Papers

We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without additional gradient training or increased inference cost. Given a pre-trained initialization and two checkpoints fine-tuned on a source dataset, the method constructs barycentric candidate weights and performs a small derivative-free search along directions connecting each candidate to the pre-trained model. Candidate weights are selected using a small validation subset of one or more out-of-distribution (OOD) datasets; the selected model is then evaluated on the held-out portions of those datasets, on additional OOD benchmarks, and on the ImageNet validation set to quantify the robustness-accuracy trade-off. The method is inspired by simplex-based derivative-free optimization, including Nelder-Mead and Torczon multidirectional search, but is specialized to the geometry of neural network weight merging. Unlike Model Soup, which typically benefits from many fine-tuned checkpoints, and unlike Model Stock, which applies a fixed geometric merge, our approach uses only two fine-tuned checkpoints and iteratively adapts the merge using validation feedback from OOD data. Experiments with CLIP ViT-B/32 show that the proposed search substantially improves performance on held-out OOD data, including ImageNet-A, ImageNet-R, and ImageNet-Sketch, while keeping ImageNet accuracy competitive. The resulting weights also improve transfer to OOD datasets not used during candidate selection, outperforming the original fine-tuned checkpoints, naive model soups, and Model Stock in our evaluations. These results suggest that lightweight optimization in anchored weight space provides a practical alternative to fixed weight-averaging rules, geometric merging, or single-model selection.

Most existing sports datasets are individual-centric or ball-centric, focusing on individual player actions while ignoring interactions among teammates. In badminton doubles, tactical success is governed by rapid team formation and coordination, yet standard resources for modeling these player interactions are scarce. To bridge this gap, we present DShuttleNet, a comprehensive dataset for badminton doubles curated from elite BWF World Tour tournaments. Beyond trajectory data, DShuttleNet uniquely incorporates expert-labeled "Loss Reasons," transforming the dataset into a diagnostic tool for causal tactical evaluation. We formally define two geometry-driven representations, Teammate-Relative Angle (TRA) and Vertical Shot Angle (VSA), to characterize coordination and shot aggressiveness. To quantify interpersonal synergy, we introduce novel metrics, Court Coverage Efficacy Index (CCEI) and Threat Load Asymmetry Index (TLAI), which evaluate the often-overlooked non-hitting partner's role and defensive coordination. Experimental results demonstrate that conventional models suffer from underfitting when failing to incorporate these coordination-centric features, highlighting the critical importance and potential impact of releasing DShuttleNet. Dataset is available at: https://doi.org/10.34740/kaggle/dsv/16097938.

Learning-to-rank (LTR) models can align rankings with undesignated signals when those signals appear as features or leak into training labels. We compare label-free genetic multi-criteria sorting (open Pikaia strategy variants), which reranks fixed candidate pools using an explicit criteria vector C, to label-trained LTR (LightGBM, XGBoost, RankSVM) under two controlled protocols on MSLR-WEB10K, Baidu-ULTR, WANDS, and Expedia. In the main proxy-skew study, labels remain clean while a calibrated proxy P is available as a feature: Genetic AI rankings show lower Spearman rank-proxy correlation than the LTR peers (e.g. about 0.15-0.16 vs. 0.59-0.87 on WANDS), with both families evaluated jointly on clean nDCG@10 on a bias-utility frontier. In a supporting label-contamination study, training labels are mixed with contaminant B: because Genetic AI methods do not use labels, their bias and utility curves stay flat, whereas LightGBM and XGBoost increase rank-B correlation as contamination rises (OLS bias_slope about 0.58-0.65 on WANDS/Baidu). The results support genetic sorting as an architectural option for optimizing declared attributes on a fixed pool when undesignated proxies or label contaminants must be refused.

Accurate day-ahead photovoltaic (PV) power forecasting requires both strong temporal modeling and adherence to physical PV system constraints. Purely data-driven models often ignore the underlying PV conversion process and may produce predictions that are outside the operational range of a PV system. In this paper, we propose a physics-informed state space framework that combines a differentiable PV conversion model with a selective state space backbone (PowerMamba). Our approach follows a physics-residual decomposition. The physics module provides a structured baseline based on solar geometry, irradiance, temperature effects, and inverter limits, while the state space model learns residual corrections from numerical weather prediction (NWP) inputs over a 24-hour horizon. Experiments on one year of utility-scale PV data show that the proposed method significantly improves forecasting accuracy, reducing RMSE by 38.5% and MAE by 45.8% compared to a physics-only baseline, and outperforming a purely data-driven model. Results further show that incorporating system-level physics provides the largest performance gains, while additional refinements offer only marginal improvements. Beyond accuracy, the model improves robustness by constraining predictions toward physical feasibility, reducing unrealistic predictions under corrupted measurements.

Drug development is an expensive and lengthy process requiring developers to select drugs for human trials and diseases to target. Computational tools that can estimate before testing which drug-disease candidates are most likely to reach FDA approval could reduce development time and costs through early program advancement and disease prioritization. Yet existing approaches predict outcomes at a single level or stage or do not distinguish between disease outcomes for the same drug. We ask (1) whether FDA approval can be forecast for a drug-disease pair using only pre-clinical trial information, and (2) whether these forecasts can help prioritize diseases for the same drug. We built a cohort of 14,134 drug-disease pairs by reconstructing programs from ClinicalTrials.gov, extracting disease-level approvals from FDA label documentation, and enriching each pair with molecular, disease, ADMET, target, and pathway features. We divided the cohort into pre- and post-2019 programs and trained a classifier on pre-2019 data to predict FDA approval. On the post-2019 cohort (2,637 programs), the model would have prioritized a program that ultimately gained approval over one that did not approximately three out of four times. For drugs tested across multiple diseases, selecting the model's highest-ranked disease would have identified an ultimately approved disease 61.3% of the time, compared with 40.7% under random selection. These results show that public pre-trial information contains signal for forecasting FDA approval at the drug-disease level and can help prioritize diseases for the same drug. We provide a public web tool for SMILES- and ICD-10-based drug-disease approval forecasting.

Many systems read the latent space of a variational autoencoder (VAE) as discrete codes, and rely on each latent being read back as the code it was written as. Shannon (1948) took such a shared codebook as given; inside a VAE nothing enforces it. We prove that no item of a standard training report can reveal whether the written and read codes agree on encoded data. We construct two VAEs that reconstruct every input perfectly, infer exactly, and match on every per-example ELBO and every code histogram, yet agreement is one in the first and zero in the second. We then show that the ELBO's own terms bound how far a measured agreement can move: the variational gap bounds the shift to exact inference, and the rate bounds the shift to generation from the prior. For Gaussian posteriors, a mean-field encoder pays an exact price in the gap that depends on its choice of axes. On probabilistic PCA the gap certifies a trained encoder in all 75 settings we test, at agreement between 0.76 and 0.97. On 240 trained VAEs, a floor set by the rate and the dataset size rules out rate-side certification in advance for 66 models, and none of them certifies. The results yield a simple protocol, Certify-or-Measure, for any pipeline that reads a VAE as codes.

Modern experiments increasingly produce rich post-treatment objects—such as text, images, and video—that may provide early surrogate signals for outcomes that are delayed, expensive, or observed only for a subset of participants. A pretrained encoder can turn such an object into a strong generic embedding, but the embedding is not trained for the estimation tasks required by a causal estimator and may emphasize information irrelevant to the causal target. We propose SIRNET, a Surrogate-Informed Representation adaptation framework for neural-NETwork-based causal estimation in the presence of unstructured post-treatment surrogates. Starting from pretrained surrogate embeddings, SIRNET learns a shared adapter jointly for outcome prediction, treatment propensity, and arm-specific surrogate marginalization, beyond the generic pretraining objective. The resulting covariate and surrogate representations provide a common interface for these nuisance tasks. The final treatment-effect estimate and confidence interval are obtained from cross-fitted orthogonal scores that attain the semiparametric efficiency bound under the stated nuisance-rate conditions. We also validate SIRNET's performance in synthetic and semisynthetic experiments, as well as the Anti-Amyloid in Asymptomatic Alzheimer's Disease (A4) trial, using frozen pretrained brain-MRI embeddings as surrogates for a long-term outcome.

Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectively to this setting. We introduce GF-Bench, a PyTorch-based framework and dataset for generating diverse failures in distributed GPU workloads. The framework supports extensible workload and fault-injection logic; based on this design, the current release targets failures visible in multi-GPU communication logs and provides 220 labeled two-GPU executions covering normal runs, CUDA out-of-memory fail-stop failures, and persistent straggler fail-slow failures. Using GF-Bench, we evaluate three sequence-based methods (DeepLog, LogAnomaly, and LogBERT) and the LLM-based LogPrompt on parsed logs, and additionally evaluate LogPrompt on raw logs. On parsed inputs, no method reliably detects both failure classes, and the highest overall F1 score is 0.667. Raw inputs raise the overall F1 score of in-context LogPrompt to 0.983, at 9.0x its average input-token usage and 8.7x its per-run cost. These results expose a substantial trade-off between effectiveness and efficiency: generic log parsing lowers operational cost but discards the distributed execution context required for accurate failure detection. GF-Bench provides a reproducible basis for studying cost-efficient analysis methods and can be extended to additional GPU workloads and failure types.

Cascaded recommender systems use the same user history for retrieval and ranking, while the two stages have access to different information at different points of an interaction. We propose the Lifecycle-aware Interaction Factorization Transformer (LIFT), which decomposes each interaction into ordered Request, Item, Context, and Action states and models them as a causal sequence. Retrieval reads the Request state, while ranking reads the Context state, allowing both tasks to share history modeling while preserving stage-specific information. LIFT instantiates this representation with Role-Conditioned Attention and a lightweight Pre-LN Bias. On ML-20M and Taobao, LIFT achieves the highest Joint Score among the evaluated joint models, improving over the strongest baselines by 4.9% and 3.6%, respectively. Loss-weight sweeps show favorable retrieval–ranking trade-offs, while ablations and scaling analyses further examine lifecycle sequence construction, model components, and capacity settings.

Longitudinal medical imaging analysis is a cornerstone of modern medical practice and patient care. Deep learning applied to longitudinal imaging offers wide potential to enhance diagnosis and track disease progression by capturing spatial changes over time. With major advances in single-timepoint deep learning for imaging, there has been growing interest in longitudinal image analysis, given its increased clinical relevance, though technical challenges remain. Several recent innovations may lead to a new era of multi-timepoint image evaluation, yet the scientific landscape, recent progress, and areas of need remain under-characterized. To address this gap, we conducted a scoping review of deep learning methodologies applied to longitudinal medical imaging, yielding 102 studies published between 2018 and 2025. Neurological disorders (48%) and ophthalmic conditions (12%) were the most common clinical applications, with MRI serving as the predominant imaging modality (67%). Sequential feature modeling approaches combining convolutional neural networks (CNNs) with temporal models (LSTM/RNN) were the most frequent methodology (40%), followed by direct feature aggregation across timepoints (23%). Most studies targeted classification tasks (56%), while external validation was performed in only 24% of studies. Our findings highlight that deep learning-based longitudinal imaging analysis remains a promising field, though newer temporal architectures and larger datasets may improve success and clinical adoption of these tools.

The spread of fake news may cause severe social consequences. Existing fake news detection methods mainly focus on stylistic variations or incorporate external information such as explanations. However, news articles are often rewritten under different emotional backgrounds while preserving their underlying factual claims, which may affect the robustness of detection models. In this work, we investigate fake news detec- tion under fact-preserving emotional variations. To study this problem, we construct emotion-rewritten test sets and generate explanations from the original news articles as stable background knowledge. We then propose a Gated Cross Attention (GCA) framework that adaptively integrates emotionally rewritten news with the corresponding explanations, enabling the model to focus on informative explanation content while reducing potential mismatches caused by emotional reframing. Experiments on PolitiFact, GossipCop, and LUN demonstrate that the proposed method achieves notable improvements under multiple emotional conditions on PolitiFact and LUN, while maintaining competitive performance on GossipCop. We further analyze the effects of explanation guidance and gating mechanisms under different emotional conditions. Our code and data are available at: https://github.com/Flulike/fakenews gca .

We present JoyAI-Voice~2.0, an end-to-end anthropomorphic speech generation model built upon a fully continuous, dual-encoder architecture. Raw speech is encoded into continuous latents and partitioned into patches. Each patch is decomposed by a semantic-acoustic dual encoder into a semantically purified representation and an acoustic representation, which are fused and jointly fed to a causal autoregressive Transformer for planning. The Transformer predicts the conditioning for the next patch, and a local diffusion Transformer renders its full latents for 48\,kHz synthesis. The model is trained with a joint flow-matching and stop-prediction objective, followed by supervised fine-tuning and reinforcement learning with DiffusionNFT to improve model performance. It achieves the lowest average word error rate of 2.51% on Seed-TTS, a 14.9% relative reduction over the strongest baseline, and state-of-the-art attribute fidelity on InstructTTSEval in both Chinese and English, leading on 5 of 10 perceptual dimensions with the highest overall score of 0.893 on MDVD-Eval.

As GUI-based mobile agents rapidly progress, rigorous safety evaluation of their autonomous decision-making in realistic app interfaces becomes increasingly critical. Existing benchmarks mainly focus on execution-level anomalies using task success or hijack rates, but fail to capture the in-task goal deviation risk in multi-candidate selection tasks, where the decision may be steered toward an attacker-specified target, even in violation of instruction-implied constraints (e.g., cheapest/highest-rated), without any overt execution anomalies. We present DIBench, a decision integrity benchmark for measuring this risk in mobile agents. DIBench covers 7 commercial and 3 simulated apps with 5 task types. Under a threat model restricted to non-privileged UI content, we construct 8 deceptive injection probe instantiations that can steer critical selections without overt anomalies. The benchmark includes 1,000 clean and 36,672 injected instances, with a unified protocol and integrity metrics for comparison. Experiments spanning 4 agent frameworks and 7 base models show that completion-based evaluation can overestimate agent trustworthiness and miss decision-integrity risks: deceptive injections steer selections and shift early action policies, inflating completion rates and creating a misleading illusion of safety. Common defenses, including detection, image preprocessing, and prompt reminders, yield inconsistent integrity gains. Overall, DIBench provides a unified, reproducible benchmark to quantify the risk of in-task goal deviation in mobile agents and enable comparable evaluations of safety defenses.

Soft tactile sensors elevate robotic touch through enhanced flexibility and adaptability, yet most existing designs depend on embedded electronics that are susceptible to interference and environmental limitations. In this work, we leverage fluid-solid interactions to develop a class of soft tactile sensors that operate entirely without electronics at the sensing site. The sensor comprises a fluid-filled elastomeric channel connected to only two external pressure sensors. Touching different regions of the elastomeric surface displaces the viscous fluid, producing distinct pressure patterns that encode both touch position and force. These signals are decoded through a machine learning framework that integrates feature extraction, soft clustering, and adaptive neuro-fuzzy inference to achieve accurate localization and force estimation. We validate this concept through single-point touch localization and force estimation in a linear (1D) sensor and extend the same sensing principle to 2D tactile mapping by routing the channel across the surface using space-filling curves, while maintaining the same minimal hardware setup. This simple approach remains effective in environments where conventional electronic sensors often fail, such as underwater or in the presence of magnetic interference.

The rapid growth of deep learning has substantially increased the energy consumption associated with model training, making energy efficiency an increasingly relevant design criterion. This study empirically measures the energy variation of training seven modern computer vision architectures, MobileNetV3-Small, MobileNetV3-Large, EfficientNet-B0, EfficientNet-B1, ViT-B/32, ConvNeXt-Tiny, and ViT-B/16 for the ImageNet-1k classification task, using a homogeneous 10,000-image subset (ImageNet-10k) and a uniform 40-epoch baseline configuration executed on two NVIDIA Tesla P100 GPUs at the Bioinformatics and Computational Biology Center of Colombia (BIOS). Energy was recorded directly via NVML and contrasted with the computational complexity of each model. The results show a Pearson correlation of 0.85 between floating-point operations (GFLOPs) and energy consumption in kWh, indicating that computational complexity is a strong but imperfect predictor of energy expenditure: architectures with comparable GFLOPs exhibited consumption differing by up to 3.1x due to differences in the hardware efficiency of their dominant operations. The EfficientNet variants offered the best balance between classification performance (Val Top-5 up to 97.15%) and energy efficiency (0.457-0.611 kWh), while Vision Transformers exhibited the highest relative energy consumption and lower classification performance under the evaluated configuration. These findings guide architecture selection in energy-constrained computing environments.

We propose a fine-tuning method for flow-matching diffusion models aimed at realistic artificial light modeling without the need for a large training dataset. We address the task of controllable interior image editing, where the goal is to turn artificial light sources on or off while preserving the scene geometry, object placement, materials, and visual identity of the original image. To achieve this, we decompose the task into two independent formulations. We introduce the LoRA Direction Training Method, which extracts the pure direction of the LoRA adapter effect in the diffusion model flow field, and we also introduce specialized loss functions to ensure the realism of the inverse transformation. Additionally, the resulting increment map is used for more precise adjustment of the lighting color and temperature.

Multi-agent LLM systems pair a sender with broad context and an executor with a limited local view. We study when a short message improves the executor's next decision, when raw context is preferable, and when a stronger sender helps. Our framework, receiver-relative bounded coordination, expresses message utility as receiver gain minus protocol tax. Compression beats raw context when tax savings exceed losses from omitted information and decoder mismatch. Even Bayes-sufficient compression can fail when a bounded executor cannot use its surface form. A three-stage decomposition separates externalization, absorption, and action closure, explaining how errors remain after the correct content reaches the receiver. Under a single-crossing condition, sender upgrades help above a receiver-burden threshold. Across six benchmarks, the same Qwen protocol raises ContextBench joint accuracy from $0.633$ to $0.775$ but lowers ToolSandbox from $0.889$ to $0.653$. Fixed-message replay reveals closure failures despite correct artifact recovery. These results guide an inference-time selector that improves the accuracy-cost frontier on the evaluated communication regimes.

Chemical reaction-condition optimization – choosing the catalyst, ligand, solvent, reagent, temperature, time, and atmosphere that jointly maximize yield and stereoselectivity – is a central, judgement-laden subtask of organic methodology research that large language models are increasingly expected to support. Yet existing chemistry benchmarks evaluate reaction-class labelling, retrosynthesis, or SMILES manipulation, and do not ask models to read a real condition-screening table and pick the best set. We introduce RxnOptBench, a benchmark whose every option and precedent is a real wet-lab entry mined from the optimization tables of organic-methodology papers published in 2025, graded by a continuous relative score derived from a declared headline utility that combines reported yield with enantiomeric excess (ee), diastereomeric ratio (dr), and regioisomeric ratio (rr), and equipped with a paired precedents-vs-no-precedents design that isolates in-context use of literature evidence from parametric memorization. Across nine frontier LLMs and three Chemistry LLMs, even the best models leave substantial headroom: chemistry-specialized models fall to the random-baseline floor on multi-axis selection, while open-weight models have closed most of the gap to proprietary frontier models. We release the final human-reviewed benchmark test set and evaluation code.

Mixture-of-Experts (MoE) architectures allow frontier language models to scale to trillions of parameters, but their deployment is constrained by massive memory footprints and memory-bandwidth limitations. Although modern accelerators provide Sparse Tensor Cores (SpTCs) that reduce weight storage and increase throughput through low-precision semi-structured sparsity, exploiting them for MoEs remains challenging because of substantial model-quality degradation and the lack of grouped sparse GEMM primitives. We present an end-to-end hardware-software co-design framework that compresses expert weights into hardware-native, low-precision sparse representations and accelerates their execution on SpTCs. Algorithmically, our framework relaxes discrete semi-structured support selection through continuous reparameterization, enabling differentiable joint optimization with quantized weights under a router-weighted reconstruction objective and scalable expert-parallel compression. Systemically, we develop a custom grouped sparse GEMM kernel tailored to low-precision sparse MoE inference on SpTCs. Across MoE models ranging from 30 billion to one trillion parameters, our framework improves state-of-the-art joint sparse-quantization accuracy by up to 4.35 percentage points while preserving 96.09% of the original model's performance. On NVIDIA B200 GPUs, our kernel outperforms the vendor baseline by up to $1.65\times$, increasing serving throughput by $1.18\times$ and reducing end-to-end latency by up to $4.03\times$. These results establish hardware-software co-design as a practical path toward scalable and efficient MoE deployment.

Algorithm-based fault tolerance detects corrupted matrix multiplications by comparing a checksum of the product against a checksum recomputed from the factors, flagging a fault when the residual exceeds a threshold. The classical threshold is tau = Ku, derived from a dot-product rounding bound that requires Ku <= 0.01. At bfloat16 with contraction length K = 4096, Ku is approximately 32, so the bound does not hold and the threshold is not defined. Prior work therefore evaluated checksum ABFT only at float32. We supply the missing calibration. This paper is a characterization of a detector under an output-level, post-GEMM perturbation model; it is not a characterization of faults in silicon, and no rate reported here estimates fault incidence in deployed hardware. We fit a Generalized Pareto distribution to 7.99e7 clean per-row residuals and extrapolate a threshold at a per-GEMM false-positive rate of 1e-6, obtaining 3.1445e-6, which sits between the two clean sample maxima we observed. The independence assumption behind the per-GEMM conversion is checked empirically rather than asserted, at a variance ratio of 0.985 against a binomial reference. Against this threshold the detector catches 304 of 400 single exponent-bit flips (76%), failing a bar of 90% that was registered before any data was collected, and catches 0 of 600 low-mantissa flips. Detectability is invariant in K across a 16x range even though the clean noise floor falls as K^-0.4999: signal and floor scale together, so bit position governs detectability and contraction length does not. This falsified the mechanism the study was designed around. We report four registered predictions that failed, including that one, and four retractions of our own earlier findings, two of which were caught by pre-publication audit rather than by prediction. Code, data, and timestamped pre-registration documents are released.

Fast and accurate simulation of hemodynamic behavior within vascular networks is essential for numerous clinical applications. However, obtaining high-quality and computationally efficient flow measurements across complex vascular networks remains challenging. To address this, we first decompose the vascular network into a set of bifurcation units and then develop an operator network capable of mapping unit-specific parameters to the local solution fields of each bifurcation unit. By lumping the Windkessel-model outlet parameters and incorporating inlet boundary conditions from the solution of parent units, the flow and pressure fields can be rapidly approximated. Subsequently, operator-network-driven Schwarz waveform relaxation is applied across bifurcation units to correct discontinuities and improve numerical accuracy. On 7-segment and 55-segment arterial tree models, the proposed method achieves $13\times$ to $17\times$ wall-clock speedups over conventional 1D numerical simulation, with relative $L^2$ errors of 1% in both pressure and velocity. The resulting pulse wave velocity biomarkers agree with the conventional reference to within 1–2%, and the same trained operator generalizes to different tree-like 1D vascular network topologies.

Spiking Neural Networks (SNNs) offer an energy-efficient approach to processing event-camera data, yet out-of-distribution (OOD) detection remains challenging in this setting. Existing OOD detection methods often depend on model outputs or computational components that are unavailable in object detection SNNs or are poorly suited to low-compute deployment. To that effect, we show that the subthreshold membrane potential \(V_{\mathrm{mem}}(t)\) provides a useful internal signal for detecting distribution shifts. Simple per-channel statistics derived from these membrane dynamics enable OOD detection. To evaluate this approach, we introduce Gen1-C, an event-camera corruption benchmark developed upon the Prophesee Gen1 automotive detection dataset, containing six sensor-motivated histogram-level stress tests at five severity levels. We further propose the Multi-Descriptor Deviation (MDD), a corruption-blind method that operates on membrane-potential statistics. At the highest corruption severity, MDD achieves an AUROC of more than 0.88 on five of the six corruptions using only a bounded 64-frame observation window. Notably, the remaining corruption is also the one that has the smallest effect on the underlying detector. These results show that the temporal membrane-potential dynamics can provide an effective and low-cost signal for OOD detection in SNN-based event perception.

Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child allocation constraints, affine objects, and distributed escrow do not by themselves prevent overspend when replies are lost, effects complete after timeout, messages repeat, branches partition, or DAG joins alias one lineage. We formalize fault-tolerant budget conservation for distributed multi-agent delegation. Budgets are quantized resource vectors represented by exclusive escrow credits that move through a delegation DAG. Before dispatch, a branch converts credit into an operation reservation bound to lineage, epoch, normalized effect, maximum charge, receiver, and idempotency key. It persists a signed dispatch permit with quarantine; the gateway verifies that permit before first acceptance. Uncertain effects remain charged until authenticated settlement, a fenced authoritative no-effect proof, or permanent retirement. We prove ownership partition, ledger and effect conservation, descendant non-amplification, at-most-once settlement, late-completion safety, and partition confinement under explicit mediation, durability, authentication, normalization, and gateway assumptions. An indistinguishability result shows that partition-local availability requires exclusive preallocation. Bounded TLA+ checking, an independent JavaScript explorer, and crash-injected two-process SQLite experiments exercise the declared scope and detect timeout-refund and historical-certificate-validation mutants. The mechanism preserves the issued budget bound across the evaluated crash, retry, duplicate, partition, join, and late-completion schedules.

Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a trigger appears in the input. Existing backdoor defences for LLMs attempt to remove the backdoor but inadvertently shift the model's output distribution to benign prompts, which can result in degraded model performance and safety. We propose NEEDLE, a training-free method for targeted backdoor removal. Once a trigger has been identified, our method estimates a backdoor direction and a refusal subspace through activation vectors, then applies sequential weight orthogonalisation to suppress the backdoor while preventing changes in refusal-related representations. NEEDLE requires neither a clean reference model nor the original poisoned training data. Evaluation is conducted across multiple model families and attack types. NEEDLE achieves the lowest mean Attack Success Rate (ASR) among the evaluated defences, including 0% on challenging code injection attacks, while resulting in the lowest KL divergence and minimal changes in capability and safety.

Self-modifying AI agents can replace, fork, and roll back identity-bearing software while descendants remain executable. Per-successor authorization does not constrain the resulting population: siblings may duplicate quotas, combine permissions, survive ancestor cuts, or overlap predecessors during promotion. We define authorization succession, which conserves authority across the active frontier of a single-parent generation forest. Our external protocol binds each generation to a manifest, root, unique parent, complete lineage, and fresh population sequence. Separate invariants bound root-lifetime consumption and current population exposure. A staged reservation freezes predecessor residual authority during replacement, while a partitioning fork validates the complete child family. Each commit atomically fences the predecessor and activates successors. Ancestor cuts invalidate dependent descendants; rollback creates a fresh generation without restoring spent authority; and a new root requires an independent grant. Under complete mediation, authenticated records, sound effect abstraction, durable monotone state, and complete lineage accounting, we prove population-safe succession, fork conservation, revocation closure, atomic handoff, rollback non-reminting, and exclusion of self-certification. An executable evaluation covers 32 registered decisions through direct-call and mailbox mappings (64/64 replays; 28 allows, 36 denies). An independent checker accepts all 64 original traces and rejects 28/28 semantic mutants; 12/12 profile invariants, 16/16 crash cuts, and 32/32 contender schedules pass. Two external adapters reproduce all 32 decisions around measured OurArk and Darwin Godel Machine mutations, including fresh-process restart, atomic succession, and predecessor rejection. The results establish authorization succession for registered protected effects.

Software that hands branching decisions to a model needs a declared option and a probability it can threshold. Typed decision models, also called System One models, return such probabilities without generating text, while supervised classifiers and generative language models are the established alternatives. One harness sends eight decision-model checkpoints from six families, including the hosted model Jev, and four open generative models from three developers the same semantic requests, and scores trained and zero-shot classifiers on the same workflow, intent, emotion and social-science items. With task labels, a fine-tuned DeBERTa-v3-large has the highest observed accuracy on every labeled benchmark but one. Without labels, no decision model is significantly more accurate than Jev on workflows or intents, but Gemma-4-31B matches it on workflows and exceeds it on CLINC-150 at higher cost and latency. Stated probabilities of generative models become unreadable when replies miss the key format, whereas key likelihoods avoid this but can saturate. A guaranteed 5 percent risk leaves Jev 0.528 of the intent decisions, and an in-scope threshold still accepts 0.310 of out-of-scope requests. On typed-decisions, swapping yes and no flips 50.5 answers per hundred for Jev and at least 16.8 for every generative model tested, against at most 6.5 for four fine-tuned decision checkpoints. Exposure to a benchmark's training data explains the largest lead of an open checkpoint, which vanishes on rater-labeled emotions. An intent-trained first stage escalating to Gemma-4-31B reaches that model's accuracy at about Jev's price. The results yield condition-dependent design rules for automated decision gates.

As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generation tasks becomes a critical challenge. Unlike unimodal threats, synergistic risks emerge when text and image modalities are coordinated to produce harm that significantly exceeds their individual components. We introduce UnifiedAttack, a novel benchmark designed to evaluate LMM safety in collaborative scenarios by focusing on the harmfulness gain achieved through cross-modal synergy. The benchmark incorporates samples filtered for their multimodal potential alongside a novel subset of synthesized disinformation queries. To verify identified vulnerabilities, we propose a synergistic hijacking framework featuring In-Context Reskinning (ICR) and Cognitive Planning Injection (CPI). ICR utilizes few-shot learning to wrap adversarial intent in benign virtual shells to desensitize safety filters, while CPI hijacks the reasoning path by enforcing a plan-then-execute paradigm. By compelling the system to commit to a neutral logical plan, we exploit its internal drive for consistency to induce the synchronized generation of harmful multimodal content. Extensive evaluations on state-of-the-art architectures demonstrate that UnifiedAttack consistently bypasses modern alignment. Our findings reveal that the structural helpfulness and logical coherence of unified models can be systematically weaponized, highlighting the urgent need for logic-aware defenses in synergistic generation tasks. Code is available at https://github.com/bingjunluo/UnifiedAttack .

How students interact with artificial intelligence (AI) systems in educational settings may determine whether that interaction supports or displaces critical thinking. This paper introduces two contributions. The first is the Three Paths of Student-AI Interaction, a typological framework identifying three qualitatively distinct modes of student-AI engagement: Passive Review, Direct Question, and Strategic Dialogue. The second is the Next Level Teaching Blueprint (NLTB), a three-stage instructional design system intended to make Strategic Dialogue more likely. Qualitative content analysis of 50 randomly sampled student-AI interaction messages from an undergraduate research methods course was used to examine the typology. Two human coders achieved 68% path-level agreement ($\kappa$ = .48), with 80% agreement on Strategic Dialogue identification specifically. GPT-5, used as a third coder, produced a similar overall distribution and introduced a coding category absent from the human scheme. Path 1 (Passive Review) accounted for 46% of exchanges in the primary researcher's classifications, Path 2 (Direct Question) for 18%, and Path 3 (Strategic Dialogue) for 36%. A second, descriptively examined dataset contained predominantly Strategic Dialogue content, offering a preliminary indication that instructional framing may influence which path students take. Together, the Three Paths framework and the NLTB contribute a language for describing student-AI interaction and a design approach for supporting higher-order engagement.

Multimodal on-policy distillation (OPD) aims to improve visual grounding while preserving the strong reasoning capabilities of language models. Recent multi-teacher approaches combine LLM and VLM teachers to provide complementary supervision. However, directly using a VLM's full predictive distribution entangles its visual grounding signal with its own language prior, preventing the grounding information from being transferred independently. Conversely, increasing the strength of visual supervision can improve perception but may overemphasize visual evidence and degrade language reasoning. To address this trade-off, we introduce LEGO-OPD, which selectively composes factors from a Language Expert and a Grounding expert into One teacher distribution for multimodal OPD. Under a generalized Bayesian formulation, the language expert provides a prior over candidate tokens, while the grounding expert contributes a visual likelihood that updates this prior, rather than transferring its complete predictive distribution. This factorized composition allows language reasoning and visual grounding to be controlled independently. We further introduce adaptive calibration to determine how strongly the visual likelihood should update the language prior at each decoding prefix. Specifically, LEGO-OPD uses the grounding expert's image-induced prediction shift as a prefix-dependent reference, preventing both insufficient and excessive visual supervision. Experiments with Qwen3 models show that LEGO-OPD consistently outperforms the evaluated single- and multi-teacher OPD baselines on both multimodal and text-only reasoning tasks. Moreover, it improves the initial student's visual perception while preserving text-only reasoning.

Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current approaches face a fundamental tension: optimizing purely for verifiable task rewards (e.g., via GRPO) leads to reward hacking, where students arrive at correct final answers through flawed intermediate logic, while regularizing with soft divergence penalties against a teacher (e.g., KL-based distillation) dilutes task performance and, critically, allows the student to compensate for severe logical violations at one step with high teacher agreement at others. We argue that this averaging is fundamentally misaligned with the nature of reasoning: a chain-of-thought is only as valid as its weakest link. Motivated by this observation, we formulate reasoning distillation as a constrained reinforcement learning problem in which the task reward is maximized subject to a worst-case constraint on the teacher log-likelihood along every prefix of the trajectory. To avoid the prohibitive cost of dual Lagrangian solvers and the test-time teacher dependence of state-augmented methods such as Saute, we derive an unaugmented constrained MDP whose reward transformation preserves the hard-constraint semantics, admits a low-variance policy gradient decomposition into single-step and long-term terms, and provably satisfies the worst-case constraint almost surely in the penalty limit. Through extensive experiments on mathematical reasoning and code generation tasks, we demonstrate that our method significantly expands the accuracy-fidelity Pareto front. By matching the high Final Answer Correctness of pure RL and drastically reducing teacher constraint violations, we ultimately achieve the highest rigorous Reasoning Success Rate across all evaluated settings.