Papers

Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on both user preferences and input prompts, controllable multi-objective generation must dynamically adapt models at inference time without retraining. To address this, we propose Evolutionary Soups, a mixture-of-experts framework for fine-grained generation control, with gating networks trained via an evolutionary algorithm. The per-layer gating networks dynamically produce expert-merging coefficients from hidden-state representations, while the evolutionary algorithm incorporates greedy hypervolume contribution for effective evolution of these gating networks, achieving consistent improvements on large and noisy training datasets and broader coverage of the non-convex Pareto front. Experiments across three tasks demonstrate the effectiveness of Evolutionary Soups over baselines: it achieves the best hypervolume, linear utility, and Tchebyshev utility (~20% improvement) among controllable methods on all tasks.

The Learning With Errors (LWE) problem, introduced by Regev in 2005, is central to modern cryptography and post-quantum security. The algorithms to solve the search version of the problem, Search-LWE, can be broadly categorised into algebraic, combinatorial and lattice-based. In this work we propose a new algebraic algorithm for the Search-LWE problem. At a high level, the algorithm combines linear-algebraic techniques with S-polynomial-based methods from Groebner basis computation. We provide a direct complexity analysis of our algorithm, avoiding semi-regularity assumptions and complexity bounds derived from the degree of regularity. Our algorithm achieves a polynomial improvement in complexity over prior results that use Groebner basis methods to solve Search-LWE.

Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-calibrated confidence scores. Fine-tuned generative VLMs excel at identifying hallucinated text spans but suffer from overconfidence and high inference latency. Discriminative sequence taggers offer deterministic speed and superior calibration but exhibit conservative span recall. We present SpanCalib-VLM, a hybrid dual-system for the SHROOM-Visions Shared Task that combines a multimodal sequence tagger, consisting of XLM-RoBERTa-Large fused with a SigLIP vision encoder via cross-attention, with our fine-tuned generative VLM (Qwen3.5-4B-SHROOM-SFT). Through a Union-Calibrated Fusion strategy, candidate spans from the generative model are re-scored with calibrated probabilities from the sequence tagger. On the SHROOM-Visions English validation split, our ensemble achieves a Pearson calibration correlation of 0.41 and an overall IoU of 0.39 (with a clean-response IoU of 0.91 and overall detection accuracy of 70.7%). On the official blind test set, SpanCalib-VLM achieves a Pearson correlation of 0.32 and an IoU of 0.25 on English, substantially outperforming the shared task baseline (0.15 on both metrics) and demonstrating consistent gains across all four languages. We make our model weights and code publicly available.

Cryptocurrency markets generate high-frequency, multi-source data that is expensive to work with unless a team already has commercial-grade streaming and warehousing infrastructure in place. This paper describes a fully open-source pipeline that reproduces the behavior of a cloud-native, event-driven system – file arrival triggering a message, a message triggering compute – entirely on commodity hardware, using Apache Kafka and a filesystem-watching poller in place of managed cloud triggers. The pipeline partitions historical Gemini exchange data into hourly and minutely files, ingests them asynchronously through two independently grouped Kafka consumers (one for audit logging, one for Spark-triggered ETL), and lands cleaned output in a PostgreSQL warehouse with historical and aggregated schemas plus asset-specific data marts. We use the resulting Bitcoin data mart to compare a seasonal ARIMA model against a single-layer LSTM network for price forecasting, and separately apply Random Forest and Gradient Boosting classifiers, with additional engineered features, to the public Ethereum fraud detection benchmark introduced by Farrugia et al. We report the architecture, the modeling methodology, and the resulting metrics, and we are explicit about the limitations of comparing forecasts issued at different horizons and of evaluating fraud detection on a static, already-labeled dataset.

As agentic systems evolve into complex multi agent orchestration workflows, there is a growing and critical need for systematic frameworks that measures an agent's behavioral consistency and determinism. In this paper, we introduce a formal evaluation methodology that is grounded in AgentGraph, a planner powered by a domain specific language that represents agent reasoning through a dynamically adjustable directed graph. We leverage this structural formalism and utilize graph traversal algorithms that exhaustively enumerate conversational paths, forming a comprehensive evaluation set that captures the agent's complete behavioral space. We then systematically replay these reproducible trajectories to compare observed outputs and state transitions against the intended DSL specification. To quantify reliability, we define novel metrics that measure response and trajectory determinism, structural adherence and semantic consistency across both exact replays and their linguistic variants. Our system's results demonstrate that agents configured using frameworks like AgentGraph and LangGraph with explicitly structured node transitions show superior determinism over agents that are not configured with controlled transitions.

Artistic Text Recognition (ATR) remains challenging because word images often combine decorative fonts, curved layouts, object-like characters, clutter, and severe distortions. This paper studies WordArt-V1.5 as a standardized benchmark for this setting and evaluates recent scene and artistic text recognizers under a common protocol. We propose a confidence-aware ensemble that combines SVTRv2, PARSeq, and MAERec after fine-tuning on the official training split. The ensemble selects predictions using the minimum confidence over disagreement positions, emphasizing characters that separate competing hypotheses. For long words, where a single character error can invalidate the whole prediction, we add a targeted refinement stage based on Needleman-Wunsch alignment and lexicon-guided correction. On the WordArt-V1.5 Test B split, the proposed system reaches 89.90% Word Recognition Accuracy, improving the best individual fine-tuned model by 1.77 percentage points. The long-word refinement produces a modest global gain, but improves the targeted long-word subset by 2.72 percentage points. Finally, an error analysis of all remaining mistakes shows that 48.8% are associated with labeling issues, visual ambiguity, or illegible samples, highlighting the value of diagnostic reporting for future ATR benchmarks and models. Our source code is available at https://github.com/lucas-azdias/Artistic-Text-Recognition/.

When a deployed vision-language-action (VLA) policy fails, fine-tuning it again for every new setting is costly, yet the person watching it can usually say what went wrong in one sentence. We ask what such a sentence can and cannot fix in a frozen policy. Labelling every failing LIBERO-90 task (out of distribution) for OpenVLA-OFT and pi0.5, we find that the failures sort into four modes and that only one, execution misalignment, where the policy reaches the right target but miscalibrates how far or how hard to move, is within reach of a sentence; the other three lack a target or a plan, not a magnitude. For this mode we define the narrowest human correction: one retrospective sentence per task, grounded by an LLM into an action dimension, direction, magnitude term, and time window, becomes a short bias on the frozen policy's actions, after which the policy completes the rest on its own, episode after episode. Re-executed on its task's failed rollouts, it recovers 65 of all 139 in-distribution and 33 of all 328 out-of-distribution failures in simulation; on a real xArm7 after the robot base is moved, it raises pick-and-place from 10/30 to 30/30 in each of two same-object conditions and from 2/30 to 24/30 with a new object, while two long-horizon tasks stay at 0/30 with and without correction, as the taxonomy predicts. A naively prompted VLM that watches the same failures and writes the same kind of correction recovers none in up to 10 attempts, suggesting that the value lies in the person's calibrated sense of magnitude and timing rather than in language itself. Videos: https://correctvla.github.io/

Domain adaptation of large language models increasingly depends on constructing high-quality training data, yet existing data-preparation pipelines typically address quality only after generation through post-hoc filtering. This creates a fundamental mismatch: data-quality issues often originate from the construction process itself, while quality control is applied only to its outputs. We introduce DataFoundry, a framework for evolving data preparators through recursive self-improvement before large-scale data production. DataFoundry represents a data preparator as an evolvable runtime specification and instantiates its evolution with a Skills-as-Modules architecture, in which a central Controller orchestrates modular skills to compile executable runtimes, diagnose deficiencies on small pilot sets using domain-appropriate criteria, and translate diagnostic feedback into adapters that revise individual preparation components while preserving stable interfaces. We evaluate DataFoundry on DataPrep-Bench across mathematics, finance, law, and medicine, and find that recursively evolved preparators produce training data with higher downstream utility than baselines. Experiments across different backbones further demonstrate that these improvements are not tied to a particular model, while analyses and case studies further reveal the framework's optimization dynamics and illustrate how its evolution unfolds in practice.

Large language models can convert medical documents into structured data, but plausible output may still be unsupported by the source. Persisting such output in a longitudinal health record, a record that accumulates patient information over time, therefore creates an integrity risk: unverified data may influence later summaries, trends, or preventive-care computations. We introduce an evidence-gated trust-promotion model that keeps generated data provisional until a deterministic monitor verifies it against the source document. The monitor admits a candidate for a specified downstream use only when the source contains a unique supporting quotation, the relevant fields occur within the same laboratory row, and the required provenance is preserved. The generator cannot approve its own output, missing or ambiguous evidence causes refusal, and refused candidates remain available for human review rather than being silently discarded. We implement the model in Medical DataCloud, a personal health-record application, and evaluate it through automated tests and a replay of saved extraction outputs. All 22 conformance and mutation tests pass. The replay covers nine historical laboratory PDF reports containing 102 manually labelled rows. The reports produce 97 numeric candidates: schema validation accepts all 97, an earlier packet-level evidence check accepts 94, and the hardened quotation- and row-level policy admits 72 while retaining 25 for review. The study evaluates system integrity rather than clinical correctness or clinical safety. The results demonstrate the technical feasibility of an enforceable boundary that prevents generated claims from authorizing their own reuse in a longitudinal health record.

Language is humanity's most consequential technology, yet for over a billion speakers across India's twenty-two constitutionally recognised languages, its digital layer remains structurally incomplete. Named Entity Recognition (NER), the foundational step in transforming raw text into machine-interpretable knowledge, has been studied exhaustively for English but remains largely unsolved across most Indic languages. This paper presents a rigorous comparative study of generative and encoder-based neural architectures for NER on all eleven languages of the Naamapadam benchmark. We evaluate five classic model families spanning sequence-to-sequence transformers and multilingual encoders; four decoder-only large language models (LLMs) fine-tuned with LoRA and 4-bit NF4 quantisation; and nine generative models in zero-to-5-shot inference. Under strict CoNLL span-level evaluation, encoder-based models (mBERT and XLM-R, both F1=0.675 on Hindi) substantially outperform every generative architecture in ten of eleven languages, with gaps of 7.5-40 percentage points against the strongest competitor (Gemma-2-2B: avg F1=0.427). The best few-shot result reaches only 28% of the encoder baseline. We identify three language clusters–encoder-dominant, partial-coverage, and failure-zone; and provide actionable deployment guidelines grounded in transfer learning and low-resource NLP principles.

Long videos contain far more visual content than Large Vision-Language Models (LVLMs) can process under a fixed visual-token budget, making frame selection essential. Existing query-aware selectors usually estimate frame-query relevance and build a compact subset from high-scoring frames. Although their mechanisms differ, the similarity sequence is still often treated primarily as values to rank or sample from, rather than as an ordered signal whose shape reflects how query-relevant evidence emerges, peaks, and fades over time. This can obscure frames that explain, contextualize, or follow an event, because such evidence may lie on the rising or falling sides of a nearby relevance peak and receive lower absolute scores. We propose RIDGE, a frame selection framework that reads the frame-query similarity curve as a temporal signal. By using local changes and curvature, RIDGE partitions the timeline into structural regions and applies region-specific selection to preserve event cores, transitions, buildup, aftermath, and contextual frames under a fixed budget. It is a lightweight post-processing step on precomputed frame-query scores and requires neither training nor iterative LVLM calls. Across four long-video benchmarks and three backbones, RIDGE achieves the best performance in most settings and remains competitive in the others.

Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete patterns. We propose the Hidden CoT Detection Score (HCDS), a comparative behavioral and mechanistic signal measuring whether neutral-prompt behavior aligns more closely with explicit CoT or explicit no- CoT. Here, hidden CoT operationally denotes this neutral-prompt CoT-like alignment; HCDS does not directly observe or prove an unexposed reasoning trace. On GSM8K, HCDS is significantly positive for both Qwen3-4B variants (Thinking $+1.87$, $p = 1.2 \times 10^{-7}$; Instruct $+1.41$, $p = 1.9 \times 10^{-4}$), replicates across a different inference stack and quantization within $0.08$ ($+1.80$ and $+1.45$), and is not significantly positive in seven of eight length-adjusted calibration-control cells. The unadjusted score produces large positive scores on single-step arithmetic and numeric factual lookup. The variants also respond differently to no-CoT instructions: Instruct complies from the prompt alone, whereas Thinking continues reasoning and requires intervention. These findings show stronger, less prompt-conditional CoT-like behavior in the reasoning-tuned model, consistent with but not proof of latent reasoning. HCDS thus investigates latent reasoning without relying on models' self-reported traces.

Digital Twins (DTs) have emerged as a key technology for improving the monitoring, optimization, and automation of manufacturing systems. However, existing Cyber-Physical Machine Tool (CPMT) implementations primarily represent the machine tool, while the machining process remains only partially synchronized with its physical counterpart. This paper extends a previously presented CPMT framework by introducing a hierarchical DT framework that simultaneously maintains DTs of both the machine tool and the machining process. The proposed framework integrates real-time CNC operational data, a voxel-based workpiece representation, synchronized process vibration measurements, and a persistent part DT repository for process replay, traceability, and future synthetic data generation. Experimental evaluation demonstrated real-time operation at a 20 Hz machining-state update rate, interactive visualization exceeding 100 frames per second, and a mean depth reconstruction error of 0.16 mm. The implementation provides a foundation for AI-assisted machining applications while preserving the machine tool monitoring and teleoperation capabilities.

Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework that synthesizes a corpus into a hierarchical, typed, navigable wiki and trains an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use. The wiki organizes knowledge into three layers - document overviews, cross- document topic pages, and page-level source records; enabling progressive refinement of retrieval when initial lookup misses. We optimize the agent's navigation policy with on-policy reinforcement learning with a multi-component reward function balancing answer correctness, retrieval quality and trajectory efficiency. Evaluation on ViDoRe-V3 (8 domains), FinanceBench, and memory benchmarks (LoCoMo, LongMemEval, PersonaMem-v2) shows that WikiResearcher- 9B which is our RL-tuned Qwen 9B model, significantly outperforms same-size untrained baselines and exceeds or matches larger external models. SearchWiki paired with WikiResearcher-9B demonstrates that learned navigation over structured corpora is a superior alternative to flat retrieval.

The current paper draws on self-presentation theory and warranting theory to evaluate how the language patterns in an online marketplace reflect seller status (i.e., a prolific seller versus an everyday seller). Using 1.6 million musical instrument listings from Reverb.com in search of content, style, and structural differences in seller product descriptions, the evidence suggested prolific sellers tend to focus more on objective and functional aspects of a product (e.g., its features and specifications) and less on subjective characteristics like tone, relative to everyday sellers. Prolific sellers also communicated in a more narrative-like style, which was driven by an elevated use of personal pronouns, and they used longer descriptions than everyday sellers. Therefore, what prolific sellers focus on tends to be quite technical, but how they communicate this information is typical of a story that is told to potential buyers. Implications for self-presentation theory and warranting theory are discussed.

Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and matching at the token level. However, this approach incurs high storage costs. Existing compression methods typically fix a single compression level at indexing time, limiting flexibility. We present ColSNAP (Spatial Nested Average Pooling)1, a training method that generates a nested hierarchy of compression levels directly from a backbone's patch grid. By spatially pooling patch embeddings into pro- gressively coarser tiers and training all tiers simultaneously, a single model learns to support retrieval at multiple compression levels without architectural changes. Crucially, a single encoding pass yields every tier, enabling the accuracy-storage trade-off to be configured at indexing time to match avail- able storage budgets, rather than being fixed during training. We demonstrate that models trained using ColSNAP maintain near full-resolution retrieval performance under substantial compression and that ColSNAP transfers effectively across multiple late-interaction backbones, and achieves most of its improvements via a lightweight adaptation stage applied to a pre-trained retriever.

As artificial intelligence (AI) is increasingly integrated into social-emotional learning (SEL) initiatives, the need for evidence-based policy has become paramount. We systematically reviewed 65 peer-reviewed papers that examine the intersection of AI and SEL to investigate how these studies articulate policy implications. Our analysis revealed a substantial "policy deficit" in the current AI x SEL literature: nearly three-quarters of the studies did not mention policy implications at all. Using the "WH-question" framework (Who, What, Why, When/Where, and How), we map the policy implications narratives present in the literature and show that they often lack the specificity and actor-oriented guidance required for effective evidence-informed policymaking. We find a significant association between publication venue and policy engagement, suggesting that current academic incentive structures may prioritize technical innovation and pedagogical feasibility over explicit engagement with governance and regulation. This study identifies a "techno-solutionist" trap, where technical potential is foregrounded while the institutional conditions for responsible implementation remain under-specified. We conclude by proposing a shift from "implication-as-afterthought" to "implication-as-methodology" and offer a set of actionable guidelines for researchers, editors, reviewers, and policymakers to bridge the gap between AI innovation and educational governance. Rather than presenting policy as a generic ethical horizon, we argue that AI-SEL studies should systematically specify Who should act, What actions are recommended, Why these actions are needed, When and Where they apply, and How strongly they are framed, thereby strengthening the translation of AI x SEL innovation into educational policy and practice.

The continued integration of distributed energy resources (DERs) motivates research into integrated system planning. While existing literature shows that DERs can reduce system costs, it often overlooks customer behaviour, particularly DER adoption driven by cost savings and incentives. System cost allocation can influence these decisions, affecting DER uptake, grid injections, and overall system efficiency. Therefore, integrated system planning should consider both system- and customer-level benefits of DERs. This paper proposes a multi-step framework that combines an integrated planning model with cost allocation and retailer business models. The integrated planning model minimizes total system costs subject to network constraints, while the cost allocation and retailer models capture customer responses to costs and DER opportunities. By coordinating these models, the framework represents how customer behaviour influences planning outcomes. The proposed approach is demonstrated on a 36-bus system, with results showing that incorporating customer decision-making reduces overall system costs, lowers reliance on transmission-connected generation, and supports more realistic system planning.

Evaluating data-text alignment remains challenging: existing metrics often provide limited explanations for the scores, while prompt-based LLM-as-Judge methods can be expensive and unreliable. We present an end-to-end explainable evaluation metric that fine-tunes a language model to identify omitted, extra, incorrect, and correct data units in a data-text pair. These local judgements are aggregated into precision, recall, and F1 scores, providing both fine-grained diagnostic feedback and an interpretable measure of alignment quality. Across benchmarks, our fine-tuned models outperform LLM-as-Judge methods in error prediction and achieve competitive precision, recall, and F1 scores, while maintaining strong correlation with human judgements. Beyond evaluation, our verifier outputs also provide useful feedback signals for downstream correction and refinement, supporting alignment-oriented improvement of data-to-text and text-to-data. Code and resources are available at https://github.com/guihuzhang/xqdt.

Brain tumor segmentation in magnetic resonance imaging (MRI) is a critical task for diagnosis and treatment planning. Despite the success of deep learning architectures such as U-Net and its variants, performance degradation across datasets remains a major challenge, particularly under domain shift and limited annotated data. To address this issue, this study systematically evaluates how individual MRI sequences influence model robustness across two well-known datasets. A ResUNet-based framework is employed, where each modality is trained independently to isolate its effect under a controlled cross-dataset evaluation protocol with tumor size stratification, without target-domain training, or with limited domain adaptation. Results show that the T2f/FLAIR sequence achieves the best cross-dataset performance, with Dice scores exceeding 75%. It consistently outperforms other modalities across most tumor size ranges, while multi-sequence training further improves performance. Additionally, even limited target-domain adaptation yields rapid initial gains, reducing the need for extensive annotations and costly retraining. Our source code is publicly available at https://github.com/henrique-zan/brain_tumor_segmentation/.

Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to remove such information, but it remains unclear whether existing methods truly erase it or merely hide it within the model. A key challenge is quantifying the persistence of sensitive data under a unified evaluation framework. To address this, we construct a synthetic dataset containing fake private information and propose a white-box auditing framework to systematically assess whether claimed-forgotten information is genuinely removed. Using this framework, we evaluate five existing unlearning methods and find that a simple "inverse greedy" decoding – selecting the least likely token at each step – can recover supposedly forgotten private information. Our results reveal that current unlearning approaches often fail to fully eliminate sensitive information, highlighting the need for more reliable methods to ensure privacy in deployed LLMs.

The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized action from a malicious, unauthorized action when both rely on external tool information. This ambiguity can cause benign actions to trigger unnecessary verification and intervention, reducing utility and adding latency. We expose this limitation through an authorization-equivalence audit of 96 conditions derived from 24 base cases. Within matched source comparisons, we hold authorization, the exact committed action, and its intended effect fixed, changing only whether a required value comes from the user or a legitimate tool result. Although the action remains unchanged, this harmless relocation shifts the causal signal toward the attack region in all 24 cases under both Llama and Gemma scorers. Matched unauthorized controls show that the signal remains attack-sensitive, yet the benign relocation produces a larger average score shift than the actual change in authorization. Architecture-level evaluation shows how this mismatch propagates through guardrail designs. With a semantic monitor, attack success is 0% and utility is 28%, compared with 16% and 60% without it. A shadow-based guardrail allows every tested harmless run, yet does not reject matched unauthorized actions more often overall: 57.5% of unauthorized runs pass automatically before reaching the later security check, compared with 29.2% of authorized runs. These results show that the studied causal signal reveals what shaped an action without reliably encoding whether the action was authorized, and that reference construction and routing are integral to the effective security decision.

Streaming-potential-mediated transport of viscoelastic fluids has attracted research attention owing to its applications in electrokinetic energy conversion and microfluidic transport. Existing analytical and semi-analytical models in published literature provide valuable physical insights, but require repeated numerical evaluations for exploring large design spaces and identifying the optimal operating conditions. In this work, a surrogate-assisted framework is developed for rapid design optimization of pressure-driven electrokinetic transport of simplified Phan-Thien-Tanner fluids in a slit microchannel. A high-fidelity numerical database is generated over a broad range of governing dimensionless parameters, which includes the zeta potential, the Debye parameter, the Dukhin number, and the viscoelastic parameter. A Machine Learning surrogate model is subsequently trained to accurately approximate the nonlinear relationship between the governing parameters and the streaming potential, while the volumetric flow rate and hydroelectric energy conversion efficiency were calculated from closed form equation by using the streaming potential predicted by the surrogate. This is coupled with a multi-objective optimization strategy to identify operating conditions that simultaneously maximize energy conversion efficiency and volumetric flow rate. The proposed methodology can significantly accelerate parametric exploration compared with repeated numerical simulations across different parameters and provides practical design guidelines for electrokinetic microfluidic devices. The study demonstrates the potential of combining computational fluid mechanics with data-driven surrogate modeling for efficient engineering design and optimization.

Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space. LaWAM established this formulation, but its original presentation left the world model, multimodal backbone, and deployment checkpoint tightly coupled. We introduce AcrossWAM1.0, a modularization and scaling study of this latent world-action stack. Rather than presenting latent subgoals as a new algorithm, we make the module boundary explicit: a policy adapter produces latent-action and action-generation contexts; a retained latent world decoder grounds the predicted transition in the current scene;and a flow-matching expert generates continuous action chunks. We further separate training-only teachers from the inference graph and provide a verifiable deployment export. On 2,000 paired LIBERO episodes, replacing a Qwen3-VL-2B backbone with Qwen3.5-0.8B yields 97.45% success versus 98.00% for the 2B model (a-0.55percentage-point difference; exact McNemarp=0.266). This does not prove equivalence, but it meets a prespecified two-point retention criterion. The compact, inference-reachable checkpoint contains 1,472.6M unique parameters, 42.4% fewer than the original 2B policy, while all retained tensors are bitwise identical to the source checkpoint. Cross-family execution is additionally checked with a MiniCPM-V adapter smoke test; closed-loop cross-family transfer remains an open evaluation. AcrossWAM1.0 therefore contributes an auditable software and evaluation boundary for compact latent world-action policies, distinct from LaWAM's original latent-subgoal contribution.

Safety alignment of large language models (LLMs) degrades across languages, yet the internal mechanism driving this asymmetry remains poorly understood. Our work, therefore, presents a systematic mechanistic analysis of multilingual safety using sparse autoencoder (SAE) features, sparse interpretable directions in the residual stream associated with harmful and harmless model behavior across three instruction-tuned LLMs, eight languages, and all model layers. We observe that safety-relevant features are architecture-dependent in terms of where they are located and how they are distributed across layers. Additionally, they are geometrically entangled with language identity and exhibit cross-lingual sharing patterns, i.e., languages share safety features to varying degrees across model depths and architectures. This safety-language entanglement has direct consequences such that ablating safety features impacts not only harmful response rates but also target language, with the degree of intervention predicted by the relationship between safety and language features. Our findings qualify the language-universality of safety alignment as architecture-dependent and offer a mechanistic account of multilingual safety interventions.

Simulation of admittance-type models requires physically consistent dynamic models that are rarely available for off-the-shelf, everyday objects, limiting the fidelity of haptic interfaces that rely on such simulations. This paper presents the first complete workflow for producing physically consistent models of large real-world objects with various constraints and mechanisms, guaranteeing physical consistency of inertia and friction parameters. The workflow separates each object and identifies the handle and body in two stages, requiring no torque sensors at hinges, axles, or other constrained joints. Models are produced for a heavy, closer-actuated door and a wheelbarrow, representing objects of differing constraint types and model complexity. The door is modeled using four-bar linkage kinematics and a fluid dynamics-based lumped parameter model including opening, backcheck, swing, and latch zones. The wheelbarrow is modeled as a rigid body with a spherical wheel and no slip during rolling. Handle estimation RMS errors were below 0.64 N and 0.042 Nm across both objects. Door body estimation had RMS error of 2.19 Nm and wheelbarrow body estimation had RMS error of 6.77 Nm.

KV-cache compression reduces LLM inference memory by evicting context tokens, but when the evicted tokens contain answer-bearing evidence, the model may hallucinate instead of recognizing that the compressed context is insufficient. We address this failure from a behavioral perspective: to our knowledge, this is the first work to formulate compression-aware abstention as a learning problem, in which a model learns to answer when supporting evidence survives compression and abstain when it does not. We construct supervision from compressor survival masks and tight answer-bearing spans, labeling examples as Confident when evidence survives and Abstain when it is removed. A 10.1M-parameter LoRA adapter trained on ~2.6K MuSiQue 2-hop QA examples reduces base-model hallucinations by 97% under prompt-style truncation while preserving correct answering on evidence-retaining examples. Unlike prompt-only abstention baselines, which over-abstain on many answerable high-retention examples, the trained adapter learns a conditional policy. We also evaluate the method under actual compressed-cache decoding, where multi-compressor training yields a 6-22x relative lift over the unaided base on evidence-retaining examples. Controlled-deletion experiments show that the learned behavior is driven by evidence content rather than input length alone.

This paper focuses on computing spectral solutions for high-order eigenvalue problems using an efficient discretization method based on Chebfun spectral discretization algorithms and domain truncation. We solve several numerical eigenvalue problems, demonstrating both the accuracy and computational efficiency of the proposed approach.

Black-box model attribution is increasingly relevant when large language models (LLMs) are served through relay and reseller APIs. A tempting low-cost signal is the prompt-token count returned by an OpenAI-compatible endpoint: two models that share a tokenizer and chat template may produce the same count sequence up to a fixed offset. Yet the validity of this signal for broader model-family attribution has received little direct holdout testing. We conduct a frozen-threshold study over 24 labeled endpoint pairs, split evenly into a development set and an untouched holdout set, with three temporal repeats and 30 controlled texts per pair. We introduce a validity-gated result contract that distinguishes an observed dissimilarity from an uninformative measurement caused by missing usage data, rate limits, or endpoint policy. The resulting shift-invariant exact-match score perfectly separates the 12 development pairs, yielding a frozen threshold of 0.725. On holdout, however, only 6 of 12 pairs are eligible under the pre-specified three-repeat rule. Among eligible pairs, balanced accuracy is 0.75, sensitivity is 0.50 (95% Wilson interval 0.15–0.85), and specificity is 1.00 (0.342–1.00). Two same-family pairs—Qwen 3.8 and DeepSeek V4 variants—fall below the frozen threshold. Across 4,320 formal API calls, every log is replayable, while holdout contains 189 non-200 responses and 157 successful responses without prompt-token usage. The study therefore validates token-count consistency as a fingerprint of a shared tokenization stack, but rejects its use as a standalone necessary test for model-family lineage.

Vehicle attribute recognition is an important task in intelligent transportation systems, particularly when Automatic License Plate Recognition (ALPR) is unavailable or unreliable. Although vision foundation models have shown strong transferability across domains, their effectiveness for fine-grained vehicle classification remains underexplored. Moreover, given the inherently three-dimensional structure of vehicles, it is unclear whether emerging 3D-aware foundation models offer advantages over standard 2D architectures. This paper presents an empirical benchmark of 14 state-of-the-art 2D and 3D-aware vision foundation models. Using the challenging real-world UFPR-VeSV dataset, we evaluate these models as frozen feature extractors via linear probing for vehicle type, make, and model recognition. We further stress-test the best-performing models under few-shot learning and Out-of-Distribution (OOD) domain shifts. Our results show that standard 2D self-supervised models, particularly DINOv3, substantially outperform 3D-aware models in fine-grained tasks, achieving over 93% Macro-Accuracy for make and model recognition. However, the 3D-aware Depth Anything v2 exhibits stronger invariance to viewing angles in vehicle type classification. These findings motivate hybrid approaches that combine 2D and 3D priors for robust vehicle recognition. Our code is publicly available at https://github.com/UFPR-IPASPPR/3D-Vision-Benchmark/.