtered, breadth-aware query expansion (SAFE-QE), a training-free, retriever agnostic method that draws on the subsequence-association account of hallucination. We score each candidate expansion term by its corpus conditioned cross-context reproducibility, terms that reappear under randomised query contexts yet lack support in the pseudo-relevant set are flagged as products of dominant hallucinatory associations and down-weighted. Drawing on the characterisation of language generation as a trade-off between consistency (no hallucination) and breadth (coverage), we cast term selection as constrained coverage maximisation over the pseudo-relevant set, keeping a set that is approximately broad but consistent and stable across resampling. We also introduce the Hallucinated Expansion Term Rate, a query side faithfulness metric that counts injected expansion terms no relevant document supports. We evaluate our approach on benchmarked TREC and BEIR collections. Our SAFE-QE is statistically indistinguishable from generative and corpus-steered expansion on nDCG@10 while injecting fewer unsupported terms 4.3 per query against 27.8 for Query2doc and 57.5 for HyDE and on a strong learned sparse retriever, where every expansion method regresses. Faithfulness is therefore available at no measurable cost in ranking quality.

Real-time embedded systems increasingly place GPU-accelerated processing of high-bandwidth sensor streams inside closed-loop systems, but the CPU (the host) remains the primary orchestrator of each iteration. The host observes sensor inputs, submits CUDA work, waits for completion, and commits actuation. This host-mediated path exposes the closed-loop end-to-end latency to I/O interrupts, host scheduler decisions, and CUDA API overheads even after common host-side mitigations such as GPU-memory RDMA or CPU core isolation. This paper presents GPU-resident Execution, a new execution model for real-time sensor processing pipelines that keeps I/O and GPU execution in a long-lived device-resident loop. Sensor inputs arrive in GPU memory, trigger GPU-side processing, and reach GPU-visible output endpoints without any host wakeups. We implement the model in the NVIDIA Holoscan C++ framework and provide reference components for building GPU-resident applications. We evaluate our system on NVIDIA GPUs and SoCs with inference, host-contention, multi-loop, and streaming camera workloads. On an industry-grade 1080p, 60 Hz real-time camera-to-display application, GPU-resident Execution reduces photon-to-display jitter from 4.83 ms to 0.66 ms (7.3x) relative to a CPU-driven GPU-memory RDMA baseline and reduces software-processing jitter from 1.70 ms to 0.01 ms (170x).

Variational quantum circuits (VQCs) are highly sensitive to circuit architecture, yet most quantum machine learning pipelines select a single best design and discard the remaining candidates. This paper addresses whether the structural diversity across quantum circuit search spaces can be used to produce stronger predictions through model fusion. We apply Combinatorial Fusion Analysis (CFA), a model fusion framework that selects and combines multiple scoring systems using rank-score function (RSF) and cognitive diversity (CD), to a pool of 29 architecturally diverse classical models and quantum circuits. Using a diversity-aware model selection method, we identify subsets of maximally diverse models and combine them with both score and rank combination. Experiments on four binary classification benchmarks covering different domains demonstrate that CFA-based hybrid classical-quantum fusion consistently outperform the best individual model on every dataset considered with improvements up to 6.03% in accuracy. When comparing with relevant literatures, the CFA framework further achieves superior performance across all four datasets.

Data augmentation is standard practice for low-resource automatic speech recognition (ASR), but its benefits are almost always reported as aggregate error rates, leaving open why and when a method helps. On four low-resource languages and English at five data sizes, we cross two augmentations that modify existing audio (speed perturbation and SpecAugment) with two that modify text transcriptions and synthesize audio from it. We analyze errors at the phoneme level and find that they help for complementary reasons. SpecAugment has the most reliable aggregate improvements, but increases tone and palatalization errors, whereas text-based methods introduce consonant insertions; in combination, each reduces the errors the other introduces. This complementarity is predictable. Tone and palatalization are each signaled by a single acoustic property and occur least frequently in training (lowest training exposure), and text-based methods that flatten word frequency raise their frequency by 37–38%, reversing those errors while further improving aggregate error. The improvement from combining the methods exceeds the sum of their individual improvements; the superadditivity vanishes by 100 hours, limiting the complementarity to the low-resource regime. Where specific error types matter, we recommend selecting augmentation by training exposure and acoustic properties, both measurable before any training.

Production recommender systems have feature-lifecycle asymmetry: adding new features must produce gains on some metric, while feature removal must not regress any metric. In practice, feature deprecation is hard to prioritize as a feature can fail to be removed if it interacts with other features, its importance changes daily, it cannot be evaluated before production models change or data drift occurs, it is in contention for A/B test space with other launches, it causes regressions in an online A/B test, or it is consumed by multiple models that need to coordinate its deprecation. We present FORTE, a model-agnostic production framework for discovering, validating, and removing features. Its efficient perturbation implementation allows daily feature evaluation. To account for interactions, it evaluates candidate feature sets constructed from all the low-rank features through grouped ablation and its offline results are sufficiently predictive of online A/B tests to allow deprecations to proceed to online testing with confidence. Lineage tracing identifies all downstream consumer models to realize the full savings of removing a feature from the training set. We validate FORTE over 2 large-scale recommender systems and find that it identifies deprecable feature sets which do not cause online regressions, while the impact on efficiency depends on model characteristics. On a search-relevance model, FORTE resulted in 3 nested candidate sets of 32, 48, and 59 features. Online guardrails rejected the largest treatment. The 48-feature set was selected for deprecation, removing 43.3% of the model's features. On a large ranking model, FORTE identified 8 candidates for removal. Retraining and A/B testing confirmed no regression. Its launch reduced the trainable parameters by 29.9%, improved serving throughput by 19.8-25.5%, and reduced annual training costs by hundreds of thousands of dollars.

Gaussian process solvers for linear partial differential equations (PDEs) return posteriors rather than point estimates, but they condition only on equality information: the PDE residual, boundary data, and measurements. Many solutions of interest also obey inequality constraints, including nonnegativity, monotonicity, and absence of arbitrage, which equality conditioning cannot enforce. We prove that conditioning a Gaussian process prior jointly on linear equality observations and a finite-dimensional inequality event is equivalent to conditioning sequentially in terms of Borel measures on the solution space. The physics-informed posterior is therefore a valid prior for the inequality update at virtual points. The combined law is non-Gaussian yet computable through truncated-Gaussian moments, and neither the PDE conditioning nor the inequality update requires modification. We evaluated the construction on a Poisson benchmark, option-price surfaces, and air-quality fields. Under incomplete boundary data, a monotonicity constraint lowered the error of a two-dimensional Poisson reconstruction by $63\%$. On a real S&P 500 option chain thinned to $20$ retained quotes, no-arbitrage constraints reduced held-out extrapolation error by $22\%$ and cut the calendar-arbitrage rate from $10\%$ to $1\%$. On four real air-quality snapshots, nonnegativity reduced a Gaussian moment-based sub-zero-tail proxy by $74\%$ at the sparsest monitor count. Changes in mean accuracy and constraint diagnostics differed across data regimes. The probability of the noisy virtual constraint event under the equality posterior measures agreement with the specified bounds before the update. The construction turns admissibility from a post-processing step into conditioning information for probabilistic PDE solvers.

Variance reduction improves the convergence rate of stochastic non-convex optimization under the average smoothness condition. Existing adaptive variance reduction methods are especially designed for average smoothness and do not adapt to standard smoothness. In this paper, we study how one algorithm can adapt to these two settings and the noiseless setting without knowing the smoothness constants or the variance bound. Given the gradient budget $T$, we develop a two-phase method. The first phase compares two independent gradients and switches to normalized momentum when their difference exceeds a threshold. This phase provides both a candidate with standard smooth and noiseless guarantees and also ensures a bounded expected function gap for the second variance reduction phase. The resulting rates are $O(T^{-1/3})$ under average smoothness, $O(T^{-1/4})$ under standard smoothness, and $O(T^{-1/2})$ without noise. When $T$ is unknown, we propose a method with two paths that attain the corresponding rates with logarithmic factors in the stochastic settings. Here, we use a variance reduction path to deal with average smoothness and employ the AdaGrad-Norm for standard smoothness and noiseless setting. Neither method restarts from the initial point or requires a growing number of oracle calls in each round.

Detecting communicative meaning in dialogue requires modeling not only lexical content but also the participant-role structures through which sentiment, emotion, politeness, and formality (SEPF) are expressed. Existing approaches rely on contextual language representations while leaving semantic roles implicit. We introduce a role-aware transformer architecture that maps the four SEPF dimensions to theory-grounded Semantic Role Labeling (SRL) configurations, incorporating these configurations directly into the transformer's self-attention mechanism. Role-aware attention models non-directional internal states (sentiment and emotion), while directional role-aware attention captures initiator-to-recipient relations for external cues (politeness and formality). The resulting role-aware representations are fused with contextual embeddings through a learned gate that adaptively weights how much role information each input contributes, rather than appending semantic roles as an auxiliary feature vector. Across four benchmark datasets, the framework yields statistically reliable gains over strong BERT-based baselines for emotion, politeness, and formality, with gains concentrated in theoretically predicted cases such as low-frequency, complex emotions and highly polite expressions; sentiment improvements are marginal and non-significant, suggesting that sentiment is conveyed more through lexical choice than participant-role structure. Additional evaluation on real-world data demonstrates that the framework improves both predictive performance and model traceability. These results demonstrate that linguistically grounded modifications to transformer self-attention improve the detection of communicative meaning, generalize beyond benchmark datasets to real-world mental-health data, and yield traceable, role-grounded explanations that extend beyond predictive performance to interpretability.

Discourse particles subtly shape the flow of discourse by reflecting conversational context and interlocutor attitudes, often leaving the truth-conditional meaning untouched. They are also often polyfunctional, with distinct senses which partially overlap with other particles; for example, the exclusive use of English "just" and "only" ("John only/just drinks water"). Despite the frequency of these words in natural language, they have gone largely unstudied due to the subtle nature of their effects. We investigate LLM sensitivity to "just" and "only" in natural conversations using behavioral and mechanistic analyses. First, we find that LLMs and humans similarly prefer the presence of these particles in context, and both are more sensitive to "just" compared to "only". Second, when sampling from LLMs with and without these particles, we find LLMs consistently rate generations as more likely, given their source context, demonstrating their particle sensitivity. In both experiments, instruction tuning increases sensitivity. Finally, we localize particle-sensitive units within LLMs and find the overlap between "just" and "only" is asymmetric: "only" units transfer selectively to exclusive "just", while all "just" units transfer to "only" equally well regardless of sense, suggesting LLM lexical-level particle representations are partially organized by sense. We release our code, sense-labeled dialogue stimuli, and human preference annotations at https://github.com/JiahuiKChen/Not_Just_an_Evaluation.

We consider an inexact version of the Schwarz domain decomposition method in $3$D to solve a Laplace problem in a domain that is the union of two overlapping spheres. We solve each subproblem approximately by projecting its boundary data $L^2$-orthogonally onto the space of spherical harmonics of degree at most $N$. The model problem arises from the ddCOSMO solver used for implicit solvation in computational chemistry. We analyze the Schwarz-spherical domain decomposition method by establishing a new variant of the maximum principle.

How well can vision-language models (VLMs) reason about what is missing from an image? We study this question with OccludeBench, a manually curated benchmark for recovering fully occluded objects from the visual evidence that remains. OccludeBench distinguishes direct cases, where the hidden object must be recovered from a specific physical cue such as a shadow or reflection, from inferential cases, where it can be inferred from broader scene context. Across five VLMs, accuracy averages 42.7% on direct cases versus 62.7% on inferential cases, exhibiting a 20.0-point gap. Humans attain higher accuracies of 63.4% versus 68.5% for direct and inferential images, respectively, with no significant gap. To locate this failure, we introduce OccludeTrace, a four-stage diagnostic that isolates where the visual reasoning process breaks down. The bottleneck emerges when models must recover the relevant object from the projection within the full image: they succeed on only 50% of failed examples, compared with 91% of examples they answer correctly. Extended reasoning, tool use, and few-shot prompting yield inconsistent improvements and do not reliably eliminate the gap. In contrast, an inpaint-then-confront intervention, which prompts models to first generate a candidate hidden object and then evaluate that hypothesis against the visible physical cue, reduces the gap to a statistically non-significant difference for both models with image-generation capabilities. Together, our results establish a tractable, controlled diagnostic for isolating how VLMs reason about visual content that is missing from an image.

Momentum methods such as STORM and second-order momentum track the gradient by adding a transport correction to momentum, at the cost of an extra oracle call per iteration. We introduce randomized momentum transport, which evaluates the correction with probability $q$ and otherwise uses a cheap prediction, with importance weighting that preserves the conditional mean and adds $(q^{-1}-1)$ times the prediction loss to the variance. Under transport-bias, second-moment, and residual-control assumptions, linear minimization oracle (LMO) updates, including normalized, sign, and exact spectral (Muon) directions, retain an $O(T^{-1/3})$ stationarity bound for each fixed $q>0$ with a single-gradient initialization. For unnormalized STORM, some $q<1$ lowers the leading coefficient of our sufficient gradient budget if and only if the gradient-difference noise modulus exceeds the smoothness constant, by at most about $10\%$. An online diagonal predictor admits a regret-to-convergence guarantee. At approximately equal oracle cost, querying a quarter of the corrections lowers the final training loss by $18$ to $43\%$ on MNIST1D and raises the test accuracy of Hessian-vector transport on CIFAR-10 by $1.5$ points.

LiDAR-inertial odometry (LIO) is widely used for real-time localization and mapping, but its reliability can degrade substantially in subterranean environments affected by smoke, dust, and other airborne obscurants, whereas radar remains comparatively robust. This article presents a one-class temporal learning framework for LiDAR degradation detection and reliability-aware localization under such conditions. A broad set of degradation-sensitive cues, including spatial, cross-modal, geometric/motion, intensity, and measurement-recency features, is evaluated to characterize changes in LiDAR sensing quality. Their temporal evolution is modelled over sliding windows using an LSTM autoencoder trained exclusively on nominal operation, enabling deviations from healthy sensor behaviour to be detected without requiring labelled degradation data. The resulting LiDAR reliability estimate governs adaptive selection between LIO and radar inertial odometry (RIO), retaining LIO during reliable sensing and transferring localization authority to RIO when degradation is detected. The framework is evaluated using real-world ground robot data collected in GNSS-denied subterranean tunnels under nominal and dense-smoke conditions. Experimental results demonstrate degradation detection, adaptive modality switching, and continued localization output under severe LiDAR degradation. A feature family ablation study further shows that a reduced feature representation can improve degradation-aware localization performance in the evaluated dense-smoke scenarios, highlighting the importance of feature parsimony in one-class sensor degradation detection. The code will be released as open source to support reproducibility and further research.

We present new algorithms for stochastic optimization problems in which the objective is neither smooth nor convex, subject to a convex constraint set. Our algorithms return a $(\delta,\varepsilon)$-Goldstein stationary point, as recently defined for constrained problems by Liu et al. (2024), with improved complexities, and are the first to achieve optimal convergence rates for this task in several settings. In particular, we design projection-based and projection-free algorithms that achieve a $\widetilde O(\delta^{-1}\varepsilon^{-3})$ rate using stochastic gradients, which we show to be optimal, and a $\widetilde O(d\delta^{-1}\varepsilon^{-3})$ rate using zeroth-order queries, which is also optimal in its dependence on the dimension $d$ and improves over prior work. Notably, our lower bound is given in terms of the Frank-Wolfe gap and holds even for smooth problems, which is of independent interest. These results show that in nonconvex stochastic optimization, the convergence rate is degraded neither by the presence of constraints nor by nonsmoothness. Our analysis is based on a reduction to online linear optimization, extending a related technique from unconstrained optimization.

Discrete graph diffusion models (GDMs) corrupt the graph structure by adding noise independently to nodes and edges under a Markovian noise model. In the unconditional setting without node features, an equivariant denoiser trained on a single graph is able to generate novel graphs and sample-level metrics such as edge overlap and WL kernel similarity find no evidence of memorization. In this work, we challenge this view and show for the first time that graph diffusion models indeed exhibit memorization. Analyzing the reverse diffusion trajectories of GDMs trained on two-block stochastic block models (SBMs), we find a strong train-data bias: the model recovers a corrupted training graph almost perfectly compared to a held-out test graph. We term this conditional memorization, as it surfaces only when the reverse trajectory is conditioned on a corrupted training graph and is not apparent during inference. It coincides with a growing generalization gap, where the training loss improves as the loss on held-out graphs degrades, and it cannot be mitigated by early stopping. The onset of memorization always precedes the emergence of community structure in the generated graphs, thus every checkpoint earlier produces structureless graphs. This behavior holds across all node sizes we test.

Memes play a central role in modern online communication, especially in contexts of political conflict where visual and textual cues combine to convey persuasive messages. We study persuasive technique detection in Ukrainian memes using vision-language models (VLMs). We introduce UkrMeme, a dataset of 200 organically produced Ukrainian wartime memes annotated for persuasion techniques, and PTM-UA, a Ukrainian translation of a subset of the Propaganda 950 benchmark that preserves original visual content while translating meme text. We evaluate VLMs in a zero-shot prompting setup across image, text, and multimodal inputs using hierarchical F1 metrics. Finally, we compare Layer-wise Relevance Propagation (LRP) and model-generated token attributions and analyze the semantic categories of evidence emphasized by each explanation method.

Driving world action models (WAMs) learn from paired trajectories and future observations. Post-training with reinforcement learning allows the policy to explore alternative trajectories and improve planning using driving rewards. However, driving logs contain future videos only for the recorded trajectories, leaving these alternatives without corresponding visual supervision. Thus, we introduce SimVTA, a simulation-grounded post-training framework that combines trajectory optimization with video supervision. First, we sample candidate trajectories for each observation and use a real-world simulator (e.g., World Engine) to render future videos for high-reward candidates in real-world scenes reconstructed with 3D Gaussian Splatting (3DGS). This provides trajectory-matched supervision independent of the model's own predictions. Under a limited rendering budget, we prioritize video supervision for higher-error futures among these rendered candidates. Finally, we optimize trajectory planning with Group Relative Policy Optimization (GRPO) and use a flow-matching loss on the matched videos to update shared representations. At inference time, the model predicts trajectories directly, without simulator calls. On NAVSIM v1, applying SimVTA to a WAM initialization improves PDMS from 86.2 to 91.3 (+5.1). It achieves 88.2 EPDMS on NAVSIM v2 and an average HD-Score of 38.8 in closed-loop evaluation on HUGSIM. Ablations show that updating shared representations with video supervision improves planning, while prioritizing higher-error futures among high-reward trajectories further improves performance.

Dead cell detection in fluorescence microscopy is essential for phenotypic screening and drug efficacy assessment. However, automated identification remains challenging due to signal variability, optical artifacts, and colocalization ambiguities across multiple channels. Markers that define nuclear boundaries do not neatly coincide spatially or temporally with apoptotic markers. Furthermore, marker accumulation kinetics vary across individual cells and apoptosis stages, making universal thresholds unreliable. We present a systematic comparison of several computational approaches for detecting apoptotic cells in nucleus-stained specimens: (1) heuristic methods using intensity thresholds, distributions, correlations, and domain guidance; (2) classification using numerical features (Logistic Regression, Random Forest, XGBoost and LightGBM) and image features (ResNet-18 and EfficientNet-B0); and (3) anomaly detection, also using numerical features (Isolation Forest, one-class SVM and PCA reconstruction) and image features (convolutional autoencoders and Deep SVDD). Using a dataset of 258 images containing 65,527 cells/nuclei across multiple scenes with 243 manually annotated ground truth dead cells, we evaluate each method on metrics such as PR-AUC, Precision, Recall, F1-score, and macro-F1. Our results indicate that classification using image features (deep learning) and numerical features (traditional) achieved the best performance, with ResNet-18 and XGBoost significantly outperforming manually designed heuristics and anomaly detection methods. Our findings demonstrate that such biomedical problems remain highly challenging to solve even with the state-of-the-art computational and learning techniques. We aim to provide an effective decision-support tool to researchers while tackling such problems either fully-automatically or in a human-in-the-loop setting as an aide to domain scientists.

State-space models (SSMs) maintain a fixed-size recurrent state, but reading and writing it at every decoding step can bottleneck hybrid models. This eager state management causes large state I/O with low arithmetic intensity, leaves speculative decoding no cheap rollback, and feeds state quantization error into subsequent recurrent updates. We introduce ReplaySSM, which unrolls the recurrence to represent the state as a checkpoint and a buffer of recent SSM inputs. This separates output computation from checkpoint updates. By updating the checkpoint periodically, ReplaySSM avoids state writes on most steps and roughly halves the dominant state memory traffic. Keeping recent inputs also makes speculative rollback a buffer-pointer operation and enables output-only verification without materializing intermediate states. The same separation allows a low-precision checkpoint to serve output computation on most steps while a higher-precision checkpoint serves recurrent updates, so rounding error in the low-precision copy never enters later updates. We implement ReplaySSM in vLLM for Mamba-2 and Gated DeltaNet. At serving batch size 256, it accelerates standard decoding by $1.20$–$1.47\times$ over a tuned vLLM baseline across four hybrid models, and delivers about $1.8\times$ the throughput of vLLM's speculative decoding on the two 120B-class models. Separate state precisions also reduce output KL divergence and downstream accuracy losses compared with a shared low-precision checkpoint.

Selective state-space models are an efficient approach to long-sequence video modeling. However, their recurrent computation makes it difficult to determine which video tokens drive a prediction. Existing attribution methods often require additional backward passes or repeated model evaluations, making them substantially more expensive than the forward inference they aim to explain. In this work, we introduce READ, a parameter-free attribution method for selective state-space models that unrolls the recurrence at the position read by the classifier. READ traces the contribution accumulated in the recurrent state back to the video tokens that contribute to the final prediction. By anchoring attribution at the classifier's readout, it produces a single spatiotemporal relevance map from which frame- and region-level relevance can be obtained directly. Despite requiring only one forward pass, READ achieves competitive faithfulness and localisation compared with substantially more expensive attribution methods. Experimental results show that READ avoids the systematic relevance biases of existing methods while recovering meaningful temporal and class-specific structure across datasets and backbones. More broadly, our results show that the recurrence underlying selective state-space models is not only an efficient mechanism for inference, but also a direct source of interpretable evidence for their predictions.

Pandora's problem is a fundamental model of sequential search in which opening each box incurs a cost. We study the variant with deadlines, where each box has a publicly known deadline for both opening and selection. We prove that a simple threshold strategy achieves a $1/2$-approximation to the optimal expected utility, improving the previous guarantee arbitrarily close to $1/4$ due to Amanatidis et al. (2025).

Multiple-gradient descent is typically formulated in Euclidean geometry, whereas matrix-aware optimizers use directions induced by other norms. We analyze a single-loop multi-objective method combining a norm-constrained linear minimization oracle with entropic updates of task weights. For any finite-dimensional norm pair, we establish an $O(T^{-1/2})$ ergodic stationarity rate in the deterministic setting, deriving the required trajectory gradient bound from smoothness and lower-boundedness in the unregularized case. With stochastic gradients and a bounded-gradient assumption, one persistent blended-gradient momentum buffer yields an $O(T^{-1/4})$ rate whose leading term has no explicit dependence on the number of tasks. We also establish static regret for the inner weighting objective on arbitrary bounded gradient sequences and, with entropy regularization and a weight floor, iteration-wise inner-gap control after burn-in while retaining ergodic stationarity, conditional on a trajectory gradient bound. The optimal blended gradient can be nonunique in spectral and sign geometries, motivating a selection-independent inner gap. Our analysis extends the spectral construction studied by concurrent MOON to general norms. Experiments compare the method with existing multi-task optimizers and examine its oracle, weighting, and momentum choices.

Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior. Yet despite this growth, systematic support for reuse and reproducibility in MARL-based swarm robotics remains limited and insufficiently standardized: a single experiment is assembled from manually aligned simulator files, training scripts, configuration values, paths, seeds, and environment details, so reuse and reproduction stay fragile even within one research group. To address this gap, we introduce MARGoS, a lightweight, configuration-driven platform developed in this project that elevates these experiment-defining inputs to first-class, platform-managed artifacts. MARGoS enables reproducible experimentation through configuration hashing, end-to-end seed propagation, frozen (immutable) configurations, structured logging, environment fingerprinting, and exportable experiment bundles that facilitate sharing, replay, and verification of results across machines and over time. A five-dimension evaluation (architecture, efficiency, reproducibility, usability, and collaboration) supports our claim that managing experiment variation as a platform responsibility makes ARGoS+MARL experiments easier to reuse, reproduce, and hand off. Our code is available at https://github.com/tombackert/margos.