Your paper timeline
Scroll AI takes the way you would scroll a great paper aggregator: quick signal first, deeper critique when something earns your attention, and challenges when a claim feels off.
Nothing here yet
0
This paper addresses the challenge of "intelligent disobedience" in shared autonomy — when assistive AI must override human commands to prevent harm but remain helpful. The authors formalize this as the Intelligent Disobedience Game (IDG), a sequential Stackelberg game where a human leader proposes actions and an assistive follower with superior environmental awareness decides whether to obey or intervene. The framework aims to provide the mathematical foundations for training safety-critical assistive systems.
0
This paper addresses the problem of forecasting outlier events far in advance in time series data, rather than merely detecting immediate anomalies. The authors propose a two-layer framework that first computes outlier scores using standard detection methods, then models the temporal structure of these scores to predict future anomalies. By assuming that outlier occurrences exhibit temporal patterns (e.g., periodicity or delayed dependencies), the method aims to forecast outlier likelihoods without requiring future observations.
0
This paper investigates why compressing different weight matrices in transformers leads to wildly different outcomes—from negligible impact to 20,000× perplexity increases. The authors map this structural sensitivity across five architectures, revealing that early-layer MLP up-projections are catastrophically fragile while value projections are nearly free to compress. Using Lyapunov stability theory, they explain how residual connections contract errors, and they provide machine-checked formal bounds in Lean 4 to guarantee per-matrix approximation quality.
0
This paper introduces ECI (Effective Contrastive Information), a training-free metric for evaluating hard-negative mining strategies in dense retrieval. The core idea is to leverage the logarithmic InfoNCE bound on mutual information combined with a harmonic mean of signal (hardness) and safety (margin) to predict downstream retrieval quality without expensive fine-tuning. The proposed metric addresses a real pain point in retrieval research: practitioners currently must run end-to-end ablation studies to evaluate negative sampling strategies, which is computationally wasteful.
0
This paper proposes automating the entire cognitive science discovery pipeline—experiment design, behavioral data simulation via foundation models, model synthesis through LLM program generation, and iterative refinement via an "interestingness" critic—to overcome the slow pace and bias of manual research. The vision is a high-throughput in-silico engine that searches vast algorithmic and experimental spaces to surface theoretically informative mechanisms for human validation.
0
AutoMOOSE introduces a multi-agent AI framework to automate the full lifecycle of phase-field simulations in MOOSE, from natural-language prompts to quantitative kinetics analysis. The system orchestrates five specialized agents that generate syntactically valid input files, execute parallel parameter sweeps, autonomously recover from convergence failures, and verify physical consistency through Arrhenius analysis. Validated on copper grain growth, it demonstrates that LLM-driven orchestration can bridge the gap between scientific intent and executable multiphysics simulations, yielding results statistically comparable to expert-authored workflows.
0
NVIDIA introduces Nemotron 3, a family of open language models (Nano, Super, Ultra) built on a hybrid Mamba-Transformer MoE architecture. The core innovation is using selective attention layers combined with Mamba-2 state space layers to achieve high throughput while maintaining accuracy. Key technical contributions include LatentMoE (dimensionality-reduced expert routing), NVFP4 training for efficiency, and multi-environment RL post-training. The paper positions these models as optimized for agentic AI with up to 1M token contexts and granular inference-time reasoning budget control.
0
Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated industries such as pharmaceuticals. However, ensuring its regulatory compliance, factual accuracy, and audience-specific personalization remains a major challenge. We report a production case study asking whether moving compliance and personalization signal from prompt-level rules into retrieval time structured context improves pharmaceutical claims generation, using Composer, a deployed internal tool built on a Golden Data Model (GDM) of 1,867 pharmaceutical claims spanning four products. The GDM integrates claim metadata, references, audience labels, material type, usage history, Match Text Variant (MTV) links, and a six dimension quality score (6C). Across six product-audience segments, the context pipeline improves intended indication (+29%), intended content type (+62%) and intended target audience (+67%), 6C quality score (+86%), and claim reuse (+34%). Production log analysis over the deployment period shows a 29.5% reduction in weekly API cost. We report this as descriptive deployment evidence. This work is a systems and data architecture contribution: it shows that in a regulated, high-stakes domain, restructuring claim data for retrieval-time filtering is a more scalable lever than expanding prompt-level rules, and documents the engineering path data cleaning, graph linking, and quality scoring.
0
Recommender systems typically serve one user at a time. However, in households, members share a finite pantry and follow different dietary rules, making independent recommendations prone to resource conflicts and dietary violations. We formulate household food recommendation as constrained fair division and present FairFRESH, a neuro-symbolic framework that learns per-member utilities, allocates foods under explicit welfare objectives, enforces dietary rules through a deterministic filter, and explains recommendations using Shapley and Banzhaf attributions. Theoretically, we show that no finite penalty guarantees compliance near a dietary-rule threshold, establish approximation guarantees for greedy allocation under utilitarian and smoothed Nash objectives in the stock-free model before filtering, and characterize the scale invariance of Nash welfare. We also use the minimax theorem to analyze rotating shared meals. On NHANES-derived data, the learned utility model achieves Recall@20 of 0.293, outperforming five learned recommenders (at most 0.244) but not a previous-day repetition heuristic (0.321). On held-out four-person households, Nash allocation reduces Gini disparity by 42% relative to conflict resolution while improving Recall@20 from 0.180 to 0.197. It comes within 2% of an upper bound on the smoothed Nash optimum, and rescaling one member's utilities changes at most 1.5% of assignments. All recommendations satisfy the encoded dietary rules, while attribution scores correlate with utility loss upon component removal (r = 0.76). In simulation, shared meals reduce pantry use by about one-third, and weekly rotation increases the worst-off member's utility by 38% over the best fixed meal.
0
Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as an offline, cost-conditional readiness assessment: select a routing policy on calibration data under explicit costs, then evaluate that frozen policy once on held-out test data. On a public 47,837-ticket, eight-class corpus, we compare four trained non-LLM classifiers with four large language models under zero- and few-shot prompting. Under the illustrative cost model (c_ok, c_triage, c_wrong) = (0, 1, 5), TF-IDF with logistic regression and a threshold of 0.60 selected on calibration reduces test cost from 0.763 to 0.472, a 38.1% relative reduction (paired ratio-bootstrap 95% CI [35.7%, 40.4%]), while lowering wrong routes from 15.3% to 3.5%. Frozen calibration-selected policies also beat both always-route and always-defer on held-out test data in 14 of 16 settings in a post-hoc cost-parameter analysis. The strongest prompted configuration reaches 0.477 accuracy on a stratified 1,000-ticket test subset, versus 0.879 for fine-tuned DistilBERT on the same tickets. Isotonic lowers expected calibration error without reliably improving discrimination: GPT-4o-mini few-shot has one confidence value before and after recalibration and correctness AUROC 0.500. We therefore report correctness AUROC and tie-aware risk-coverage area alongside ECE. At the analytically derived break-even probability 0.80, seven prompted configurations defer all tickets; Haiku few-shot routes only 19/1,000. An LLM-only agreement control and margin/entropy rejection baselines further separate calibration from discrimination. The findings are scoped to this dataset, prompt design, model endpoints, and illustrative costs; the work is an evaluation framework, not a new abstention algorithm or universal deployment certification.
0
Large language models (LLMs) differ in capabilities and costs, motivating routing methods that adaptively choose a model for each query. These methods rely on performance prediction: given a query, estimate whether a model will answer it correctly. Most routing methods train separate predictors of candidate models' performance to guide model selection. Our work shows that performance prediction only beats a simple baseline when the candidate model is suboptimal on the task or the performance predictor adds significant capacity relative to the candidate model. Specifically, we take a model's self-confidence, the probability it assigns to its chosen answer, as a baseline and study how much a performance predictor can improve on it. First, we show that any performance predictor that outperforms a model's self-confidence can be used to improve the model's loss: the predictor's advantage transfers exactly in log loss through recalibration. Second, accounting for the predictor's additional parameters, we bound its advantage by the model's suboptimality plus the gain from those parameters. Third, we extend our theoretical results to two-model cascades, which route queries to a more capable model when the first model is predicted to fail. Experiments with 16 language models on four benchmarks show that predictors gain a larger advantage over self-confidence on more suboptimal models. This advantage shrinks as models improve through finetuning. Cascading exhibits the same two patterns: predictor-based routing offers larger gains over confidence-based routing for more suboptimal models, and these gains diminish after finetuning.
0
This paper studies the problem of safe tool execution for large language model (LLM) agents under prompt injection. Using Petri nets, we formalize the execution harness between the LLM and its tools as a supervisory control problem, in which marks represent capabilities, approvals and budgets. Since a transition fires only if the marks it needs are present, an injected request whose preconditions are unmet or already spent is refused regardless of its wording. Treating tool outcomes as uncontrollable, we enforce safety by the conventional maximally permissive supervisor, and this safety transfers to the running system under four assumptions. Moreover, to capture an agent that may propose again after a refusal, we introduce the notion of a replanning closed loop, in which each retry costs an inference call. We show that, in this loop, the conventional supervisor can be arbitrarily more intrusive than a stricter safe one. Furthermore, for a given proposer model, the maximally permissive least-intrusive supervisor is characterized as a value-threshold refinement of the conventional one. Under precise conditions, this refinement orders two concurrent actions by at most one monitor place. On an autonomous release agent, we find by synthesis that safe deployment requires a step that the supervisor can refuse after a rollout starts.
0
In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can extract structured information from unstructured content and deduce attributes users never disclosed. A person's true exposure is not what they post but what can be inferred from it. As these practices become routine, exposure to social engineering attacks becomes an operational certainty, demanding a shared framework for assessment and mitigation. We make this exposure measurable by quantifying how accurately a target can be profiled, and how far that profile enables social engineering attacks. Because no existing model fully spans this continuum, we unify Social Media Intelligence (SOCMINT) and Cyber Human Intelligence (Cyber-HUMINT), two individual-focused disciplines that evolved separately, into a single doctrine-grounded taxonomy of 38 capabilities across the Cyber Threat Intelligence lifecycle, where user profiling bridges passive collection and active engagement. Domain experts validated the taxonomy (Fleiss' $\kappa$ = 0.92). We operationalize its core path (extraction, inference, and susceptibility assessment) as an LLM-augmented multi-agent pipeline, evaluated on real participants' public data. Susceptibility is assessed indirectly: the pipeline predicts how each target would rank personalized engagement options, matching their actual choices significantly above chance. This ranking capacity captures the personalization on which tailored attacks depend. The underlying profiles are accurate: extraction reaches F1 = 97.3%, and inferred attributes score 4.73/5, both far above rule-based and NER-based baselines at negligible cost. The framework augments security analysts' tradecraft rather than replacing it and enables defenders to gauge their own exposure before an adversary does.
0
Individual preferences often become visible only after deployment, when a user accepts one decision or revokes it in favor of another. Jev-style typed interfaces make this feedback explicit by identifying the selected action and, under revocation, the decision it replaces. We study how these consequences persist across requests as Decision-Level Continual Learning from Typed Feedback (Jev-DLC). Jev-DLC treats each correction as both evidence about a recurring action identity and a directed relation between the preferred and rejected choices. It preserves these signals in complementary bounded channels above a frozen scorer and combines their scores to shape the next decision. The method retains no raw interaction history, adds no scorer call, and performs no runtime language-model backward pass. We also introduce TCPA-Bench, a chronological suite that credits a correction only through its effect on later decisions. On TCPA-Repeat, Jev-DLC reaches 44.83% user-macro accuracy overall, 2.43 points above Recent-4 history replay. After at least two earlier feedback events, it reaches 56.07%, a 7.54-point margin over the strongest reported comparison at this depth. These results show how explicit typed corrections can become compact causal state for continual personalization.
0
Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM output.
0
Projected quantum kernels (PQKs) have emerged as a notable approach to circumvent the hardness of machine learning tasks arising from the exponential dimensionality of the quantum Hilbert space. However, recent PQK studies often rely heavily on extensive classical hyperparameter tuning of the radial basis function (RBF) kernel parameter and the support vector machine regularization parameter. The extensive tuning can mask the true representational power of the underlying PQKs induced by quantum feature maps, which has not been explored in detail. Thus, this work aims to expose the structural capabilities of PQKs by isolating and evaluating their native inductive bias through comparisons between untuned and tuned PQKs against the RBF baseline. Furthermore, we propose novel quantum feature maps that leverage two-qubit entanglement to capture multivariate correlations in IoT data. The results show that extensive tuning can lead to competitive performance architectures, while our proposed entanglement topologies exhibit a significantly stronger native inductive bias. This reveals that superior quantum architectural design can yield structurally better PQKs with improvements arising from quantum-mechanical properties rather than from classical hyperparameter tuning.
0
Accurate estimation of diffuse horizontal irradiance (DHI) is critical for optimising photovoltaic system performance and energy forecasting yet remains challenging in regions lacking comprehensive ground-based instrumentation. Recent advancements using Vision Transformers (ViTs) trained on extensive sky image datasets have shown promise in replacing costly irradiance measurement equipment, but the scarcity of long-term, high-quality sky imagery significantly restricts practical implementation. Addressing this critical gap, this study proposes a novel dual-framework approach designed for data-scarce scenarios. First, calculated atmospheric parameters, including extraterrestrial irradiance and cyclic time encodings, are integrated to represent sky conditions without utilising any instrumentation. Next, a sequential pipeline initially predicts synthetic global horizontal irradiance (GHI) and uses it as a feature, to refine DHI estimation. Finally, a dual-parallel architecture simultaneously processes raw and overlay-enhanced fisheye sky images. Overlays are generated through unsupervised, physics-informed cloud segmentation to highlight dynamic sky features. Empirical validation is performed using data from the Chilbolton Observatory, chosen for its temperate climate and frequent cloud variability. To simulate data-scarce conditions, models are trained on a single month (e.g., January) and evaluated across a temporally disjoint, full-year test set. Under this setup, the sequential and dual-parallel frameworks achieve RMSE values within 2-3 W/m^2 and 1-6 W/m^2, respectively, of a state-of-the-art ViT trained on the complete dataset. By combining physics-informed modelling with unsupervised segmentation, the proposed method provides a scalable and cost-effective solution for DHI estimation, advancing solar resource assessment in data-constrained environments.
0
Continual learning requires a model to keep acquiring new skills and knowledge without compromising its existing capabilities. Parametric methods suffer from catastrophic forgetting and loss of plasticity. Non-parametric methods, such as prompts, skills, and harnesses, leverage in-context learning but are limited by context length and lossy plain-text compression. To effectively combine their complementary strengths, we propose HERD (Harness-Evolving Recursive Distillation), a hybrid continual learning framework that learns efficiently in the harness and internalizes experience into cumulative capabilities via distillation. On the harness side, HERD continually refines its skills to capture reusable patterns, while retaining high-residual examples that the skills fail to capture in a bounded memory. On the parameter side, HERD performs drift-constrained distillation with dual anchors, substantially reducing forgetting over long recursive runs. On the 25-stage task stream of TRACE+17, under fixed memory and compute budgets, HERD matches the strongest parametric baseline in new-task acquisition while exhibiting the least forgetting and the strongest retention of general capabilities.
0
Finite element model updating is among the most general approaches to discover constitutive models from structural experiments: since the displacement field is computed rather than measured, it accommodates arbitrary geometries, boundary conditions, and sparse or noisy data. However, every loss evaluation requires a nonlinear finite element solve per load step, and training neural materials requires many such evaluations. Intrusive model order reduction lowers this cost while retaining boundary conditions and variational structure. How can a reduced model remain accurate while the network weights change at every training step? We combine proper orthogonal decomposition and energy-conserving sampling and weighting with adjoint sensitivities of the reduced model, and adapt both the trial space and the sampled elements along the optimization path. The constitutive law is a polyconvex neural network: a logarithmic normalization term, together with a zero-anchored input convex architecture and a growth term, renders the energy polyconvex, coercive, and non-negative by construction, independent of the trained weights. We demonstrate the approach on two experimental datasets and one synthetic three-dimensional example. For a two-phase specimen, training time decreases from nine hours to 41 minutes compared with a full-order identification, without loss of accuracy. In the three-dimensional example, six modes replace 48 672 degrees of freedom, 116 of 15 625 elements suffice to evaluate the internal forces, and training takes 13 minutes. In all cases, the identified material reproduces the measured reaction force and predicts the displacement field from the force alone. Hyperreduction makes the discovery of neural materials from structural data affordable while retaining the advantages of finite element model updating.
0
While arousal can be reliably predicted from musical audio, emotional valence remains difficult to model due to its subjective and context-dependent nature. In this work, we investigate the potential of in-context learning (ICL) with large language models to advance continuous valence and arousal prediction. Rather than predicting emotion scores directly, our framework leverages contextual demonstrations from an auxiliary dataset to refine the initial predictions produced by a small, task-specific base model. We systematically evaluate a text-based ICL variant using lyrics and generated audio captions, alongside a multimodal variant that incorporates raw audio signals. Using the entire MER60 dataset strictly as a held-out test set, our experiments demonstrate substantial performance gains, particularly for valence. Text-based ICL improves the valence $R^2$ from 0.110 to 0.427 with 80 demonstration shots, while the multimodal variant achieves 0.346 with only 10 shots. These findings suggest that training-free ICL offers an effective inference-time strategy for current language models to predict continuous music emotion.