Computation and Language
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Monday 17 August
Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perception across speech, vision, and language, including emotion recognition. However, it remains unclear whether they recognize speech and facial emotion through shared affective functional units or modality-specific pathways. We explore emotion-sensitive neurons (ESNs), sparse decoder neurons selectively associated with emotion categories, in three MFMs: Gemma-4-12B-it, MiniCPM-o-4.5, and Qwen2.5-Omni-7B. Using speech emotion recognition and facial expression recognition as complementary probes, we identify acoustic and visual ESNs. Visual ESNs are causally meaningful: deactivating them selectively impairs recognition of the associated facial emotion, whereas steering their activations selectively enhances recognition of that emotion relative to other emotion categories. Acoustic and visual ESNs further show emotion-matched overlap and similar layer-wise distributions, indicating partial structural alignment between affective representations across speech and faces. Finally, cross-modal interventions reveal bidirectional causal transfer: ESNs identified from one modality produce emotion-specific effects when applied to the other. Our findings provide one of the first cross-modality activation-level analyses of affective functional units in MFMs, suggesting that speech and facial emotion recognition partially converge onto sparse decoder-level components that can be localized and manipulated without training.
Human-Computer Interaction
Appearing Legitimate is Not Enough: Interrogating Synthetic Agents in Representational Processes through a Participatory Design Lens
Synthetic agents built atop LLM-based foundation models are gaining popularity as substitutes for human participants across research contexts, including user-testing, market-research, computational social science, surveys, and qualitative research. We are also witnessing an extension of synthetic agents into experimental implementations of policy consultation, jury deliberation, humanitarian diplomacy, and similar contexts where human participation and representation are central to the perceived legitimacy of the institutional processes. The value of participation extends beyond informational contributions and consensus generation; participation is a necessary, legitimizing condition for democratic political institutions and processes. Treating synthetic agents as human substitutes raises serious political, representational, and ethical concerns. Participatory Design's modes of engagement — probing, priming, understanding, and generating — offer helpful tools for engaging with representational questions of personhood. We apply the lens to three case studies of synthetic agents substituting for personhood at varying representational scales: local policy, enterprise jury deliberation, and global diplomacy. We argue that legitimacy and personhood are integral and mutually constitutive while identifying the ethical, representational, and methodological risks of using synthetic agents in representational processes. We conclude by proposing soft and hard boundaries for designing oversight on LLMs and synthetic agents in representational processes.
Read the full abstract
Computation and Language
A Glyph Is Not a Letter, a Token Is Not a Word, a Space Is Not a Space: What the Units of Voynichese Are Not
The Voynich manuscript (Beinecke MS 408) is usually analysed on three unstated assumptions: that its glyphs are letters, that the strings between blanks are words, and that every blank is a word space. We test all three against the Zandbergen-Landini transliteration with matched prose, cipher, and pseudo-text controls and quire-level resampling. None holds, and the failures share a shape: the order in Voynichese sits at the edges of tokens and at graded boundaries between them, not in the succession of tokens themselves. Glyph regularity is too strong for one-to-one substitution of any tested plaintext (conditional entropy 2.7 bits against about 3.5 for Latin, Italian, and English) and resolves instead onto a quire-stable scale of recurrent multi-symbol units. Tokens form a plausible vocabulary, yet the identity of one token predicts the next by under 1% of token entropy, below every matched control (2-10%), while the glyphs at token edges share 0.2 bits of mutual information, more than in any prose control. Blanks fall into two regimes: the separators transcribers marked uncertain behave like word-internal junctures, are physically narrower on the page (AUC 0.905 from independent image coordinates, with the same sign in a small blind ink audit), and are crossed by learned units even when every space is erased before learning. This profile is also what discriminates. A published Voynich-imitating cipher and a self-citation text generator both reproduce the low entropy, the unit scale, the weak token order, and the null result of a calibrated substitution attack; neither reproduces the edge-glyph coupling or the open, hapax-rich vocabulary (70% singleton types against 41% and 59-60%). Any account of the manuscript must therefore earn, rather than assume, the step from glyphs, tokens, and separators to letters, words, and word spaces, and these are the measurements on which to do so.
Read the full abstract
Computer Vision
Inference-Time Attention Steering for Vision-Language-Action Driving Models
Vision-language-action (VLA) driving models couple a reasoning stage with a diffusion-based trajectory decoder, but do not give a direct way to redirect attention toward safety-critical actors at inference time without retraining. We studied a bounded additive pre-softmax attention bias on the visual tokens of detector localized traffic actors on Alpamayo-R1's Qwen3-VL backbone. It is applied as a fail open forward pre-hook with no weight changes. On 50 lane-change scenarios from the Physical AI World Model Synthetic dataset. The trajectory decoder shows a monotonic dose response in the bias magnitude, separate from a paired zero bias control at every tested magnitude. It reaches $\approx 17$\,cm mean displacement with lateral shifts up to $\sim 140$\ cm at the clamp. A layer ablation places the action-relevant signal in late layers, where the effect increases with the number of hooked layers (2.0cm for the first 8 layers; 67.6cm for all 36). A per call injection audit explains why the Chain-of-Causation text never changes. The mask based bias never reaches the reasoning pathway in this serving stack, so the invariance is verified exposure, not robustness. Steered trajectories tend to shift toward the attended actor, suggesting the bias governs where the model looks rather than encoding a target behavior.
Read the full abstract
Cryptography and Security
Digital Twin-Based Intrusion Detection for Vehicle Powertrain CAN Bus Systems
Existing automotive intrusion detection systems (IDSs) for the Controller Area Network (CAN) largely target discrepancies in message timing, frequency, or sequencing and cannot detect attacks that preserve these properties while manipulating the payload. Digital twins (DTs) have been used to emulate CAN traffic and generate attack scenarios for IDS evaluation, but their use for intrusion detection remains unexplored. This study develops a DT-based IDS that jointly models physical relationships among decoded powertrain signals and identifies attacks through residuals between predicted and observed behavior. A shared-encoder LSTM DT was trained on 17 decoded signals from a real Hyundai/Kia CAN log to jointly predict seven numeric and two categorical gear signals over a 24-step window. A timestep is flagged when a residual exceeds a calibrated threshold, while adaptive rollout protects the twin's input history from sustained contamination. Four attacks (plateau, continuous drift, masquerade, and gear masquerade) were evaluated against the twin and a range-and-plausibility baseline. The DT outperformed the baseline across all attacks, achieving detection rates of 94.6% for continuous drift and 89.2% for masquerade, while the baseline detected almost none of the fabricated payload attacks. These results demonstrate that learning coupled vehicle dynamics enables detection of stealthy payload manipulations that preserve normal CAN communication patterns. False positive rates reached 39.6%, highlighting the need for improved robustness under sustained attacks. The DT-based IDS shows promise for detecting stealthy payload-level CAN attacks that preserve normal communication patterns, supporting behavior-based cybersecurity for connected and automated vehicles.
Read the full abstract
Cryptography and Security
Structured Driving-State Narratives for Small Language Model-Based GNSS Spoofing Detection
Autonomous vehicles (AVs) depend on reliable Global Navigation Satellite System (GNSS) positioning. However, spoofed GNSS signals can induce plausible but incorrect vehicle states. This study develops a small language model (SLM)-based framework for detecting and classifying GNSS spoofing attacks by comparing vehicle behaviors independently derived from GNSS and other sensing sources. The framework converts independent driving states from GNSS and other sensing sources into structured semantic narratives that are provided to an SLM for spoofing detection and attack classification. The performance of the SLM-based framework is compared with large language models (LLMs) fine-tuned on identical training data and evaluated on the same test set. The evaluation considers five classes: no attack, overshoot attack, stopped attack, turn-by-turn attack, and wrong-turn attack. The framework is also evaluated with geographically unseen field data collected in Clemson, South Carolina, United States. Experimental results indicate that the evaluated SLMs achieve performance similar to the LLMs, achieving an average accuracy of 96.99%, precision of 99.05%, recall of 95.59%, and F1-score of 97.18%. In terms of computational efficiency and resource utilization, the SLMs demonstrate advantages over the LLMs by requiring lower inference latency and less GPU memory during both fine-tuning and inference. Evaluation using field data collected in a geographically distinct location further demonstrated its efficacy. The presented framework can detect and classify GNSS spoofing attacks in real-time while requiring relatively low computational and memory resources, and is therefore suitable for deployment on resource-constrained vehicular computing platforms.
Read the full abstract
Machine Learning
Deep Learning for Cross-Border Electricity Price Forecasting: A Comparative Study
While publicly available electricity market data presents a valuable resource for forecasting research, the field lacks established benchmark datasets for standardized comparison. As a result, many studies have relied on different datasets and metrics to evaluate methods in isolated settings, making it difficult to assess progress and compare state-of-the-art approaches consistently. In this work, we use public data to evaluate deep learning models for electricity price forecasting (EPF) across multiple market settings. Our goal is to establish a reproducible framework that enables a consistent evaluation of forecasting models. Although deep learning has been explored for day-ahead EPF, many prior studies are limited to single-market settings, narrow feature sets, or fixed training regimes. This work presents a comparative evaluation of six deep learning models–covering state-space, MLP, RNN, and Transformer-based architectures–emphasizing generalization across markets. We simulate low-data target-market conditions using zero-shot, one-shot, and few-shot learning. Our test set focuses on the Germany-Luxembourg (DE-LU) bidding zone in 2024 using a standardized dataset with calendar, historical price, and market-derived features. Our findings suggest that N-HiTS and NBEATSx perform competitively in limited-data scenarios, while transformer-based models can reach comparable accuracy but tend to require more adaptation and tuning. Model performance also benefits from careful feature selection and hyperparameter tuning, and we note that the differences between the strongest models are often small.
Read the full abstract
Computation and Language
There is No Theoretical Curse of Multilinguality For Embedding Space Structure
A central goal of multilingual NLP is to achieve high monolingual performance per language and cross-lingual alignment for large-scale language coverage with a multilingual model. The curse of multilinguality describes the phenomenon of degradation in multilingual model performance as we increase language coverage, posing a threat to the above goal. This paper asks whether multilingual embedding spaces are inherently incapable of achieving perfect multilinguality without a prohibitive increase in required capacity. We first formalize the goal of "perfect multilinguality", embodied in two multilinguality conditions. We then prove that the minimum dimensionality required for perfect multilinguality grows only logarithmically in the number of languages. That is, we show that there is no theoretical curse of multilinguality for embedding space structure. This suggests that the empirical curse of multilinguality is a result of real world data and training conditions. We back this understanding with a small-scale empirical study. Our paper provides the first theoretical and intrinsic perspective on the curse of multilinguality.
Read the full abstract
Machine Learning
Backward through Time, Algebraically
Linear temporal logic is a modal extension of propositional logic that allows one to state how a system should behave over time. Its canonical domain is the booleans, but discretely-valued judgements are of little use in steering softly-valued systems (neural policies, adaptive controllers, sequence models, etc). In such cases, the goal formula's (dis)satisfaction becomes a training signal, and differentiability becomes a prime concern. Candidate differentiable semantics abound, but navigating them is tricky. Implementations, where available, are shallow embeddings, demanding an upfront commitment to a single semantic algebra and its (usually implicit) conduct. The paper casts the reader as a functional programmer asked to come to terms with this predicament, and refusing. Out of that refusal comes an evaluation engine that is algebra-generic and amenable to differentiation, together with an executable specification of the algebras it can accept. Various algebras are implemented and audited for their behavior, both forward and backward. Each algebra turns out to be a choice of which direction to disappoint, and how. Everything described (and more) is part of the PyTorch library telos, to be found at https://github.com/konstantinosKokos/telos.
Read the full abstract
Computation and Language
Uncertainty-Aware Decision Making in Multimodal Large Language Models
Multimodal large language models (MLLMs) increasingly answer questions whose correctness depends on visual, textual, temporal, acoustic, document, chart, or embodied evidence. Their failures are therefore not only linguistic. A fluent answer may conceal poor input quality, a perceptual error, weak grounding, conflict between modalities, unstable reasoning, distribution shift, or a question that is not answerable from the supplied evidence. This survey organizes the literature on uncertainty-aware MLLMs around a decision-centered framework: uncertainty sources give rise to observable signals, signals must be calibrated or controlled for risk, and calibrated uncertainty should determine the system action. We review work on token and logit uncertainty, semantic disagreement, perturbation instability, grounding and attribution scores, verbalized confidence, verifier and judge scores, conformal prediction, selective answering, abstention, clarification, retrieval, self-checking, and escalation. The central argument is that uncertainty should not be evaluated only as a confidence number; it should be evaluated by whether it improves behavior under insufficient, conflicting, shifted, or high-risk multimodal evidence. We position this survey against text-only uncertainty and abstention surveys, broad MLLM surveys, MLLM hallucination surveys, and safety-oriented reviews. We conclude with open problems in source-aware decomposition, action-aware benchmarks, calibration under shift, black-box uncertainty estimation, broader modality coverage, reproducible reporting, and human-centered uncertainty communication.
Read the full abstract
Computers and Society · Cross-listed from stat.AP
Statistical Assessments of Representational Reforms: A Case Study from Los Angeles
Electoral reforms – including changes to district boundaries, electoral rules, and the size of elected bodies – are a recurrent feature of American state and municipal politics. The representational impact of such reforms is challenging to assess before they are implemented, and even well-intentioned civic reformers are often surprised by the unintended consequences of changes to the political system. We develop a statistical framework for the prospective evaluation of electoral reforms by integrating several modes of analysis: descriptive statistics of the voter file, probabilistic race and ethnicity imputation, ecological inference, and redistricting simulations via ensembles. Together, these tools provide a unified assessment of how proposed reforms affect whose voices are ultimately heard in government. We apply this framework to reforms currently being considered for the Los Angeles City Council, including increasing the number of single-member districts, adopting ranked-choice voting, and introducing multimember districts elected by proportional ranked choice voting. We find that expanding the Council alone is unlikely to substantially improve representation for underrepresented communities. In contrast, eliminating low-turnout primary elections and adopting multimember districts produce larger improvements in representational equity. Our analyses were shared with L.A.'s Charter Reform Commission via public testimony in late 2025. Although motivated by Los Angeles, the framework is broadly applicable to evaluating prospective electoral reforms across American jurisdictions.
Read the full abstract
Cryptography and Security
SentryBus: A Multi-Vantage Observability Model and Validated Instrument for I2C Sensor-Interface Manipulation
Sensor-driven systems in medical Internet of Things devices, drones, and cyber-physical systems commonly trust a measurement once it reaches the embedded processor. An adversary on the digital interface between sensor and processor can supply a plausible value that correct firmware accepts and reports as ordinary telemetry. The hypothesis is that sensor interface manipulation leaves observable evidence on the acquisition path, that the evidence appears at different vantages depending on attacker position, and that a passive host-side monitor therefore has a measurable boundary beyond which manipulation becomes indistinguishable from legitimate acquisition. SentryBus models acquisition behavior on the I2C sensor bus using transaction timing, read and write sequences, transfer lengths, address behavior, register and FIFO state access, and raw data transitions. The adversary is modeled as an inline interposer, parallel controller, sensor replacement, or compromised host, because a commodity target-only sensor cannot initiate transfers or stretch, reorder, or delay bus transactions. A dual sided testbed captures both busses, host memory, and telemetry, and the detector consumes the host facing bus alone while the remaining vantages serve as ground truth. A physiological instantiation reports three measured results: an inline interposer bounded at 0.842 percent of acquisition service time while preserving acquisition schedule and payload content, clean acquisition stability sustained over 6304 seconds at the telemetry vantage with no clock regression, and a negative result establishing that data-transition features encode session specific signal statistics and do not transfer across capture sessions. Instrument characterization shows that a low-cost analyzer can truncate captures without kernel visible error. Controlled attack trials are still outstanding, so no detection rate is claimed.
Read the full abstract
Machine Learning
Dynamic Regime-Aware Conformal Calibration for Reliable Economic Forecast Intervals under Multiple Distribution Shifts
Conformal prediction provides distribution-free prediction intervals but relies on exchangeability, an assumption often violated in economic forecasting because of covariate shift, concept drift, local heterogeneity and latent regimes. We propose Dynamic Regime-Aware Conformal Prediction (DRACP), which combines density-ratio, localized kernel and probabilistic regime-aware weighting with a self-tuning online significance controller in a unified weighted conformal calibration framework. We distinguish three theoretical results: finite-sample validity under oracle importance weights, a coverage-gap bound for estimated weights with rates in effective sample size, and deterministic or regret guarantees for the online controller. We evaluate DRACP against six baselines on 48 real forecasting series covering euro-area and EU-27 HICP inflation, US macroeconomic and energy indicators, and daily financial series. Recent online methods (FACI, strongly-adaptive online conformal prediction and conformal PID) were verified against the authors' implementations. DRACP is not the most efficient method: strongly-adaptive online conformal prediction achieves the best interval score and intervals about 20% narrower. Instead, DRACP provides the most reliable calibration, achieving coverage closest to the nominal 0.90 (0.890), never falling below 0.80 on any series, maintaining the best coverage at all forecast horizons, and performing best during the 2021-2023 inflation surge. The strongly-adaptive method undercovers on 20 of 48 series versus 10 for DRACP. DRACP therefore offers a principled trade-off between calibration and efficiency, favoring reliable coverage when prediction intervals must satisfy coverage standards. An ablation study shows that the online controller and conditional-scale normalization provide most of the performance gain, whereas the weighting components make a smaller contribution.
Read the full abstract
Computation and Language
Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecasting
Next-encounter ICD forecasting predicts which standardized diagnosis codes will be documented at a future visit from the longitudinal record available beforehand. The task is prospective and multi-label: the target note does not yet exist, and several codes may be correct. Structured EHR foundation models capture recurrence and temporal progression, whereas language foundation models generate flexible diagnostic hypotheses. We introduce ICD-Deepresearch, a DeepResearch workflow that composes these predictive foundation models with medical search and ICD dictionaries. Because no source reveals the future code set, research evaluates candidate transitions by linking patient evidence, external clinical relations, and exact code semantics under a fixed top-K budget. Candidate Generation uses SparseEHR to produce an EHR Prior that initializes two bounded Research Expansion rounds; an independent GPT-5 Direct Forecast supplies complementary candidates. Final Selection validates, deduplicates, and jointly ranks both paths, after which a separate module writes rationales without changing predictions. Finally ICD-Deepresearch achieves patient-averaged precision/recall of 24.60/35.09% on MIMIC-III and 25.14/48.32% on MIMIC-IV. Physicians rate 51% and 68% of its retrieved documents useful, compared with 22% and 39% for standalone GPT-5 web search and 32% and 41% for Medical Deep Research. ICD-Deepresearch therefore improves over the registered local comparators while retrieving evidence with higher physician-rated usefulness than the standalone research systems
Read the full abstract
Artificial Intelligence
KernelArc: A Multi-Agent Framework for GPU Kernel Optimization
We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in parallel and coordinate through conclusions-only shared memory, a deterministic benchmark guard, and read-only cross-agent state with plateau-triggered drafting. We evaluate KernelArc on NVIDIA H100 and B200 GPUs using category-representative SOL-ExecBench workloads. The resulting implementations span custom BF16 GEMM, static cuBLASLt Expert-API configuration tables, fused mixture-of-experts backward, shape-gated decoder-layer fusion, native NVFP4 grouped-query attention, and paged prefill attention. In the public SOL-ExecBench leaderboard snapshot recorded on August~20, 2026, KernelArc ranked first on every representative L1, L2, Quantization, and FlashInfer task evaluated. The trajectories support the paper's central motivation: shared multi-agent search can broaden exploration and reach stronger incumbents within a fixed candidate budget, while the value of individual coordination features depends on the kernel and optimization stage.
Read the full abstract
Machine Learning
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings. However, model parameters are often commercial secrets that cannot be disclosed to auditors or end users. To this end, we present PANDA, a scalable system that uses zero-knowledge proofs (ZKPs) to prove the robustness and fairness properties of a model without revealing its private parameters. PANDA is built on top of CROWN, an efficient robustness certification framework that is used in many state-of-the-art formal verification tools for neural networks. The core contribution of PANDA is a novel algorithm for proving linear relaxation bounds for non-linear activation layers, yielding simple, lightweight proofs. Remarkably, our implementation can generate proofs of local robustness for neural networks with more than 2.9M parameters in 5 minutes, and can verify them in 10 seconds. Prior ZKP-based robustness system rely on exponential-time algorithms that cannot scale to nontrivial networks. In contrast, PANDA scales polynomially in the number of neurons in a network, allowing us to support neural networks 4 orders of magnitude larger than previous approaches with significantly reduced prover overhead.
Read the full abstract
Machine Learning · Cross-listed from quant-ph
Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction
Federated deployments of variational quantum classifiers are attractive for cross-organisation risk prediction in supply chains, because raw data never leaves the client, yet data-protection regulations such as the GDPR grant clients a right to request that their contribution be removed from a trained model after the fact. Retraining a federated model from scratch to honour such a request is correct but wasteful, and it is not obvious which quantum circuit parameters actually carry a given client's influence. We introduce Entanglement-Weighted Pruning (EWP), an unlearning procedure for quantum federated learning that scores every trainable circuit parameter with the product of two signals: the diagonal entry of the quantum Fisher information matrix estimated on the target client's data via the parameter-shift rule, and a structural entanglement weight associated with the parameter's gate. Parameters with the lowest scores are pruned, optionally followed by a short fine-tuning pass on the retained clients. We implement the full pipeline in Qiskit for a four-qubit data-re-uploading ansatz trained with FedAvg across five simulated supply-chain-risk clients, and benchmark EWP against full retraining, fine-tuning alone, random pruning, Fisher-only pruning, and entanglement-only pruning, over three random seeds. EWP attains a mean post-unlearning accuracy statistically indistinguishable from the full-retraining oracle, while producing a lower forgetting score and requiring roughly 16 times less wall-clock time. Ablations over pruning threshold, client count, and non-IID strength show that combining the two signals is necessary, as entanglement-only and Fisher-only pruning each substantially degrade accuracy relative to EWP.
Read the full abstract
Cryptography and Security
CUSTOS: Toward Forensic-Ready Zero Trust at the Capture-Containment Boundary
Zero Trust (ZT) replaces implicit trust with continuous verification, but automated containment can destroy volatile evidence before preservation. We propose CUSTOS, a forensic-ready ZT reference architecture whose Forensic Management Point (FMP) links identity and policy context to tiered, rate-limited capture and orders volatile-state acquisition ahead of defender-routed destructive containment. In a controlled real-container experiment, the planted artifact was lost in all 1000 trials when capture and SIGKILL began concurrently, showing that the direct kill outran the evaluated acquisition path. The sequencing barrier completed capture before releasing that same kill in all 1000 trials. In a matched four-condition comparison, only sequencing recovered the transient artifact (200/200); a periodic snapshot-chain baseline recovered long-lived evidence (200/200) but missed the transient artifact at both cadences. Sequencing added 0.140 s of containment delay and 9.99 MB per event. At a 2 s cadence, the chain added no containment delay but suspended the workload for 4.9% of wall-clock and accrued 59.2 KB/s after its root snapshot. The always-on decision record reduced in-process request-path throughput by 1.9-3.0%. In-kernel enforcement and adversarial self-destruction bypass the sequencing barrier; CUSTOS preserves volatile state otherwise lost to defender-routed containment at measured cost.
Read the full abstract
Artificial Intelligence
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization
As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, further exacerbated by red-teaming adversarial attacks. Existing defenses predominantly operate under white-box assumptions, relying on text encoder optimization, weight editing, or inference-time intervention, and fundamentally cannot scale to proprietary models. Black-box alternatives based on LLM prompt rewriting offer broader applicability, yet fail in a critical regime we identify as the benign adversarial problem: prompts that are linguistically safe but still trigger harmful generation due to the model's learned data distribution. We propose DiSCO, a zero-shot, strictly black-box defense that operates entirely at the prompt level as a plug-and-play module, requiring no model retraining, fine-tuning, or access to model internals. DiSCO performs distribution-guided suffix expansion via beam search, optimized through contrastive scoring over safe and unsafe image pools generated by the target model itself, with iterative adaptive feedback until safe content is produced. We demonstrate that DiSCO consistently enhances the safety of both undefended and defended models on the I2P benchmark under multiple red-teaming attacks, achieving 37.7% and 25.13% ASR reduction, respectively, while maintaining semantic fidelity and improving image coherence. As a black-box, architecture-agnostic module, DiSCO can be readily applied to any text-to-image system without necessitating any changes to the model itself.
Read the full abstract
Machine Learning
J-Miner: Recovering the Decision Logic of Fine-Tuned LLM Classifiers as Compact Rules
Task-fine-tuned large language model (LLM) classifiers acquire task-specific decision knowledge, but this knowledge remains implicit in distributed internal computations, making their decision logic difficult to interpret. We introduce the Executable Decision Compression (EDC) framework and propose J-Miner, which mines vocabulary-named variables from internal readouts and learns rules shared across inputs to produce executable explanations. Analysis reveals that a small set of these variables captures much of the classifier's decision behavior, holding for both varying parameter scales within a family and distinct families. Across six binary tasks, a rule using just one variable reproduces 76.7% of source-classifier decisions on average, rising to 88.8% with 16 variables. Most of the decision information retained by these variables comes from internal activations beyond literal surface matching. A lightweight text reader predicts the variable states, allowing the same fixed rules to execute independently of the source classifier.
Read the full abstract
Computer Vision
CAS-FD: Contact-Aware Temporal Sampling for Single-View Foul vs Dive Recognition
Distinguishing a genuine foul from a simulated dive in football remains one of the sport's most contested fine-grained recognition problems, especially when such decisions have to be from a single broadcast view without multi-view camera angle. We introduce a balanced 600-clip single-view Foul/Dive dataset and show that contact-aware sampling concentrating the model's attention around the moment of physical contact rather than treating all frames equally yields substantially improved recognition of this contact- specific problem. The proposed approach achieves 86.0% accuracy and macro-F1 0.860 on the held-out test split, a 12 percentage- point gain over contact-unaware alternatives that grows further on unseen data. We also evaluate each pipeline component against human annotations, establishing where and why the system suc- ceeds and fails. The result is a documented dataset, a reproducible single-view pipeline, and a grounded evaluation framework for fine-grained contact-event recognition in broadcast football footage. The dataset and code are available at https://github.com/hossain- tamim/contact-aware-dive.
Read the full abstract
Computers and Society
Wasted large language models: A life cycle thinking approach
Large Language Models (LLMs) are machine learning (ML) models that have an increasingly large carbon footprint through their development and use. Efforts to increase the energy efficiency of these models have not translated into reduced consumption due to rebound effects such as Jevons Paradox - that increased efficiency drives increased use. There is therefore a need for additional measures to solve this problem. We suggest that one possible way forward is to use life cycle thinking, and view LLMs as products that can become waste. With this perspective, we investigate the potential of the waste hierarchy from the EU's Waste Framework Directive, which suggests five different measures for how to manage waste: prevention, reuse, recycling, recovery, and disposal. We examine how these measures can inform and motivate new types of thinking and approaches to reducing LLM waste and their environmental impact in general. Applying the waste hierarchy to LLMs highlights that preventing waste is essential for reducing the models' environmental impact, mainly because it reduces the need for training new models. Prevention can be achieved through many existing methods for reusing, "recycling", and "recovering" LLMs. Additionally, disposal can be important both for saving energy and for keeping a considerate attitude to the resources being spent on training LLMs. We also call to attention that prevention of unnecessary use of LLMs carry huge potential for lowering the climate impact of the models.
Read the full abstract
Human-Computer Interaction
Why This and Not That? A Collaborative Reflection Approach for Understanding Thought Coverage in Decision Making Support Dialog
Conversational agents that support reflection for decision-making often rely on adaptive dialog policies that map observed user behavior to actions such as probing, deepening, or redirecting. Yet the same pattern can reflect a range of different reasons such as deliberate prioritisation or limited self-access. By modeling the observable pattern rather than the user's reason for it, current policies risk premature assumptions about the user state and inappropriate next actions. To address this gap, we introduce a human-centered method for surfacing this hidden inference step. In a user study with 62 users and 232 collaborative moments, we pause a reflection-support agent when it would normally redirect the conversation, surface its observation, and ask users to interpret the pattern and decide how to proceed. We derive a taxonomy of nine interpretation categories and show that similar reflective states can call for substantially different follow-up actions. Our findings challenge the assumption that adaptive dialog policies can rely on observable behavior alone, and suggest how user-provided interpretations can inform more appropriate conversational actions.
Read the full abstract
Artificial Intelligence
Memory Is Communication: The Frontier Between Remembering and Signaling
A bounded agent may obtain information for a decision from its own past, from peers, or from both sources. Retaining task-relevant history can reduce later communication, while a peer message can supply what memory lacks. Under limits on both resources, how should an agent allocate its information budget? Given a fixed task and decision rule, the memory and message rate pairs attaining a performance threshold form an achievable region under specified rules for using history and peer observations. We call its efficient boundary the remembering–signaling frontier. Across conditions where history permits the same maximum reduction in task loss, we hypothesize that a bounded agent will need less peer communication when it obtains a larger loss reduction from history. In preliminary referential games, target repetition coincided with shorter successful messages, while predictability from a hidden cyclic rule did not shorten them. Experiments varying memory and message rates can estimate the frontier and test this prediction across cooperative tasks.
Read the full abstract
Computation and Language
Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss
Secondary use of electronic health records requires de-identification, yet existing systems miss institutionally situated protected health information (PHI) such as hospital abbreviations, building names, and internal codes whose status is locally determined. We ask whether large language models (LLMs) with in-context learning (ICL) can close this gap and control the precision–recall trade-off. On 100 annotated pediatric oncology notes (5,322 PHI spans) from Texas Children's Hospital, we benchmarked eight LLMs against two purpose-built systems (Stanford TiDE, OpenMed PII) and two pattern-based baselines. Each LLM ran under three prompts of increasing specificity: (1) a HIPAA-aligned baseline, (2) baseline plus the institutional PHI categories it missed, and (3) prompt 2 plus instructions against over-redacting clinical content. We then compared 14~multi-agent and ensemble configurations against the best single prompt, with recall the primary safety metric. LLMs outperformed the purpose-built systems (best F1=0.918$\pm$0.001 vs.\ TiDE 0.779), with advantages concentrated in contextual categories. Naming the missed categories recovered 79% (48/61) of them, and discouraging over-redaction restored precision. No agentic architecture beat calibrated single-pass prompting (F1 0.906–0.907), but LLM outputs surfaced 414~candidate annotation gaps; re-annotation confirmed 227~PHI spans, against which the final prompt reached recall=0.981 (F1=0.907$\pm$0.002). Well-calibrated ICL resolves both the institutional PHI gap and the precision–recall trade-off in one LLM call per note. LLMs cost more to run than traditional methods, but that cost buys a way to audit the reference standard. LLMs are a legitimate, adaptable alternative to purpose-built de-identification systems; institution-specific prompt development should be the primary adaptation strategy.
Read the full abstract
Computation and Language
Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge, but adds retrieval latency, context overhead, and only shallow integration with the backbone. Parametric adaptation is efficient at inference time, but entangles knowledge with model weights and can be hard to update, audit, or transfer. Engram-style hashed memory occupies a middle regime: it stores learned information in an external, addressable table, yet consumes that table through a small learned reader. This raises a basic question: when such a memory is moved across backbones, what matters more, the frozen memory itself or the target-side reader? We study this question through cross-model frozen-memory extraction, in which a memory trained on a source model is frozen and attached to a different target model, with only a lightweight reader trained. Ablations show that learned memory content and correct addressing both matter, while the amount of usable signal depends on how well the reader is aligned to the target model. In downstream question answering tasks, a dual-layer, four-branch reader nearly closes the gap between same-model and cross-model reuse, achieving an average score of 38.8 under our controlled evaluation protocol. Moreover, when the provider reader is directly compatible with the target interface, the frozen artifact can provide substantial utility without target-side training, while optional reader adaptation yields further improvement. These results suggest that Engram can serve as a reusable external knowledge artifact, provided that the target has access to a compatible reader interface; target-side adaptation can further improve alignment when direct reader reuse is insufficient.
Read the full abstract
Computational Complexity
Secret Sharing at the Shannon Ceiling
For every $n\geq 9$ that is a multiple of 3, we construct an explicit access structure on $n$ participants. In every perfect secret-sharing scheme realising this access structure, if $S$ denotes the random secret, then the sum of the share entropies is at least $\left(\frac{n^2}{9}+\frac{2n}{3}\right)H(S)$, and some participant has share entropy at least $\left(\frac{n}{6}+\frac12\right)H(S)$. After normalisation by $H(S)$, these are respectively $\Omega(n^2)$ and $\Omega(n)$ lower bounds and also give the same asymptotic lower bounds on the total and largest expected binary lengths of the shares. This improves by a logarithmic factor the longstanding general lower bounds of $\Omega(n^2/\log n)$ for total share size and $\Omega(n/\log n)$ for maximum share size due to Csirmaz. The proof uses only elementary Shannon inequalities, together with some averaging arguments. The Shannon-information method has universal $O(n^2)$ and $O(n)$ ceilings for the total and maximum normalised entropy lower bounds it can certify, so our construction reaches both ceilings up to constant factors.
Read the full abstract
Computer Vision
The 10th AI City Challenge
The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical AI. Since its 2017 start with vehicle detection, classification, and tracking, the challenge has grown into a broad benchmark suite for multi-camera perception, multimodal reasoning, synthetic-to-real learning, generative forecasting, and privacy-preserving evaluation. The 2026 edition continued this growth with 325 registered teams, up from 245 in 2025, and participation from 26 countries and regions, up from 15. Its six primary tracks cover multi-camera 3D perception, transportation safety captioning and VQA, traffic anomaly reasoning, text-based person anomaly search, generative traffic video forecasting, and cross-city object detection. Track 3 further includes two out-of-domain leaderboards, submitted as Tracks 7 and 8, for fisheye traffic-violation understanding and pedestrian situated-intent VQA. This paper summarizes the challenge setup, datasets, evaluation protocols, leaderboard results, and workshop papers. Across tracks, successful systems combine foundation models with geometric grounding, retrieval or reranking, synthetic-data design, domain adaptation, and controlled inference.
Read the full abstract
Cryptography and Security
Remote-Timer-as-a-Service: Efficient Microarchitectural Leakage in the Cloud with Remote Timers
Edge computing solutions have become a crucial part of the industry, delivering fast, flexible and scalable applications close to the end users, with typical use cases including dynamic content creation, image resizing and chatbots. Cloudflare Workers is one such framework, which handles millions of HTTP requests per second worldwide. To reduce start-up latency, Cloudflare Workers removes process-isolation boundaries between multiple tenants and leverages language-level isolation. This architecture poses the risk of Spectre attacks. To mitigate these, Cloudflare Workers previously introduced several countermeasures such as restricted timer measurements, no shared memory, no multithreading and Dynamic Process Isolation (DyPrIs), detecting potential attacks and process-isolating potentially malicious scripts. We demonstrate that the production implementation of DyPrIs was insufficient. We adopt microarchitectural amplification techniques and discover various possibilities to measure time in the production environment of Cloudflare Workers. Given these techniques, we show that freezing and coarsening timers in the Cloudflare Workers security model is insufficient. Leveraging both timing amplification and remote timers, we demonstrate a remote Spectre attack that leaks a JWT token from a co-located victim worker in the Cloudflare Workers production environment. We outperform the existing attack by orders of magnitude, going from 2 bit/min to up to 12 bit/s at an accuracy of 99.16%, posing an immediate risk to customer data. Following our end-to-end attack, Cloudflare Workers mitigated it in a coordinated effort by integrating the V8 Sandbox limiting transient access to 64-bit pointers, improving the detection capabilities of DyPrIs, and deploying hardware-assisted MPK-based in-process isolation to confine each tenant heap under a dedicated memory-protection key.
Read the full abstract
Systems and Control
Python-based RTL Generator Demonstrated on a Low-IF 2-FSK Wireless Communication System
Hardware optimization is critical in the design of efficient wireless communication systems. Wireless communication hardware often consumes a significant fraction of the total system's power budget, with much of this power used in circuits that reduce various types of noise, particularly in the analog front end. The Single-Chip Micro Mote, or SCuM, uses a crystal-free radio architecture and makes design trade-offs that favor power consumption over noise performance while maintaining standards compatibility with popular Internet-of-Things (IoT) protocols such as IEEE 802.15.4 and Bluetooth Low Energy. In the continued development of SCuM, we recognize that the digital baseband hardware developed can be more closely optimized with the architecture of the chip. In this paper, we present an extensible Python-based RTL generator that is closely linked to simulation and testing environments. This approach provides flexibility for use on different hardware platforms, such as tape-outs and FPGA implementations, and has promise in AI-assisted design workflows.