Papers

Clinical diagnosis is a step-by-step, cost-aware process: a physician orders examinations one at a time, observes the results, and updates the diagnosis before reaching a final conclusion. Most medical language models instead treat diagnosis as a one-pass classification task and ignore the trade-off between a test's value and its cost. We model diagnosis as a cost-aware sequential decision process and train the policy with reinforcement learning. The main difficulty is credit assignment: the only reliable signal comes once at the end of a long trajectory, so it scores a wasteful workup the same as an efficient one. We propose CDPR (Counterfactual Diagnostic Process Reward), which needs no expert labels and no learned critic. CDPR first finds the states where the policy hesitates, using the uncertainty of its action distribution, and then scores the chosen action by its advantage over the alternatives the policy itself would consider, estimated with short rollouts under a utility that balances correctness against test count, cost, and infeasible requests. A rollout cache reuses within-batch trajectories to keep the cost low. We integrate CDPR into GRPO and test it on one in-domain (MIMIC-IV) and two out-of-domain (ClinicalBench and a private hospital dataset) benchmarks. CDPR improves diagnostic accuracy while clearly reducing the number and cost of examinations.

Memes have turned out to be a powerful tool through which individuals share their ideas concerning contemporary social and political problems. Their anonymity, as well as their ability to go viral, make them a powerful medium for spreading hate. It remains very difficult to identify such complex and context-dependent hate speech. Although they display excellent performance on multimodal tasks, vision-language models (VLMs) tend to ignore context, irony, and other subtle cues that play a key role in identifying hateful memes. In this work, we present a qualitative analysis of four state-of-the-art VLMs: LLaVA-7B, Qwen-VL, GPT-4o mini, and Claude 3 Haiku. We evaluate these models under zero-shot and few-shot prompting to examine how contextual framing influences their outputs. Our analysis goes beyond simple classification accuracy and focuses on a qualitative evaluation of the models' generated justifications, providing a more in-depth understanding of their thought processes and constraints when dealing with hateful memes.

Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation without erasing the foundational knowledge of harmful concepts acquired during pretraining. This study demonstrates that this architectural disconnect leaves models vulnerable to Semantic Camouflage – adversarial attacks that wrap harmful intent in benign narrative contexts (e.g., creative writing), effectively bypassing standard input and output guardrails. By analyzing the latent activation trajectories of three distinct Small Language Model (SLM) families (Phi-3, Qwen2.5, and Gemma-2b) under adversarial stress, this research identifies a universal “Intent Horizon” – a critical depth (typically 15–20% of total layers) where the model's distinct, pre-trained representation of harmful intent collapses as it contextualizes the query into a “safe” narrative. Results indicate that while late-layer representations of camouflaged attacks are mathematically indistinguishable from safe queries (Detection Rate $< 20\%$), early-layer representations retain a distinct, detectable “harm signature.” Leveraging this insight, this paper proposes Latent Intent Verification (LIV), a lightweight probing defense. Experiments on the PKU-SafeRLHF dataset demonstrate that LIV outperforms standard guardrails by a margin of 20–50% across all tested architectures, effectively neutralizing zero-day semantic attacks without requiring model retraining.

The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models–another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains and neural networks suggests that it may be a fundamental property of intelligent systems.

Large language models are already advisors to millions of people of faith who bring them real decisions. The pressing question for a person of faith is not what a model knows or professes but what its counsel does to the person who receives it. We introduce JaleesBench, which measures whether an AI agent is a righteous companion, judged by the residue an exchange leaves on the user, in the manner of the perfume-seller and the blacksmith. It comprises 140 two-turn scenarios drawn from a classical compilation organized by virtue (Riyad al-Salihin), under six adversarial pressures and three framings, scored by two frontier judges against each scenario's own supporting texts. Across eight systems: (1) generic frontier models are only middling companions out of the box but a one-page guide makes them genuinely good ones, on par with the domain-tuned assistant: the frontier APIs climb from +0.28/+0.23 to a Guided +0.84-0.87, so most of the expert's edge is companionship instruction that fits in a prompt; (2) every system caves under relational pressure, insistence and personal appeal; (3) the domain-tuned assistant's advantage is overwhelmingly its retrieval-and-prompting layer, not its base model (+0.74 over the identical underlying model); and (4) it can be used to improve existing systems: guided by its diagnosis, a single steadfastness instruction lifts a deployed Islamic assistant from +0.48 to +0.84 (Faith unstated, after pressure), matching the best guided frontier systems while preserving first-response quality. The construct is faith-general; we instantiate it for Islam as the first of a planned cross-tradition family. Code, scenario bank, and rubric are open source (github.com/iaser-ai/jaleesbench), with an interactive results browser at s.iaser.ai/jb.

Equitable access to scientific knowledge often depends on informal gatekeeping decisions, particularly when resources such as paywalled articles, nonpublic datasets, or a researcher's CV must be shared selectively. We introduce a controlled simulation framework in which LLM-based professors must grant access to only one requester. Across prompts, requesters vary systematically by global region (Global North vs. Global South) and academic seniority, while all other factors remain constant. Most models prioritize PhD candidates, although preferences vary by model and scenario (e.g., Claude favors tenured professors when the request is for the professor's CV), and the smaller models' status choices are sensitive to the order in which options are presented. When the requesters' regions differ, the models split into two groups. The three large proprietary LLMs systematically favor requesters from the Global South, a pro-equity bias consistent with their safety alignment, whereas the two small open-weight models reverse this preference and favor the Global North, possibly reflecting weaker alignment or the geographic skew of their pre-training data. Linking choices to national income reveals that the large models' preference largely tracks economic need rather than the regional label: they strongly favor requesters from low-income countries, but their preference for the Global South is weak or absent when both countries have equal income, whereas the small models favor the Global North regardless of income. Because model scale, alignment, and training data are confounded in our sample, these explanations remain hypotheses for future work. Our findings show that LLMs embed differing normative assumptions about need and reputation that can shape gatekeeping decisions, which highlights the need to audit AI systems for fairness and value alignment before such tasks are delegated to them.

Speech-to-speech dialogue models increasingly depend on prosody and interactional nuance to convey social intent, yet benchmarks for these cues remain limited. We introduce StanceBench, a benchmark for measuring interpersonal stance in conversational speech and evaluating audio-capable LLMs as automated judges. Using the Seamless Interaction corpus, StanceBench (1) specifies 9 stance dimensions via role-prompt poles, (2) standardizes single-speaker and interaction-based evaluations, and (3) reports LLM-as-a-judge robustness, bias, and stance inference. Across evaluated stances, empathy and politeness are the easiest. Warmth and assertiveness are moderately separable with positivity skew/asymmetry. Honesty is the hardest and shows high prompt order bias, consistent with needing cross-turn evidence. Attentiveness is separable but aligns weakly with humans. Interaction stances are more context-sensitive, with threshold gaps and high variance, especially conflict regulation.

Large language models (LLMs) can reproduce disinformation-aligned narrative frames as plausible explanations, raising the question of whether existing machine-unlearning algorithms can suppress this behavior. We introduce Level-based Evaluation of Narrative Suppression (LENS), a contextualization based evaluation protocol for testing target narrative reproduction across direct, attributed, contrastive, and abstract resistance levels. We evaluate two source-grounded narratives: one framing Russia's war against Ukraine as forced by NATO expansion, and one framing the United States as exploiting or abandoning Taiwan. The experiments cover four near-12B multilingual instruction models: Lapa LLM, Gemma-12B, Qwen-14B, and TAIDE-Gemma. We introduce the Suppression-Collapse Efficiency (SCE) score as a checkpoint selection summary that rewards target-narrative suppression while penalizing degraded outputs. Our results shows that selected checkpoints can reduce narrative reproduction and suppression may transfer beyond direct forget prompts. We also report entity recovery as a separate side effect: abstract A/B/C prompts can cause models to recover the real-world actors associated with the target frame after unlearning. These findings demonstrate that LENS is a successful diagnostic protocol for both reporting and guiding the further study of the deeper structure of narrative unlearning.

A crucial step in machine learning pipelines is to present each entity with features or attributes that are representative of the characteristics of the processed entities. Feature engineering is an important step in finding a relation among attributes that otherwise may not be processed by the ML algorithms. Meanwhile, Large Language Models have shown promising abilities in coding, mathematical reasoning, and processing world knowledge. In this work, we utilize an LLM for the problem of feature generation from tabular data based on the previously given features. We have created a pipeline that takes a set of attributes and a prompt to generate new features. Then, our selection algorithm selects the best-performing sets of attributes. We apply our method to eight datasets from different domains and data types. Our results show that, in most cases, the language model can produce new features based on mathematical and logical operators that are useful for the given tasks and can improve classification results.

Machine learning-based Type 2 diabetes risk prediction models obtain good internal validation results but lose effectiveness in real-world applications due to deficient external testing and fairness assessment. We developed a multi-dimensional framework evaluating discrimination, calibration, interpretability, and algorithmic fairness on nationally representative populations. An XGBoost model was trained on NHANES 2015-2020 (n=15,685) using eight non-laboratory predictors: age, sex, race/ethnicity, BMI, smoking status, physical activity, history of heart attack, and history of stroke. External validation was performed on BRFSS 2020-2022 (n=1,285,783) under realistic distribution shift. Internal validation showed good discrimination (AUC=0.794, 95% CI 0.788-0.800), with performance loss on external validation (AUC=0.717, relative decrease: -9.7%, p<0.001). Fairness analysis revealed severe bias: elderly adults (>=60) showed AUC=0.607 vs 0.742 for young adults (difference=0.135, p<0.001); obese individuals showed AUC=0.698 vs 0.735 for normal weight (difference=0.037, p<0.001). Gender showed comparable performance (male=0.723 vs female=0.712, p=0.142). Calibration revealed risk overestimation (Brier score=0.123). SHAP analysis identified age, BMI, and physical activity as primary risk drivers. Populations with highest diabetes risk receive the worst algorithmic performance, underscoring the need for fairness-aware, age-stratified deployment strategies before clinical use.

Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models. Under a fixed rank budget, LoRA parameterizes each adapted weight through a single low-dimensional input-side pathway, which may couple heterogeneous behaviors through shared input directions and induce interference during optimization. We propose Static Orthogonal Subspace LoRA (SOS-LoRA), a drop-in extension that reparameterizes a rank-rtot update as a sum of K static (always-on, non-routed) low-rank experts. SOS-LoRA (i) decomposes the total rank across experts, (ii) applies a fixed multi-scale scaling scheme to encourage scale-separated optimization dynamics, and (iii) promotes diverse input-side directions via cross-expert orthogonal initialization and a lightweight regularizer. SOS-LoRA remains fully mergeable, adding no inference-time parameters or latency after merging. Experiments on reasoning and knowledge-intensive benchmarks (Llama 2/3), encoder-based NLU (GLUE), and math reasoning (GSM8K/MATH) show consistent gains over matched-budget LoRA baselines and recent variants. Code is available at https://github.com/llm172/sos-lora.

Estrogen Receptor (ER) status is a critical biomarker in breast cancer diagnosis, prognosis, and treatment selection. Recent advances in high-throughput sequencing technologies have enabled the generation of multi-omics datasets that provide complementary molecular information for computational prediction tasks. This study presents a systematic benchmarking analysis of classical machine learning models for ER status prediction using transcriptomic (RNA expression), genomic (copy number variation; CNV), and proteomic (RPPA) data from the TCGA-BRCA cohort. A rigorous experimental framework incorporating stratified train-test splitting, stratified five-fold cross-validation, class imbalance handling, and fold-specific feature selection was employed to ensure reliable evaluation and prevent data leakage. Random Forest, XGBoost, LightGBM, CatBoost, Support Vector Machines (SVM), and Logistic Regression were evaluated across single-omic and multi-omic settings. Results demonstrated that RNA expression provided the strongest predictive signal, while multi-omic integration yielded modest but consistent improvements over individual modalities. Among all evaluated approaches, Random Forest achieved the best overall performance in the integrated multi-omic setting, obtaining a balanced accuracy of 90.3% and an ROC-AUC of 97.1%. Furthermore, recurrent selection of biologically relevant genes, including ESR1, PGR, FOXA1, and GATA3, supported the biological validity of the learned models. These findings indicate that carefully regularized classical machine learning methods remain highly effective for small, high-dimensional genomic datasets and that multi-omic integration provides complementary information for breast cancer ER status prediction.

Probabilistic seismic hazard and risk analyses are backbone to building codes, insurance pricing, and disaster management. Yet their open-engine pipelines remain accessible primarily to experts. We present the first agentic interface to the end-to-end probabilistic seismic hazard and risk chain via an open-source server, addressable through the Model Context Protocol (MCP). MCP wraps the OpenQuake engine and the 2020 European Seismic Hazard and Risk Models using twenty-four typed endpoints. Here, an agent is defined as a large language model (LLM) with tools. LLM is confined to the role of an orchestrator so it plans, translates, and explains, while the OpenQuake engine and custom codes compute hazard values, damage probability, and loss. Each response carries source-model, ground-motion model (GMM), and certified data provenance for transparency. Results are benchmarked against ESHM20 at seventy-three cities, the replicated 475-year spectral accelerations match official values within a median of 5 %, and a full hazard-to-loss estimate runs in minutes. The interface additionally accepts a user-supplied empirical or machine-learning GMM on any tectonic region type of the published tree, and adds additional features that existing web services omit: conditional spectra, deterministic scenarios, surface hazard, per-building loss, retrofit comparison, and record selection with waveform retrieval. The proposed design layers transfer to other regional models, and to other hazards.

Long-context large language model inference relies on the KV cache to avoid redundant attention computation, but incurs high memory and bandwidth overheads. Low-bit KV-cache quantization reduces this cost, yet it severely degrade quality; particularly, one-bit quantization reduces accuracy from 84.2% to 47.8% on Llama-3.1-8B under RULER. Rather than common beliefs that absolute error of logits, we find that the root cause is structured local misranking, where the distribution of logits in top-K region is drifted. We thereby propose local distribution restoration, a new technique that detects steps with high local distribution risk from quantized-logit features and restores only the selected top-K candidate distribution before token selection. We implement DGAP to achieve local distribution restoration, with efficient risk detcetors and correctors. Expeirments show that on Llama-3.1-8B, DGAP recovers K1V1 RULER accuracy from 47.8% to 83.2% and reduces distribution drift from 0.38 to 0.14; across Llama, Mistral, and Qwen models, it preserves the persistent low-bit KV-cache footprint with modest decode overhead.

Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost. The central question of when to invoke the LLM has received limited formal treatment. We cast this as a risk-based sequential stopping problem, where a trigger policy fires when a risk functional over the observation history exceeds a threshold. Within this framework, we prove six results: a minimum inter-event time bound excluding trigger chattering; optimality of threshold policies via smooth pasting; approximate SPRT guarantees under estimated parameters; O(sqrt(T log T)) regret for stationary streams, extending to O(sqrt((C_T + 1) T log T)) under C_T changepoints; O(1/sqrt(T)) convergence of online gradient descent for adaptive thresholds; and a calibration-to-miss-rate transfer inequality. Several classical trigger families, including event-triggered, optimal stopping, SPRT, CUSUM, and Bayesian triggers, can be expressed as special cases of this framework. On turbofan degradation data (CMAPSS) with real LLM calls, we empirically verify the theoretical assumptions, ablate the risk function design, compare against six baselines including a RouteLLM-style router and contextual bandits, and analyze cost sensitivity and LLM failure modes. The results confirm sublinear regret, with alpha < 1 for all principled triggers; high diagnostic quality, with 92.9 percent of 1600 LLM diagnoses reaching grounding score >= 0.75 under our rubric; and that anomaly-score-driven risk functions dominate alternatives by roughly an order of magnitude on the Pareto AUC.

To help evaluate the mathematical skills of current AI systems, we present a set of formulas for fundamental mathematical constants. These problems are attractive for AI evaluation because they are concrete and can be checked numerically to arbitrary precision, yet proving them may require non-obvious mathematics. Mathematical constants such as $\pi$, $e$, Catalan's constant, and special values of the Riemann zeta function have fascinated mathematicians for centuries. The search for formulas evaluating mathematical constants has produced some of the most beautiful mathematics in the field, especially in cases that yield irrationality proofs or fast convergence rates. Ramanujan's legacy is emblematic of this tradition. The list we provide contains two types of problems: formulas whose proofs are known to the authors but will remain encrypted for a short initial period; and formulas that are not yet proven. We are curious to see the achievements of AI in both cases.

Recent advances in language–audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space. While effective, existing retrieval embeddings are primarily optimized for audio–caption matching, limiting their ability to support diverse retrieval objectives and controllable retrieval behaviors. We present ALM2Vec, a universal audio embedding framework derived from pretrained large audio–language models (LALMs). By transferring the audio understanding, instruction-following, and reasoning capabilities acquired through large-scale multimodal training, ALM2Vec learns a unified embedding space for retrieval across audio domains and task types. Beyond conventional text–audio retrieval, ALM2Vec incorporates natural-language instructions into the embedding process, enabling instruction-aware retrieval for scenarios such as audio question answering and aspect-conditioned retrieval. Experimental results show that ALM2Vec achieves competitive performance on standard audio and speech retrieval benchmarks while exhibiting promising compositional and controllable retrieval capabilities, highlighting its potential as a unified audio embedding model for retrieval across domains, tasks, and user intents.

Large Language Models (LLMs) are rapidly being adopted in low-code and no-code automation platforms, where non-expert users design workflows that combine natural language understanding with external services and APIs. LLM agents are LLM systems that use LLMs as a core "brain" to reason, plan, and autonomously execute complex, multi-step tasks. In this paper, we present the first large-scale empirical study of LLM agentic workflows in low-code automation platforms. We analyze more than 6,000 publicly available n8n workflows and examine four aspects of their design: task distribution, structural and tool use patterns, reliability mechanisms, and autonomy levels. Our analysis shows that LLM workflows are not merely prompt response pipelines. Instead, LLMs are commonly embedded within broader automation structures involving control logic, external tools, communication services, storage systems, and human review points. We further find that while many workflows include lightweight post-processing or routing logic after LLM execution, explicit reliability mechanisms such as structured fallback paths, repair loops, failure-specific alerts, and human approval gates remain relatively uncommon. These results reveal a gap between the increasing deployment of LLM agents in practical automation ecosystems and the limited engineering support for reliability, safety, and governance. Overall, our study provides ten empirical findings and five research takeaways for researchers, platform developers, and practitioners seeking to understand and improve real-world LLM agentic workflows.

Autonomous vehicles (AVs) are increasingly deployed in urban environments, yet their safety frameworks remain primarily designed around collision avoidance and minimal risk condition (MRC) behaviors such as slowing or stopping when uncertainty arises. Although effective in reducing immediate crash risk, real-world deployments indicate that stopping alone does not guarantee safe integration into human-governed roadway systems. Incidents reported by municipalities and public records show that AV fallback behaviors can obstruct traffic, interfere with emergency response operations, and create accessibility challenges for passengers and pedestrians. This paper presents an analysis of publicly documented incidents involving AV stopping behavior and human-AV interaction failures. We categorize these incidents according to limitations in perception, planning, and control within current AV architectures. Using this taxonomy, we identify key gaps in existing safety paradigms, particularly the lack of mechanisms for interpreting human authority, responding to multimodal instructions, and adapting to dynamic, socially regulated traffic conditions. We then review emerging research directions that support human-interactive perception, language-grounded and accessibility-aware planning, and assisted control through remote guidance and teleoperation. The analysis highlights the need to augment current AV safety frameworks with capabilities that enable cooperative interaction with human agents and infrastructure. These findings suggest that reliable urban deployment of AVs requires moving beyond passive fallback strategies toward human-interactive autonomy.

Large language models (LLMs) increasingly mediate strategic interactions through natural language, making semantic control a critical element of communication and deception. This paper develops a semantic signaling game in which a sender selects a semantic control, an LLM generates a stochastic message, and a receiver evaluates the message using an awareness-dependent scoring mechanism. Receiver awareness is modeled as a type that determines which linguistic features are perceived and used for inference, providing a formal model of systematic blindness. The framework connects prompt-based control, statistical detection, and game-theoretic equilibrium analysis. Gaussian approximations of aggregate message scores enable likelihood-ratio decision rules, while Perfect Bayesian Nash equilibria characterize strategic behavior. The paper further develops mechanism-design approaches that reshape receiver awareness, penalize deceptive semantic controls, and modify receiver populations to induce benign pooling equilibria. Numerical experiments validate the Gaussian approximation, quantify awareness-ordering effects, analyze mindset dynamics under adaptive adversaries, and demonstrate how awareness shaping and guardrail costs reduce successful phishing attacks. The proposed framework provides a principled foundation for analyzing strategic language-mediated interactions in agentic AI systems and offers new tools for the design of robust and secure human-AI communication.

When firms deploy autonomous AI, they must decide how much work to leave to the system and how much to keep workers engaged. This decision affects current output and future human capital. We develop a parsimonious two-period model in which AI may outperform the worker when it functions, but may fail with positive probability. A firm chooses worker engagement; engagement lowers current output for below-benchmark workers, but changes future skill through learning and erosion. We distinguish two dimensions of AI progress: capability, the system's output when it works, and reliability, the probability that it works. In a single-firm benchmark, engagement is valuable only as fallback investment. The firm engages the least-skilled workers most, because they have the largest skill gaps and are least costly to bring toward a useful fallback level. With worker mobility, engagement also affects labor-market sorting: workers prefer jobs that build more valuable skill trajectories. This sorting motive targets higher-skill workers near the AI frontier, where skill gains are more valuable and engagement is less costly. Mobility can therefore reverse the engagement pattern, shifting investment from the least-skilled toward the most-skilled workers below the AI benchmark. Mobility also reshapes how AI progress affects engagement: greater capability raises engagement by increasing the value of the skill trajectory a firm offers, whereas greater reliability can raise or lower it because it reduces fallback need while also changing learning opportunities. Under worker mobility, human-AI work design becomes a problem of human-capital investment, in which allocating work today shapes future skill.

Neurological disorders involve diverse pathologies of the brain and nervous system, making early and accurate detection essential. While many deep CNNs have been developed for MRI-based classification of neurological disorders, most are optimized for binary tasks and often fail to capture the multi-class features needed to distinguish subtle anatomical differences across conditions. This study proposes the Enhanced Neurological Disorder Detection Network (End-Net) for multi-class MRI classification of neurological disorders. End-Net includes 24 convolutional layers, beginning with convolutional blocks followed by 21 optimized inception modules. These modules extract multiscale features via parallel 1 x 1, 3 x 3, and factorized 5 x 5 convolutional branches, along with max pooling, enabling the model to capture complementary texture, edge, shape, and contextual information. A global average pooling head, compact fully connected classifier, and dropout reduce parameters, limit overfitting, and improve robustness. End-Net was evaluated on the Multi-Class Neurological Disorder dataset, comprising MRI scans from patients with Alzheimer's disease, brain tumors, multiple sclerosis, and healthy controls. Severe class imbalance was addressed by augmenting minority classes with WGAN-GP and randomly undersampling the majority class. The results show that End-Net outperforms existing architectures in both accuracy and generalization. The model is also integrated into an online system for real-time web-based inference and accessibility.

Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to task-private representations, permanently discarding the boundary cues and semantic priors each branch could supply to the other. This work introduces BTI-Net, which establishes bidirectional communication at every decoder level through two parallel pathways via Task Interaction Modules (TIM). Spatial boundary context is gated into the classification branch, while global semantic priors multiplicatively modulate the decoder, with refined features propagating progressively from coarse semantics to fine boundary detail across all four decoder resolutions. Since cross-task interaction is not equally reliable for every input, Uncertainty Proxy Attention (UPA) gates each TIM output per instance and per level using three signals that capture cross-task alignment, scene complexity, and prediction confidence, without external annotations or additional inference passes. Experiments on three medical benchmarks spanning ultrasound, dermoscopy, and brain MRI demonstrate consistent improvements in segmentation IoU and classification accuracy over both encoder-sharing and decoder-interaction baselines. Ablation confirms adaptive gating contributes +2.36 IoU over fixed bidirectional interaction, and classification accuracy improves by up to +2.26 points over the strongest multi-task baseline. UPA's uncertainty proxies serve as reliable single-pass task-failure signals without the overhead of stochastic sampling. Code: https://github.com/C-loud-Nine/BTI-Net_MTL

Artificial neural networks (ANN) provide accurate continuous-valued representation, whereas spiking neural networks (SNN) offer event-driven temporal processing, yet both paradigms face limitations when value encoding and timing dynamics must be learned within a single computational structure. This paper introduces a network based on Unified Complex-valued Neuron (UCN), a new neural computational model that integrates continuous activation and phase-driven event generation through an asymmetric complex-valued state. In the UCN, magnitude encodes signal strength while phase governs intrinsic temporal evolution and valued spike emission. A foundational training framework combining backpropagation (BP) and backpropagation through time (BPTT) is first developed to optimize magnitude and phase pathways in a unified way. To reduce computational complexity, an event-driven adaptive phase learning (EAPL) rule is then introduced as a more efficient alternative. The proposed model is evaluated through object tracking and Lorenz attractor learning. Results demonstrate that UCN-based Network (UCNN) provides accurate, stable, and interpretable spatiotemporal learning while preserving sparse event-driven computation for neuromorphic and edge-AI applications.

In a changing decision problem, standard dynamic-regret analyses have often equated the cost of non-stationarity to how far loss moves. However, it is simultaneously possible for a loss sequence to travel far and retain the same optimal policy, or for a small movement in loss to force the optimal policy to change completely. Thus, the size of the movement through loss variation, transition variation, or comparator path length describe the adversary's motion, but not the cost of that motion to the control problem. For a more faithful analytic interpretation, this paper develops a normal-fan geometry for finite-horizon adversarial MDPs with fixed transitions. Occupancy measures form a polytope, and each loss vector exposes an optimal face of that polytope. Non-stationarity in rewards is therefore a path through the normal fan, where motion inside one cone leaves the optimal face unchanged, while crossing a wall may carry regret. We pose the notion of a face-crossing price, which is the minimum regret incurred by remaining on the previous optimal face under the new loss. For any learner that tracks the previous face, dynamic regret decomposes exactly into intrinsic priced face motion plus within-face selection error. The resulting theory separates consequential from harmless non-stationarity, where loss variation can be arbitrarily large at zero price, and identical one-coordinate variation can hide horizon-scale differences in regret.

Tabular foundation models cannot reason about data produced by running systems without access to the rules that govern them. We make this statement falsifiable. The Operational Turing Test (OTT) constructs pairs of legal and rule-violating database states whose $1$- and $2$-way column-value marginals match to a total variation of $<0.02$; Le~Cam's lemma then bounds any values-only classifier at $\geq0.49$ Bayes error. Three values-only baselines (XGBoost, TabICL, TabPFN) hit the bound exactly (accuracy $0.50$, pre-registered two one-sided tests (TOST) $p<0.002$), raw row-level access does not help, exposing relational value consistency closes most of the gap, and only a classifier fed by seven executable rule-derived audits reaches $1.00$ classification accuracy. In three matched $100$-state frontier large-language-model (LLM) runs, models given the schema, trigger source, rule tables, and state files classify at most $2/50$ legal states as LEGAL; GPT-5.5 accepts $0/50$ legal states even with higher reasoning effort and a Structured Query Language (SQL) executor. The access-ladder pattern also appears on a second schema with structurally distinct rule families (banking ledger: cross-row balance, cumulative aggregate). The barrier is identifiability, not capacity: scale, data, and richer features cannot cross it without operational grounding.

Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted. With a growing share of question answering systems built on top of commercial language model APIs, a method that can decide how much to retrieve, and how far to trust its own answers, without retraining the underlying model, is of clear practical value. This paper presents AB-RAG (Adaptive Budgeted Retrieval-Augmented Generation), a training-free and backbone-agnostic framework that generates an answer, estimates its confidence from a combination of three signals, and then decides whether to stop or to retrieve more evidence, subject to a fixed retrieval budget. The estimator combines the model's own certainty, the agreement between the answer and the evidence, and the variance of the retrieval scores. For models that expose token probabilities the certainty signal is read directly; for closed APIs it is approximated by self-consistency, so the method works without access to model internals. Across three backbones and two datasets, the central result is that the confidence estimate reliably separates correct from incorrect answers on every backbone, reaching a clean split of 57.6% against 0% Exact Match between high- and low-confidence answers on a factoid dataset. The adaptive policy improves accuracy on capable backbones, and the study reports its negative and nuanced findings honestly, including a confidence signal that proved unsuitable for short answers and a retrieval signal whose sign was found and corrected through measurement. The entire study was carried out on a single consumer laptop with only a few dollars of API spend.

There are various benchmarks to evaluate bugfixing capabilities of Large Language Models. However, most widespread benchmarks do not fully reflect real-world bugfixing practices. They are small, weakening statistical reliability, and the buggy programs are often similar to one another, potentially distorting evaluation results. The range of bug types can also be narrow, failing to capture a representative range of bugs. To address these issues, we introduce MegaBugFix, a large-scale bugfixing benchmark containing 12,629 buggy Python programs synthesized from correct ones by a Large Language Model. Bug injections were generated as diffs representing code changes. Through this approach, we were able to avoid common pitfalls of LLM-based mutation techniques like injecting overly simplistic bugs or failing to modify the input program. We evaluated 13 open-weight models on MegaBugFix and baseline benchmarks, finding consistently lower performance on MegaBugFix. This reveals that our benchmark presents more challenging bugs and exposes model failures that may remain hidden when evaluating on existing benchmarks. The benchmark and fine-tuned model used for bug injection are available at hf.co/collections/szalontaib/megabugfix.

Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports. As agents move from connection to execution, security decisions often remain split across clients, servers, prompts, approval dialogs, OAuth deployments, and logs. This paper asks whether a runtime can make execution-layer invariants explicit and testable while preserving MCP-like workflows. We define eight invariants: metadata non-authority, grant-backed approval, canonical resources, principal binding, scoped capability invocation, source-and-target data-flow authorization, deny-path audit, and explicit protocol state. We implement these invariants in HCP, a Handle-Capability Protocol reference runtime for MCP-style agent execution that represents calls through principals, resources, grants, capabilities, handles, policy decisions, data-pipe checks, and audit entries. We evaluate HCP against two MCP-like baselines: a naive connection-layer runtime and a practice-informed connection-layer mitigation baseline with metadata linting, session checks, and per-call approvals. Across 10 benchmark cases, the naive baseline permits all modeled attacks, the mitigation baseline permits 6 of 10, and HCP blocks all 10 while preserving audit evidence. Ablations identify which runtime components block attacks and preserve forensic evidence. A local in-memory microbenchmark reports sub-millisecond mean latencies for measured policy, invocation, peek, and pipe operations. A bounded GitHub README-screening sample provides ecosystem signals, not vulnerability findings. The results support a narrow claim: MCP-style agent systems need an execution-control layer in addition to connection-layer conventions.

Concept-based Explainable AI (C-XAI) seeks human-understandable explanations grounded in semantic concepts, yet validation is limited by the scarcity of fine-grained concept annotations. We evaluate whether mid-scale Multimodal Large Language Models (MLLMs) can perform localized concept naming under strict zero-shot conditions by assigning labels to bounding-box regions at both object and part levels. We propose a reproducible zero-shot evaluation protocol for Concept Naming (CoNa) with (i) closed-set, category-constrained prompting for moderate vocabularies and (ii) Open-CoNa, an embedding-similarity-based strategy for large label spaces. Experiments with four MLLMs (7B-32B) show consistent performance trends across datasets, reaching 62%-88% object-level exact-match accuracy, highlighting the potential of training-free concept annotation from localized regions. We discuss limitations and failure modes and release a reproducible framework to support future low-cost C-XAI research.