Papers

We introduce Semantic Intent Fragmentation (SIF), an attack class against LLM orchestration systems where a single, legitimately phrased request causes an orchestrator to decompose a task into subtasks that are individually benign but jointly violate security policy. Current safety mechanisms operate at the subtask level, so each step clears existing classifiers – the violation only emerges at the composed plan. SIF exploits OWASP LLM06:2025 through four mechanisms: bulk scope escalation, silent data exfiltration, embedded trigger deployment, and quasi-identifier aggregation, requiring no injected content, no system modification, and no attacker interaction after the initial request. We construct a three-stage red-teaming pipeline grounded in OWASP, MITRE ATLAS, and NIST frameworks to generate realistic enterprise scenarios. Across 14 scenarios spanning financial reporting, information security, and HR analytics, a GPT-20B orchestrator produces policy-violating plans in 71% of cases (10/14) while every subtask appears benign. Three independent signals validate this: deterministic taint analysis, chain-of-thought evaluation, and a cross-model compliance judge with 0% false positives. Stronger orchestrators increase SIF success rates. Plan-level information-flow tracking combined with compliance evaluation detects all attacks before execution, showing the compositional safety gap is closable.

Precise interference detection and identification are crucial for enhancing the survivability of communication systems in non-cooperative wireless environments. While deep learning (DL) has advanced this field, existing single-task learning (STL) approaches neglect inherent task correlations. Furthermore, emerging multi-task learning (MTL) methods often lack a theoretical foundation for quantifying and modeling task relationships. To bridge this gap, we establish a theoretically grounded MTL framework for joint interference detection, modulation identification, and interference identification. First, we derive an upper bound for the weighted expected loss in MTL frameworks. This bound explicitly connects MTL performance to task similarity, quantified by the Wasserstein distance and learnable task relation coefficients. Guided by this theory, we present the adversarial multi-task interference detection and identification network (AMTIDIN), which integrates adversarial training to minimize distributional discrepancies across tasks and uses adaptive coefficients to model task correlations dynamically. Crucially, we conducted a quantitative analysis of task similarity to reveal intrinsic task relationships, specifically that modulation identification and interference identification share a substantial feature overlap distinct from interference detection. Experiments demonstrate that AMTIDIN outperforms its independently trained single-task counterparts and MTL baselines under the evaluated conditions of limited training data, short signal lengths, and low signal-to-noise ratios (SNRs)

Server-based screening tools impose subscription costs, while open-source alternatives require coding skills, and full-text screening has remained outside the scope of no-code open-source tools. We developed TiAb Review Plugin, an open-source Chrome browser extension that provides no-code, serverless artificial intelligence (AI)-assisted study selection covering both title and abstract (T&A) screening and full-text screening. It uses Google Sheets as a shared database and Google Drive as a PDF store, and users supply their own large language model (LLM) API key. For T&A screening, it offers manual review, LLM batch screening, and machine learning (ML) active learning. For full-text screening, it retrieves open-access PDFs from PubMed Central, Europe PMC, Unpaywall, OpenAlex, and publisher pages, supports blinded dual review with structured exclusion reasons and adjudication, optionally obtains an LLM judgment with page-anchored evidence, and computes PRISMA 2020 flow counts. We re-implemented the default ASReview algorithm (TF-IDF with Naive Bayes) in TypeScript and compared it with the Python original using 10-fold cross-validation on six datasets. For LLM T&A screening, we compared 16 parameter configurations on a benchmark dataset, validated the best (Gemini 3.0 Flash, low thinking budget, TopP 0.95) on five public datasets (1,038 to 5,628 records; 0.5% to 2.0% prevalence), and benchmarked nine further models from four developers. The TypeScript classifier produced top-100 rankings identical to ASReview on all six datasets. LLM T&A screening achieved recall of 94% to 100% with precision of 2% to 15%, and work saved over sampling at 95% recall (WSS@95) of 46.3% to 89.3%. No additional model exceeded the 96.1% recall of the reference configuration; the most recent models traded recall for precision. The classification accuracy of the full-text stage has not yet been evaluated.

Linear recurrent models offer linear-time sequence processing but often suffer from suboptimal long-range memory. We trace this to the decay spectrum: for $N$ channels, random initialization collapses the minimum spectral gap to $O(N^{-2})$, yielding sub-exponential error $\exp(-\Omega(N/\log N))$; linear spacing avoids collapse but degrades to $\exp(-O(N/\sqrt{T}))$, practically algebraic over long contexts. We introduce Position-Adaptive Spectral Tapering (PoST), an architecture-agnostic framework combining two mechanisms: (1) Spectral Reparameterization, which structurally enforces geometrically spaced log-decay rates, proven minimax optimal at rate $O(\exp(-cN/\log T))$; and (2) Position-Adaptive Scaling, the provably unique mechanism that eliminates the scale mismatch of static spectra (where only $N\log t/\log T$ of $N$ channels are effective at position $t$) by stretching the spectrum to the actual dependency range, sharpening the rate to $O(\exp(-cN/\log t))$. This scaling natively induces fractional invariance: the impulse response becomes scale-free, with channels interpolating between relative and absolute temporal coordinates. PoST integrates into any diagonal linear recurrence without overhead. We instantiate it across Mamba-2, RWKV-7, Gated DeltaNet, Gated Linear Attention, and RetNet. Pre-training at 180M-440M scales shows consistent zero-shot language modeling improvements, significant long-context retrieval gains for Mamba-2 (MQAR and NIAH), and competitive or improved performance across other architectures. Code: https://github.com/SiLifen/PoST.

Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less useful systems. This work introduces Guardian-as-an-Advisor (GaaA), a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference, keeping the base model operating under its original spec. To support training and evaluation, GuardSet is constructed, a 208k+ multi-domain dataset unifying harmful and harmless cases with targeted robustness and honesty slices. GuardAdvisor is trained via SFT followed by RL to enforce label-explanation consistency. GuardAdvisor attains competitive detection accuracy while enabling the advisory workflow; when used to augment inputs, responses improve over unaugmented prompts. A latency study shows advisor inference uses below 5% of base-model compute and adds only 2-10% end-to-end overhead under realistic harmful-input rates. Overall, GaaA steers models to comply with the model spec, maintaining safety while reducing over-refusal.

Multi-task learning for advanced driver assistance systems requires modeling the complex interplay between driver internal states and external traffic environments. However, existing methods treat recognition tasks as flat and independent objectives, failing to exploit the cognitive causal structure underlying driving behavior. In this paper, we propose CauPsi, a cognitive science-grounded causal multi-task learning framework that explicitly models the hierarchical dependencies among Traffic Context Recognition (TCR), Vehicle Context Recognition (VCR), Driver Emotion Recognition (DER), and Driver Behavior Recognition (DBR). The proposed framework introduces two key mechanisms. First, a Causal Task Chain propagates upstream task predictions to downstream tasks via learnable prototype embeddings, realizing the cognitive cascade from environmental perception to behavioral regulation in a differentiable manner. Second, Cross-Task Psychological Conditioning (CTPC) estimates a psychological state signal from driver facial expressions and body posture and injects it as a conditioning input to all tasks including environmental recognition, thereby modeling the modulatory effect of driver internal states on cognitive and decision-making processes. Evaluated on the AIDE dataset, CauPsi achieves a mean accuracy of 82.71% with only 5.05M parameters, surpassing prior work by +1.0% overall, with notable improvements on DER (+3.65%) and DBR (+7.53%). Ablation studies validate the independent contribution of each component, and analysis of the psychological state signal confirms that it acquires systematic task-label-dependent patterns in a self-supervised manner without explicit psychological annotations.

Broadly applicable quantum advantage, particularly in classical data processing and machine learning, has been a fundamental open problem. In this work, we prove that a small quantum computer of polylogarithmic size can perform large-scale classification and dimension reduction on massive classical data by processing samples on the fly, whereas any classical machine achieving the same prediction performance requires exponentially larger size. Furthermore, classical machines that are exponentially larger yet below the required size need superpolynomially more samples and time. We provide evidence for these quantum advantages in real-world applications, including single-cell RNA sequencing and movie review sentiment analysis, demonstrating four to six orders of magnitude reduction in size with fewer than 60 logical qubits. These quantum advantages are enabled by quantum oracle sketching, an algorithm for accessing the classical world in quantum superposition using only random classical data samples. Combined with classical shadows, our algorithm circumvents the data loading and readout bottleneck to construct succinct classical models from massive classical data, a task provably impossible for any classical machine that is not exponentially larger than the quantum machine. These quantum advantages persist even when classical machines are granted unlimited time or if BPP = BQP, and rely only on the correctness of quantum mechanics. Together, our results establish machine learning on classical data as a broad and natural domain of quantum advantage and a fundamental test of quantum mechanics at the complexity frontier.

This research considers a scalable inference for spatial data modeled through Gaussian intrinsic conditional autoregressive (ICAR) structures. The classical estimation method, restricted maximum likelihood (REML), requires repeated inversion and factorization of large, sparse precision matrices, which makes this computation costly. To sort this problem out, we propose a variational restricted maximum likelihood (VREML) framework that approximates the intractable marginal likelihood using a Gaussian variational distribution. By constructing an evidence lower bound (ELBO) on the restricted likelihood, we derive a computationally efficient coordinate-ascent algorithm for jointly estimating the spatial random effects and variance components. In this article, we theoretically establish the monotone convergence of ELBO and mathematically exhibit that the variational family is exact under Gaussian ICAR settings, which is an indication of nullifying approximation error at the posterior level. We empirically establish the supremacy of our VREML over MLE and INLA.

Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align through an intermediate modality at lower complexity than through a direct map. We introduce a reference formalism that evaluates all modalities on a fixed neighborhood site and defines two directed invariants. Projection hardness \(H_{a\to b}(\varepsilon)\) is the minimum complexity within a nested Lipschitz-controlled family required to reach error \(\varepsilon\). For a declared local projection family, sheaf-Laplacian obstruction \(C_{a\to b}(\varepsilon)\) is the minimum variation of locally fitted projection parameters required to reach the same error. Under identity restrictions, obstruction is the graph Dirichlet energy of a vector-valued parameter field; the sheaf formulation identifies zero energy with successful gluing and extends to edge-dependent transports and heterogeneous parameter spaces. We relate obstruction to the site spectral gap and excess global-map error, and construct ReLU examples showing non-transitive compatibility and a quadratic separation between staged and direct width. Controlled synthetic calibrations recover the predicted hardness separation, cut-induced obstruction scaling, and sensitivity to the fixed site graph.

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the accepted token distribution to exactly match the target model. This constraint leads to the rejection of many plausible tokens, lowering the acceptance rate and limiting overall time speedup. To overcome this limitation, we propose Dynamic Verification Relaxed Speculative Decoding (DIVERSED), a relaxed verification framework that improves time efficiency while preserving generation quality. DIVERSED learns an ensemble-based verifier that blends the draft and target model distributions with a task-dependent and context-dependent weight. We provide theoretical justification for our approach and demonstrate empirically that DIVERSED achieves substantially higher inference efficiency compared to standard speculative decoding methods. Code is available at: https://github.com/comeusr/diversed.

Industrial forecasting often involves multi-source asynchronous signals and multi-output targets, while deployment requires explicit trade-offs between prediction error and model complexity. Current practices typically fix alignment strategies or network designs, making it difficult to systematically co-design preprocessing, architecture, and hyperparameters in budget-limited training-based evaluations. To address this issue, we propose an auto-configuration framework that outputs a deployable Pareto set of forecasting models balancing error and complexity. At the model level, a Multi-Scale Bi-Branch Convolutional Neural Network (MS–BCNN) is developed, where short- and long-kernel branches capture local fluctuations and long-term trends, respectively, for multi-output regression. At the search level, we unify alignment operators, architectural choices, and training hyperparameters into a hierarchical-conditional mixed configuration space, and apply Player-based Hybrid Multi-Objective Evolutionary Algorithm (PHMOEA) to approximate the error–complexity Pareto frontier within a limited computational budget. Experiments on hierarchical synthetic benchmarks and a real-world sintering dataset demonstrate that our framework outperforms competitive baselines under the same budget and offers flexible deployment choices.

Large Language Model (LLM) inference is rapidly becoming a core datacenter service, yet current serving stacks keep the host CPU on the critical path for orchestration and token-level control. This makes LLM performance sensitive to CPU interference, undermining application colocation and forcing operators to reserve CPU headroom, leaving substantial capacity unutilized. We introduce Blink, an end-to-end serving architecture that removes the host CPU from the steady-state inference path by redistributing responsibilities across a SmartNIC and a GPU. Blink offloads request handling to the SmartNIC, which delivers inputs directly into GPU memory via RDMA, and replaces host-driven scheduling with a persistent GPU kernel that performs batching, scheduling, and KV-cache management without CPU involvement. Evaluated against TensorRT-LLM, vLLM, and SGLang, Blink outperforms all baselines even in isolation, reducing pre-saturation P99 TTFT by up to 8.47$\times$ and P99 TPOT by up to 3.40$\times$, improving decode throughput by up to 2.1$\times$, and reducing energy per token by up to 48.6$\%$. Under CPU interference, Blink maintains stable performance, while existing systems degrade by up to two orders of magnitude.

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction has become a central theoretical question in machine learning. This study investigates the role of optimization dynamics and implicit regularization in enabling generalization in overparameterized neural networks through controlled experiments. We examine stochastic gradient descent (SGD) across batch sizes, the geometry of flat versus sharp minima via Hessian eigenvalue estimation and weight perturbation analysis, the Neural Tangent Kernel (NTK) regime through wide-network experiments, double descent across model scales, and the Lottery Ticket Hypothesis through iterative magnitude pruning. All experiments use PyTorch on CIFAR-10 and MNIST with multiple random seeds. Our findings demonstrate that generalization is strongly influenced by the interaction between network architecture, optimization algorithms, and loss landscape geometry. Smaller batch sizes consistently produced lower test error and flatter minima, with an 11.8x difference in top Hessian eigenvalue between small-batch and large-batch solutions corresponding to 1.61 percentage points higher test accuracy. Sparse subnetworks retaining only 10% of parameters achieved within 1.15 percentage points of full model performance when retrained from their original initialization. These results highlight the need for revised learning-theoretic frameworks capable of explaining generalization in high-dimensional model regimes.

Supervised machine learning assumes that labeled data provide accurate measurements of the concepts models are meant to learn. Yet in practice, human labeling introduces systematic variation arising from ambiguous items, divergent interpretations, and simple mistakes. Machine learning research commonly treats all disagreement as noise, which obscures these distinctions and limits our understanding of what models actually learn. This paper reframes annotation as a measurement process and introduces a statistical framework for decomposing labeling outcomes into interpretable sources of variation: instance difficulty, annotator bias, situational noise, and relational alignment. The framework extends classical measurement-error models to accommodate both shared and individualized notions of truth, reflecting traditional and human label variation interpretations of error, and provides a diagnostic for assessing which regime better characterizes a given task. Applying the proposed model to a multi-annotator natural language inference dataset, we find empirical evidence for all four theorized components and demonstrate the effectiveness of our approach. We conclude with implications for data-centric machine learning and outline how this approach can guide the development of a more systematic science of labeling.

Real-world categorization is severely hampered by class imbalance because traditional ensembles favor majority classes, which lowers minority performance and overall F1-score. We provide a unique ensemble technique for imbalanced problems called CAMO (Class-Aware Minority-Optimized).Through a hierarchical procedure that incorporates vote distributions, confidence calibration, and inter model uncertainty, CAMO dynamically boosts underrepresented classes while preserving and amplifying minority forecasts. We verify CAMO on two highly unbalanced, domain-specific benchmarks: the DIAR-AI/Emotion dataset and the ternary BEA 2025 dataset. We benchmark against seven proven ensemble algorithms using eight different language models (three LLMs and five SLMs) under zero-shot and fine-tuned settings .With refined models, CAMO consistently earns the greatest strict macro F1-score, setting a new benchmark. Its benefit works in concert with model adaptation, showing that the best ensemble choice depends on model properties .This proves that CAMO is a reliable, domain-neutral framework for unbalanced categorization.

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to learning in humans. We argue LLMs are best seen as an instance of lossy compression, where over training they learn by retaining only information in their training data relevant to their objective(s). We show pre-training results in models that are optimally compressed for next-sequence prediction, approaching the Information Bottleneck bound on compression. Across an array of open weights models, each compresses differently, likely due to differences in the data and training recipes used. However even across different families of LLMs the optimality of a model's compression, and the information present in it, can predict downstream performance on across a wide array of benchmarks, letting us directly link representational structure to actionable insights about model performance. In the general case the work presented here offers a unified Information-Theoretic framing for how these models learn that is deployable at scale.

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We propose a reasoning-based refinement framework that leverages large language models (LLMs) not as embedding generators, but as semantic judges that validate and restructure the outputs of arbitrary unsupervised clustering algorithms. Our framework introduces three reasoning stages: (i) coherence verification, where LLMs assess whether cluster summaries are supported by their member texts; (ii) redundancy adjudication, where candidate clusters are merged or rejected based on semantic overlap; and (iii) label grounding, where clusters are assigned interpretable labels through a two-stage process that generates and consolidates semantically similar labels in a fully unsupervised manner. This design decouples representation learning from structural validation and mitigates the common failure modes of embedding-only approaches. We evaluate the framework in real-world social media corpora from two platforms with distinct interaction models, demonstrating consistent improvements in cluster coherence and human-aligned labeling quality over classical topic models and recent representation-based baselines. Human evaluation shows strong agreement with LLM-generated labels, despite the absence of gold-standard annotations. We further conduct robustness analysis under matched temporal and volume conditions to assess cross-platform stability. Beyond empirical gains, our results suggest that LLM-based reasoning can serve as a general mechanism for validating and refining unsupervised semantic structure, enabling more reliable and interpretable analysis of large text collections without supervision.

Activity cliff prediction - identifying positions where small structural changes cause large potency shifts - has been a persistent challenge in computational medicinal chemistry. This work focuses on a parsimonious definition: which small modifications, at which positions, confer the highest probability of an outcome change. Position-level sensitivity is calculated using 25 million matched molecular pairs from 50 ChEMBL targets across six protein families, revealing that two questions have fundamentally different answers. "Which positions vary most?" is answered by scaffold size alone (NDCG@3 = 0.966), requiring no machine learning. "Which are true activity cliffs?" - where small modifications cause disproportionately large effects, as captured by SALI normalization - requires an 11-feature model with 3D pharmacophore context (NDCG@3 = 0.910 vs. 0.839 random), generalizing across all six protein families, novel scaffolds (0.913), and temporal splits (0.878). The model identifies the cliff-prone position first 53% of the time (vs. 27% random - 2x lift), reducing positions a chemist must explore from 3.1 to 2.1 - a 31% reduction in first-round experiments. Predicting which modification to make is not tractable from structure alone (Spearman 0.268, collapsing to -0.31 on novel scaffolds). The system is released as open-source code and an interactive webapp.

Small longitudinal cohorts, common in maternal health, rare diseases, and early-phase trials, limit computational modeling because enrollment is slow and the data are too sparse to train reliable models. We present multiplicity-weighted Stochastic Attention (SA), a generative framework based on modern Hopfield networks. Stochastic attention stores real patient profiles as memory patterns in a continuous energy landscape. The resulting distribution is a finite mixture with one component centered on each stored profile. We generated the reported cohort with Langevin dynamics; direct sampling from the same distribution reproduced its fidelity and membership-inference results. Multiplicity weights amplify selected subgroups at inference time without retraining. We applied the method to longitudinal coagulation data from 23 patients, with 72 features measured before pregnancy and during the first and third trimesters. The cohort included three patients with polycystic ovary syndrome and five who developed preeclampsia. Across statistical, structural, and mechanistic tests, including a separately specified coagulation model that was blind to the generator but calibrated on the same cohort, the synthetic profiles closely matched the real profiles under the measures applied at this sample size. A model calibrated on synthetic profiles predicted held-out real-patient TGA measurements as well as one calibrated on real profiles. These results provide proof of concept for using SA in the tested modeling tasks, including mechanistic calibration and hypothesis generation, with very small longitudinal cohorts.

Time Slotted Channel Hopping (TSCH) is a widely adopted Media Access Control (MAC) protocol within the IEEE 802.15.4e standard, designed to provide reliable and energy-efficient communication in Industrial Internet of Things (IIoT) networks. However, state-of-the-art TSCH schedulers rely on static slot allocations, resulting in idle listening and unnecessary power consumption under dynamic traffic conditions. This paper introduces RL-ASL, a reinforcement learning-driven adaptive listening framework that dynamically decides whether to activate or skip a scheduled listening slot based on real-time network conditions. By integrating learning-based slot skipping with standard TSCH scheduling, RL-ASL reduces idle listening while preserving synchronization and delivery reliability. Experimental results on the FIT IoT-LAB testbed and Cooja network simulator show that RL-ASL achieves up to 46% lower power consumption than baseline scheduling protocols, while maintaining near-perfect reliability and reducing average latency by up to 96% compared to PRIL-M. Its link-based variant, RL-ASL-LB, further improves delay performance under high contention with similar energy efficiency. Importantly, RL-ASL performs inference on constrained motes with negligible overhead, as model training is fully performed offline. Overall, RL-ASL provides a practical, scalable, and energy-aware scheduling mechanism for next-generation low-power IIoT networks.

We present an RL-driven compiler that jointly optimizes ASIC architecture, memory hierarchy, and workload partitioning for AI inference across 3nm to 28nm. The design space is formulated as a single Markov Decision Process with mixed discrete-continuous actions and a unified Power-Performance-Area (PPA) objective. Soft Actor-Critic (SAC) with Mixture-of-Experts gating explores the joint space of mesh topology, per-core microarchitecture, and operator placement. We validate on two workloads, Llama 3.1 8B FP16 (high-performance mode, 29809 tokens per second at 3nm) and SmolVLM (low-power mode, less than 13 mW at all nodes, 10 MHz). Across 7 process nodes, the RL automatically adapts mesh sizes and per-tile configurations, including heterogeneous FETCH, VLEN, and memory allocation without node-specific manual retuning.

Harnessing the predictive capability of Markov process models requires propagating probability density functions (beliefs) through the model. For many existing models however, belief propagation is analytically infeasible, requiring approximation or sampling to generate predictions. This paper proposes a functional modeling framework leveraging sparse Sum-of-Squares (SoS) forms for valid (conditional) density estimation. We study the theoretical restrictions of modeling conditional densities using the SoS form, and propose a novel functional form for addressing such limitations. The proposed architecture enables generalized simultaneous learning of basis functions and coefficients, while preserving analytical belief propagation. In addition, we propose a training method that allows for exact adherence to the normalization and non-negativity constraints. Our results show that the proposed method achieves accuracy comparable to state-of-the-art approaches while requiring significantly less memory in low-dimensional spaces, and it further scales to 12D systems when existing methods fail beyond 2D.

These lecture notes provide a comprehensive framework for performing global statistical fits in high-energy physics using modern Machine Learning (ML) surrogates. We begin by reviewing the statistical foundations of model building, including the likelihood function, Wilks' theorem, and profile likelihoods. Recognizing that the computational cost of evaluating model predictions often renders traditional minimization prohibitive, we introduce Boosted Decision Trees to approximate the log-likelihood function. The notes detail a robust ML workflow including efficient generation of training data with active learning and Gaussian processes, hyperparameter optimization, model compilation for speed-up, and interpretability through SHAP values to decode the influence of model parameters and interactions between parameters. We further discuss posterior distribution sampling using Markov Chain Monte Carlo (MCMC). These techniques are finally applied to the $B^\pm \to K^\pm \nu \bar{\nu}$ anomaly at Belle II, demonstrating how a two-stage ML model can efficiently explore the parameter space of Axion-Like Particles (ALPs) while satisfying stringent experimental constraints on decay lengths and flavor-violating couplings.

Persona simulation based on large language models—often referred to as digital twin simulation—is increasingly used for market research, recommender systems, and social science research. However, these simulations often exhibit systematic bias and miscalibration relative to real human behavior. We propose SYN-DIGITS, a model-agnostic, post-hoc calibration framework that learns relationships among questions from digital twins and transfers them to predict human responses. We focus on a cold-start setting in which no human response to the target question is observed, so calibration must rely on digital twins and human data on reference questions. Our analysis shows that, though digital twins may not reproduce individual human responses accurately, they can capture nontrivial relationships among questions that can be effectively transferred to the human side. When individual-level data is unavailable and we only have access to marginal information on reference questions, our framework also supports distribution-level calibration for predicting the distribution of human responses on the target question. Across three datasets and thirteen persona constructions, experiments show that SYN-DIGITS achieves 11% to 417% relative improvements in individual-level correlation and 46%–57% relative reductions in distributional discrepancy compared to uncalibrated baselines.

We present Rhizome OS-1, a semi-autonomous operating system for small molecule drug discovery in which multi-modal AI agents operate as a full multidisciplinary discovery team. These agents function as computational chemists, medicinal chemists, and patent agents: they write and execute analysis code (fingerprint clustering, R-group decomposition, substructure search), visually triage molecular grids using vision capabilities, formulate explicit medicinal chemistry hypotheses across three strategy tiers, assess patent freedom-to-operate, and dynamically adapt generation strategies based on empirical screening feedback. Powered by r1 - a 246M-parameter graph diffusion model trained on 800 million molecular graphs - the system generates novel chemical matter directly on molecular graphs using fragment masking, scaffold decoration, linker design, and graph editing primitives. In two oncology campaigns (BCL6 BTB domain and EZH2 SET domain), the agent team executed 26 seeds and produced 5,231 novel molecules. Across both targets, 91.9% of generated Murcko scaffolds are absent from ChEMBL, with median Tanimoto similarity of 0.56-0.69 to the nearest known active. Boltz-2 binding affinity predictions, calibrated against ChEMBL data, achieved Spearman correlations of -0.53 to -0.64 and ROC AUC values of 0.88-0.93. These results demonstrate that semi-autonomous agent systems, equipped with graph-native generative tools and physics-informed scoring, enable a new paradigm for early-stage drug discovery: scaled, rapid, and adaptive inverse design with embedded medicinal chemistry reasoning.

Context: AI coding agents route every task to a single frontier large language model (LLM), paying premium inference cost even when many tasks are routine. Objectives: We propose Triage, a framework that uses code health metrics – indicators of software maintainability – as a routing signal to assign each task to the cheapest model tier whose output passes the same verification gate as the expensive model. Methods: Triage defines three capability tiers (light, standard, heavy – mirroring, e.g., Haiku, Sonnet, Opus) and routes tasks based on pre-computed code health sub-factors and task metadata. We design an evaluation comparing three routing policies on SWE-bench Lite (300 tasks across three model tiers): heuristic thresholds, a trained ML classifier, and a perfect-hindsight oracle. Results: We analytically derived two falsifiable conditions under which the tier-dependent asymmetry (medium LLMs benefit from clean code while frontier models do not) yields cost-effective routing: the light-tier pass rate on healthy code must exceed the inter-tier cost ratio, and code health must discriminate the required model tier with at least a small effect size ($\hat{p} \geq 0.56$). Conclusion: Triage transforms a diagnostic code quality metric into an actionable model-selection signal. We present a rigorous evaluation protocol to test the cost–quality trade-off and identify which code health sub-factors drive routing decisions.

Epidemiologic studies of infectious diseases often rely on models of contact networks to capture the complex interactions that govern disease spread, and ongoing projects aim to vastly increase the scale at which such data can be collected. However, contact networks may include sensitive information, such as sexual relationships or drug use behavior. Protecting individual privacy while maintaining the scientific usefulness of the data is crucial. We propose a privacy-preserving pipeline for disease spread simulation studies based on a sensitive network that integrates differential privacy (DP) with statistical network models such as stochastic block models (SBMs) and exponential random graph models (ERGMs). Our pipeline comprises three steps: (1) compute network summary statistics using node-level DP (which corresponds to protecting individuals' contributions); (2) fit a statistical model, like an ERGM, using these summaries, which allows generating synthetic networks reflecting the structure of the original network; and (3) simulate disease spread on the synthetic networks using an agent-based model. We evaluate the effectiveness of our approach using a simple Susceptible-Infected-Susceptible (SIS) disease model under multiple configurations. We compare both numerical results, such as simulated disease incidence and prevalence, as well as qualitative conclusions such as intervention effect size, on networks generated with and without differential privacy constraints. Our experiments are based on egocentric sexual network data from the ARTNet study (a survey about HIV-related behaviors). Our results show that the noise added for privacy is small relative to other sources of error (sampling and model misspecification). This suggests that, in principle, curators of such sensitive data can provide valuable epidemiologic insights while protecting privacy.

Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph Transformers with global attention have been proposed; however, global attention does not take into account the graph topology and thus lacks graph-structure-based inductive biases, which are typically very important for graph machine learning tasks. In this work, we propose an alternative approach: cluster attention (CLATT). We divide graph nodes into clusters with off-the-shelf graph community detection algorithms and let each node attend to all other nodes in each cluster. CLATT provides large receptive fields while still having strong graph-structure-based inductive biases. We show that augmenting Message Passing Neural Networks or Graph Transformers with CLATT significantly improves their performance on a wide range of graph datasets including datasets from the recently introduced GraphLand benchmark representing real-world applications of graph machine learning.

Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models. However, GRMs face two major challenges: reliance on costly human-annotated data restricts scalability, and self-training approaches often suffer from instability and vulnerability to reward hacking. To address these issues, we propose ConsistRM, a self-training framework that enables effective and stable GRM training without human annotations. ConsistRM incorporates the Consistency-Aware Answer Reward, which produces reliable pseudo-labels with temporal consistency, thereby providing more stable model optimization. Moreover, the Consistency-Aware Critique Reward is introduced to assess semantic consistency across multiple critiques and allocates fine-grained and differentiated rewards. Experiments on five benchmark datasets across four base models demonstrate that ConsistRM outperforms vanilla Reinforcement Fine-Tuning (RFT) by an average of 1.5%. Further analysis shows that ConsistRM enhances output consistency and mitigates position bias caused by input order, highlighting the effectiveness of consistency-aware rewards in improving GRMs. Our implementation is available at https://github.com/yuliangCarmelo/ConsistRM.

Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism configuration, and workload routing under latency, accuracy, memory, and budget constraints. While mixed-integer linear programming (MILP) can model this problem, its computational cost limits frequent re-optimization under demand variability. Existing heuristics often optimize individual components separately and may become infeasible when system-wide constraints are enforced. This paper presents a scalable framework for SLO-constrained LLM inference. We formulate the problem as an MILP with a two-phase delay model capturing both prefill and autoregressive decoding under tensor and pipeline parallelism. To solve it efficiently, we develop two constraint-aware heuristics: a Greedy Heuristic (GH) and an Adaptive Greedy Heuristic (AGH). AGH extends GH through multi-start construction, local search, and GPU consolidation. Both methods maintain feasibility through parallelism-aware filtering, cost-based ranking, and adaptive parallelism scaling. Experiments based on the Azure LLM Inference Trace show that GH generates feasible solutions within one second, while AGH achieves near-optimal performance within three seconds and scales to large instances where exact solvers fail to converge. Under out-of-sample stress with up to 1.5x delay and accuracy inflation, AGH degrades gracefully through provisioned headroom, yielding substantially lower cost and SLO violations than cost-minimal MILP solutions. Across synthetic and real Azure workloads, AGH maintains SLO compliance at significantly lower cost than exact MILP solutions. These results demonstrate that high-quality allocations provide substantial robustness to demand variability while enabling rapid adaptation to workload changes.