Understanding and forecasting lake dynamics is critical for monitoring water quality and ecosystem health across lakes and reservoirs. While machine learning methods have been recently applied to ecological time-series data, existing works assume regular sampling in time and depth, and struggle to generalize across lakes with heterogeneous variables, depths, and observation patterns. To address these limitations, we introduce \textsc{LakeFM}, a foundation model for aquatic systems, pre-trained on large-scale ecological datasets comprising both simulated and observed lakes. Through extensive empirical evaluation, we show that \textsc{LakeFM} learns meaningful representations spanning broader lake-level characteristics, and achieves competitive or often superior-forecasting performance compared to existing time-series foundation and non-foundation models, while producing physically plausible predictions consistent with real-world lake dynamics.

Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise. None operates on the artifact an auditor most often holds: the model's output. We ask what can be decided about leakage from predictions and outcomes alone. We give a decision-theoretic framework in which leakage diagnostics are functionals of the predicted-risk/outcome law, parameterized by a threshold-weighting linked to proper scoring rules and decision-curve analysis. We prove a sharp impossibility: a recalibrated leak matching an honest model's calibration and discrimination is indistinguishable from honest performance by \emph{any} function of the predictions, so the broad class is detectable only against an externally supplied ceiling on achievable discrimination. We then prove what leakage cannot hide: a near-deterministic subgroup -- the signature of a near-label leak -- produces a sustained unit-purity head that no legitimate predictor of a non-deterministic outcome can manufacture, yielding a prior-free test. These results organize leakage into a trichotomy -- miscalibrated, broad-calibrated, and deterministic -- each with a matched detector and failure mode. We validate on UK Biobank using time-windowed comorbidity leakage with known, graded severity, measuring a detection floor of $Δ\cstar \approx 0.007$ on this endpoint, below which residual leakage is undetectable from output and too small to alter conclusions. The numerical floor is cohort- and endpoint-specific; the structural lesson is general: output-only detection fails where residual leakage is indistinguishable from an honestly stronger predictor. The test returns a verdict on a prediction vector in under a second on commodity hardware.

The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode budget has been exceeded. At race speeds, where collisions are instantaneous and irreversible, any safety mechanism that waits for cost to accumulate is structurally too late. We present VLM-Safe-RL, a framework that integrates a frozen vision-language model into the CMDP Lagrangian update as an anticipatory cost term. The framework comprises four contributions: (i) Decoupled Dual-Path CLIP, independent reward/cost paths that respect the CMDP's factorization; (ii) VLM-Lagrange, an augmented multiplier update that incorporates a per-step VLM cost as an anticipatory term; (iii) Confidence Gating, a Bayes-optimal weight derived from a logistic noise model on the CLIP margin; and (iv) VLMPPOLag, the composed algorithm. On Safety-Gymnasium FormulaOne L2, our principal evaluation ($n{=}5$ seeds, $10^{6}$ steps, budget $d_{\text{lim}}{=}25$) VLMPPOLag$+$Conf is the only configuration in our default budget comparison that simultaneously retains substantive return ($J_r{\approx}40$) and holds cost within budget on a majority of seeds; the five constraint-aware baselines (PPOLag, CPO, CPPOPID, CPO-CLG, PPOLag-RND) each fail at least one requirement. The mechanism generalizes to held-out MetaDrive Medium (catastrophe rate $41\%{\to}26\%$, 95\% bootstrap CI $[-26,-5]$\,pp) and shows directionally consistent transfer to Bullet Safety-Gym; we report honestly where it does not (MetaDrive Easy/Hard, Qwen2-VL backbone) and trace the Hard failure to a Lagrangian-regulation pathology rather than the VLM signal itself. To our knowledge, this is the first work to use frozen VLM signals as an anticipatory cost term inside the CMDP Lagrangian update.

Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference. A common hypothesis is that interference during adapter composition arises from overlap in linear parameter updates, suggesting that enforcing orthogonality or directional independence should improve multi-domain performance. We test this hypothesis using DoRA-RBAC, a hierarchical adapter composition framework based on weight-decomposed low-rank adaptation. We compare conventional Euclidean merging with a geometry-aware Riemannian-inspired merging strategy that approximates the Frechet mean via normalized directional averaging across multiple QA benchmarks (GPQA, PubMedQA, SimpleQA, WMDP) on LLaMA-3.1-8B and Mistral-7B. Our results show that while single-domain performance matches LoRA, geometry-aware merging provides no consistent advantage over standard averaging in multi-domain settings.Diagnostic analysis further reveals that angular alignment and orthogonality of adapter updates are weak predictors of composition performance. These findings suggest that adapter interference is not governed primarily by parameter-space geometry, but is instead consistent with interactions in shared nonlinear representations.

Humans process rich auditory environments through tightly integrated cognitive capabilities such as audio perception, audio reasoning, and memory. Despite recent progress in large audio-language models (LALMs) across speech understanding and multimodal audio reasoning, current evaluation paradigms remain largely task- or modality-centric, focusing on end performance while overlooking underlying auditory cognitive behaviours. This reveals a fundamental gap between how auditory cognition is understood in humans and how it is evaluated in LALMs, particularly in the lack of frameworks that operationalise cognitive principles beyond task-level metrics to systematically capture model behaviour. In this work, we introduce RAIL, a human-centric evaluation paradigm grounded in the Cattell-Horn-Carroll (CHC) cognitive framework. RAIL formalises auditory cognition into five core capabilities and develop them into structured evaluation tasks that probe how models process, retain, and integrate auditory information. We further construct a cognitively grounded benchmark with principled data curation and human-aligned evaluation protocols. Evaluating 26 state-of-the-art LALMs, we find that current models exhibit highly uneven performance across cognitive abilities. RAIL establishes a new evaluation paradigm that moves beyond task-centric benchmarking toward cognitively grounded assessment of auditory intelligence.

Gradient-based inversion of reaction-diffusion systems is typically approached via surrogate models or physics-informed neural networks (PINNs), while the most direct route, backpropagation through the PDE's structure itself, has largely been avoided. We pursue this direct route as a diagnostic probe, backpropagating a steady-state loss through unrolled Gray-Scott simulation to recover its parameters, with no surrogate or neural-network augmentation. Optimization fails to converge, and plotting the landscape directly locates the failure in its geometry -- flat plateaus with no gradient signal, bounded by sharp cliffs that align with bifurcation boundaries -- a structure that recurs across loss functions and is inherited however the gradients are routed to parameters. Reading this minimal setup as an ablation of PINN, we disentangle each component's role: with the neural network fixed, the residual loss is quadratic in the PDE parameters and yields a smooth landscape, so it alone already avoids the pathology, by implicitly encoding the full PDE dynamics across all initial conditions. The neural network, for its part, cannot repair an ill-posed parameter subspace, and so serves only to complete the observed data -- a division of labor not previously made explicit. These findings carry concrete design implications for PINN-type methods and a broader heuristic on when added dimensions actually help.

Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation. Running them entirely on-device benefits privacy, latency, and offline use, but the energy cost of CPU inference is a major barrier. We present what is, to our knowledge, the first end-to-end RAG pipeline that runs all neural stages -- embedding, reranking, and LLM generation -- on the Qualcomm Hexagon NPU of the Snapdragon X Elite. Profiling on a Dell XPS 13 laptop, we compare NPU-accelerated RAG against CPU and OpenCL/Adreno GPU baselines on indexing and query workloads. On indexing, the NPU achieves 9.1x higher embedding throughput and 12.3x less system energy. On a 120-query Wikipedia-passage benchmark, it delivers 18.1x faster LLM prefilling, 4.0x lower end-to-end query latency, and 4.0x less system energy than the CPU baseline; the same workload on the integrated GPU is 1.7x slower than CPU and uses 6.5x more energy than the NPU. A GPT-4.1 LLM-as-judge evaluation finds NPU answer quality on par with CPU and GPU within evaluator noise (mean 9.32 vs. 8.95 vs. 9.03 on a 1-10 rubric), with 86.7% of queries scoring identically across all three backends. On the Snapdragon X Elite / Hexagon class of laptop SoC, the NPU thus enables practical, energy-efficient on-device RAG without quality regression -- a sustainable path toward green edge intelligence that we expect to generalize to comparable mobile NPUs (Apple Neural Engine, Intel NPU, MediaTek APU) as their software stacks mature.

Many multivariate dynamical systems are observed only through trajectories, leaving the mechanisms governing their joint dynamics hidden. Existing approaches can impose interpretable dynamics or learn flexible state transitions, yet the resulting interaction structure is typically either specified in advance or left implicit within the learned dynamics. We introduce MF-Net, a recurrent dynamical model that represents all variables in a shared field state and updates this state through a learned relation law. Each variable carries a field component, and these components evolve jointly through a learnable mechanical transition. Here, mechanical refers to the relation-to-motion organization of the transition, where learned relations shape state-dependent flows, field responses, and motion tendencies that move the field state forward. The resulting structure is part of the rollout itself: learned relations influence how the field moves, and the same internal quantities support both forecasting and structural readout. Across known-law interaction systems, chaotic benchmarks, real neural recordings, and ecological time series, MF-Net achieves competitive short- and medium-horizon forecasting while retaining inspectable structural readout. On the 40-dimensional Lorenz--96 testbed, MF-Net achieves an eight-step $R^2$ of $0.798\pm0.018$; across five seeds, its learned relation matrix recovers the local coupling support with a local/nonlocal strength ratio of $19.80\pm1.00$ and Precision@$K$ of $1.000\pm0.000$. MF-Net provides a structure-readable dynamical modeling framework in which learned relations are trained through forward evolution and, on real data, interpreted as functional predictive couplings under appropriate observational limits.

Realizing the vision of 6G connected robotics requires reconciling high-performance collaborative control with the rigid spectral limitations of physical wireless channels. In realistic collaborative sensing scenarios, spectral resources are quantized into finite physical resource blocks or orthogonal subcarriers, rendering simultaneous transmission by all agents infeasible. To address this, we propose Multi-Agent Semantic K-Scheduling (MASK), a control architecture designed to sustain robust, risk-aware coordination under strict instantaneous bandwidth caps. We introduce Arbiter-Assisted Semantic Information Gating (A-SIG), a lightweight coordination mechanism that enforces hard access constraints by scheduling only the top-K agents based on locally computed semantic importance scores. By aggregating these prioritized observations into a compact latent state, a self-supervised global encoder enables a distributional policy to mitigate tail risks despite data sparsity. We evaluate MASK across diverse benchmarks, demonstrating that it matches the performance of communication-unconstrained baselines even when channel access is restricted to a small fraction of the swarm size. Furthermore, the framework exhibits inherent resilience to packet erasures, validating semantic scheduling as a critical enabler for resource-constrained 6G systems.

Generative models are increasingly used to propose designs, data, and control actions for physical systems, yet many such systems are governed by hard physical constraints rather than by perceptual plausibility. Semiconductor manufacturing provides a demanding test case: generated masks, layouts, synthetic defect data, and process recipes must obey lithography, transport, reaction, and device-physics constraints, because physically invalid samples are not merely low quality but unusable. This Perspective argues that semiconductor manufacturing exposes a broader computational-science challenge, namely that generative AI for constrained physical domains must be physics-informed by construction, not corrected only through post-hoc filtering. We survey the emerging architectural toolkit, including physics-informed diffusion, PDE-constrained variational models, neural-operator priors, and conservation-law-respecting generative networks, and show how it connects to differentiable lithography, TCAD, process simulation, and autonomous experimentation. We identify four integration patterns between generative models and physics-based simulators, and we propose a research agenda centered on physics-fidelity benchmarks, differentiable simulator infrastructure, and multimodal foundation models for physical design and manufacturing. The central claim is analytical rather than rhetorical: where physical validity is the binding criterion of success, architectures that enforce it by construction should be expected to outperform those that filter for it after the fact, and the fab is the setting where this distinction is sharpest.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI). This position paper argues that integrating explicit memory is the cornerstone for advancing LLMs toward AGI. The key reason is that the underlying learning mechanism of LLMs is highly analogous to human implicit memory. However, higher-order cognitive functions necessary for AGI, such as long-term strategic planning, metacognition, and symbolic reasoning, heavily rely on hippocampal explicit memory and cannot arise solely from implicit statistical learning. Drawing on findings from neuroscience, I advance this perspective and complement it with computational requirements for artificial explicit memory systems, hoping to foster further research and lay the groundwork for explicit memory integration.

De novo protein generation has transformative potential in therapeutic design, enzyme engineering, and synthetic biology. While diffusion-based and flow matching approaches have achieved progress, they typically operate at single resolution and lack mechanisms for incorporating functional constraints. We introduce ProHiFlo, a hierarchical flow matching framework with three innovations: (1) coarse-to-fine generation that models backbone geometry before refining to all-atom coordinates, reducing computational cost while maintaining accuracy; (2) functional guidance leveraging pretrained predictors to steer generation toward desired properties without retraining; (3) adaptive SE(3)-equivariant architecture for efficient multi-scale processing. Experiments on unconditional generation, motif scaffolding, and functional design demonstrate state-ofthe-art performance while requiring 4 fewer sampling steps. On enzyme active site scaffolding, ProHiFlo achieves 58.9% success rate compared to 41.2% for RFDiffusion.

A key step in knowledge discovery is the evaluation of data mining results. In several applications, including pattern mining, graph analysis, and others, this step includes the evaluation of the statistical significance of the results, to avoid spurious discoveries due only to noise or random fluctuations in the data. While specialized procedures have been developed for some specific applications, resampling-based approaches are widely used, in particular for complex analyses where analytical results cannot be derived. However, current resampling-based approaches require the generation and analysis of thousands of resampled datasets, and are therefore impractical for large datasets or computationally intensive analyses. In this paper, we introduce FewRS, a simple and effective resampling-based approach to assess the statistical significance of data mining results with rigorous guarantees on the probability of false discoveries. Our approach can be used in every situation where resampling-based approaches are applied. FewRS builds on our derivation of a novel bound to the supremum deviation of test statistics representing the quality of data mining results. We prove that FewRS needs to generate and analyze an extremely small number of resampled datasets, leading to a highly scalable approach with wide applicability. We test our approach on common tasks such as pattern mining and network analysis. In all cases, our approach results in a reduction of up to two orders of magnitude in running time compared to the state of the art, while preserving high statistical power, enabling the statistical validation of data mining results on large-scale real-world datasets.

Supervised Contrastive Learning (SupCon) has achieved strong performance by explicitly modeling pairwise relationships among samples. However, existing SupCon-based methods suffer from two key limitations: negative-sample dilution induced by the standard InfoNCE loss, and feature-space entanglement caused by the lack of explicit constraints separating category-relevant (common) and category-irrelevant (style) features. These limitations reduce feature discriminability and generalization ability. To address these issues, we propose OSCS-SupCon (Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning), a unified framework that combines a sigmoid-based pairwise contrastive objective with explicit orthogonality constraints. Specifically, we introduce a sigmoid-based contrastive loss with two learnable parameters, temperature and bias, which adaptively modulate pairwise decision boundaries and alleviate negative-sample dilution. Furthermore, we enforce orthogonality between common and style feature subspaces via a linear projection with ReLU nonlinearity, thereby reducing feature overlap and improving disentanglement of style-irrelevant representations. Extensive experiments on six benchmark datasets demonstrate that OSCS-SupCon consistently outperforms state-of-the-art supervised contrastive learning methods across multiple backbone architectures. In particular, on the fine-grained CUB200-2011 dataset with a ResNet-18 backbone, the proposed method achieves a 3.4% improvement in classification accuracy over CS-SupCon, highlighting its robustness and generalization capability. Ablation studies further confirm the effectiveness of each component.

Existing LLM moral benchmarks usually ask which isolated moral act, value, or foundation a model prefers. This is useful but incomplete. Realistic judgments often require a model to combine several moral signals within the same option. We introduce **Moral Trolley Arena**, a two-stage blind ELO benchmark for measuring how LLMs compose moral evidence. The single-scene arena first calibrates individual moral acts from a 229-scenario corpus across five Moral Foundations Theory foundations; the composite arena then combines calibrated acts into two-act moral items over a controlled intensity grid and measures the resulting composite preferences. Across ten frontier models, composite judgments are largely predicted by component act strength, but the relation is consistently compressed rather than simply additive. Models also show non-additive intensity anchoring, bounded foundation-specific residuals after component control, and highly convergent composite preference surfaces across providers. These results suggest that moral audits should measure composition rules for moral evidence, not only rankings over isolated acts.

Vision-language reinforcement learning has recently shown strong target-present localization for camouflaged object detection (COD). Yet localization is only one side of the decision: when the agent faces an ordinary image with no camouflaged target, will it still claim that a camouflaged object exists? Standard COD training and evaluation data are positive-only, so agents optimized under this setting can acquire an over-detect bias, a task-specific form of object hallucination that standard COD evaluation leaves unmeasured. To quantify this target-absent behavior, we construct Counterfactual COD (CF-COD), a paired benchmark that removes the camouflaged target from each held-out COD evaluation image while preserving a plausible background. CF-COD evaluates whether a model detects the target on the original image and abstains on the target-absent counterfactual, summarized by Pair Accuracy (PA). We further introduce CFCamo, a paired counterfactual framework for COD with abstention. For training, CFCamo optimizes a Qwen3-VL-4B-Instruct agent with Counterfactual Sequence Policy Optimization (CSPO), which samples paired original-counterfactual rollouts and uses a Counterfactual Paired Reward (CPR) to couple original-image detection with counterfactual abstention. On CAMO-test, CFCamo improves S_alpha by +3.7 pp over the prior RL-based COD baseline; across CF-COD, it reaches 80.0-90.8% PA. Ablations show that removing counterfactual coupling reduces PA to 1.4-5.2% despite strong target-present COD scores, showing that target-present evaluation alone does not characterize detect-or-abstain behavior. Overall, these results indicate that CFCamo improves COD agents by coupling target-present detection with target-absent abstention, rather than merely strengthening target-present localization. Code and data are available at https://github.com/suhang2000/CFCamo.

How much meaning does a text carry? Shannon's theory measures uncertainty over symbols and is intentionally indifferent to meaning, while pairwise metrics such as BERTScore compare two texts rather than characterizing one. We develop a geometric framework that measures semantic content from the structure of a text's sentence embeddings. The framework has three parts. First, within a fixed embedding and baseline, six natural axioms uniquely determine a scalar measure up to scale, a frame-conditional uniqueness theorem. The resulting scalar is empirically too coarse, motivating a richer representation. Second, we propose a three-coordinate semantic profile capturing novelty (displacement from generic discourse), breadth (diversity of distinct ideas), and integration (connectedness among them), together with a discrete minimal unit (the semantic quantum) whose resolution is fixed by a clustering threshold $τ$. Third, we prove a no-go theorem: no scalar summary of the profile can simultaneously satisfy analytic stability under paraphrase and concatenation, ordinal robustness across text scales, and cross-representation comparability. We exhibit two practical scalars, $S_{\mathrm{minmax}}$ and $S_{\mathrm{rank}}$, each occupying a distinct corner of this trade-off triangle. Validation across 23 synthetic categories, 5 Project Gutenberg novels, and 3 embedding models confirms the trade-off. The recommended rank-normalized configuration passes 25 of 28 ordinal checks as point estimates (21 of 28 after Benjamini-Hochberg correction), outperforming seven baselines including unigram entropy and a BERTScore-based novelty signal. A separate variational result connects the breadth coordinate to the log-determinant of a determinantal point process (Spearman $ρ= 0.985$ over 507 Gutenberg chapters), giving an optimization-theoretic foundation for breadth.

We take a Gromov-Wasserstein perspective on Vision-Language-Action (VLA) learning, where the goal is to make the relational geometry of action representations compatible with the semantic geometry of VL embeddings. However, this alignment is non-trivial due to the mathematical heterogeneity between the domains: the semantic space of vision-language is topologically linear and isotropic, whereas the physical manifold of robotic action is non-Euclidean and anisotropic. Their disjoint metric structures render direct regression ill-posed. To resolve this incompatibility, we introduce LAST (Lie-algebraic Action Space Tokenizer), which reconstructs the action space to establish local metric compatibility with the VL modality via a two-stage transformation: (1) Global Topological Linearization: linearizing the action manifold via Lie-algebraic mapping, converting trajectories into a fixed-length, physically additive representation. (2) Local Metric Discretization: hierarchically discretizing the representation into schemas and whitened residuals, yielding approximately isotropic local charts that are statistically aligned with the semantic metric. By resolving the structural mismatch at both global and local levels, LAST enables VLA models with superior convergence and generalizability.

Forecasting human life outcomes is important to gain insights into how individuals attain long and healthy lives. Conventional statistical approaches yield limited accuracy, potentially due to discarding the sequential structure of the life course. Modern methods such as transformer architectures require large scale training data that most longitudinal panel studies lack. Here we introduce LifeSentence, a model for life-course reasoning that bridges large language models with longitudinal panel data. By representing each life event as a structured natural-language record and instruction-tuning a pretrained 24-billion-parameter language model across an 18-task evaluation taxonomy spanning prediction, robustness and reasoning, LifeSentence supplements panel data with distributional knowledge already encoded during pretraining. Trained on approximately 65,000 individuals from the German Socio-Economic Panel - roughly 45 times fewer than prior transformer-based approaches - LifeSentence outperforms classical and deep learning baselines across all task families, achieving a threefold improvement in joint event-and-timing prediction from best baselines and 91.2% Kendall's tau when reconstructing chronological order from timestamp-stripped event sets. Without explicit supervision, the model recovers documented patterns of social stratification, including the education premium, the gender wage gap and the motherhood penalty, from discrete event sequences alone. A natural-language interface further enables qualitatively new research queries, such as connecting an early-life history to a specified late-life endpoint, establishing LifeSentence as both a predictive tool and a probe for counterfactual exploration of human biographies.

Audio language models (ALMs) are increasingly used for speech-based understanding, yet their ability to perform semantic reasoning beyond transcription, Text-to-Audio Retrieval, Captioning, and Question-Answering accuracy remains insufficiently benchmarked. In particular, the effects of accent variation, domain shift, and semantic over-inference on audio reasoning are poorly understood. We evaluate audio language models across five semantic and paralinguistic reasoning tasks: entailment, consistency, plausibility, accent drift, and accent restraint. Collectively, these tasks assess a model's ability to reason over spoken audio as the primary evidence source, including whether a textual hypothesis can be inferred, contradicted, or left undetermined by the audio, whether statements align or conflict with spoken content, whether claims are plausible given the discourse, and whether model predictions remain stable or appropriately constrained across accent variation. These findings highlight critical limitations in current audio reasoning evaluations and hope to provide guidance for more robust and equitable ALM design and assessment

We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions

Standard Retrieval-Augmented Generation (RAG) pipelines route every query through retrieval and generation unconditionally, incurring unnecessary computation and propagating low-quality context to the generator. We introduce EverydayGPT, a lightweight conversational QA system built around a Confidence-Gated Routing (CGR) mechanism that formalises the routing decision as a joint policy over retrieval distance and extraction adequacy. The backbone is a 205M-parameter GPT trained from scratch on 10B tokens of FineWeb-Edu. CGR avoids invoking the costly GPT pathway (~5.9s) for 85 percent of queries by resolving them via fast RAG extraction (~45 ms), yielding over 120x latency reduction on the majority of queries while maintaining answer quality. On a 500-question in-domain benchmark, the system achieves F1 = 0.226 +/- 0.004 compared to 0.171 for GPT-only and 0.210 for unconditional RAG. Gains over strong baselines are modest but consistent, while efficiency improvements are substantial (6.3x mean latency reduction). A structured grounding audit finds no unsupported claims in the sampled set, with explicit scope limitations. We position this work as a study of routing strategies under resource constraints rather than a claim of state-of-the-art performance.

The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some settings, increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident, assigning high confidence to incorrect answers. We call this phenomenon Calibration Drift Under Reasoning (CDUR) and study it both theoretically and empirically. We define reasoning budget B and analyze conditions under which Expected Calibration Error ECE(B) follows a non-monotonic pattern: it first decreases as reasoning corrects errors, then increases as longer reasoning produces internally consistent but incorrect explanations. We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior. We evaluate Llama-3.1-8B and Llama-3.3-70B on 47 reasoning-trap questions across four reasoning budgets and three seeds (1,368 API calls; 574 valid responses). The 8B model shows non-monotonic calibration behavior, while results for the 70B model are limited to baseline evaluation and are inconclusive for budget-dependent effects. We introduce CABStop, a calibration-aware stopping rule that halts reasoning when confidence diverges from an auxiliary accuracy estimate. These results suggest that increasing reasoning depth does not always improve reliability and should be monitored carefully.

Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts. We introduce Text to Multimodal Model (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment. To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics. Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.

Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Optimization (GRPO) can improve multimodal reasoning, but most approaches rely on sparse outcome-only rewards. As a result, they struggle to tell whether an incorrect answer comes from a small mistake late in the reasoning or from an unhelpful trajectory from the start. A common solution is to train a process reward model (PRM) for step-level supervision, but this typically requires large-scale high-quality chain-of-thought annotations and additional training cost. We propose ProcessThinker, a practical post-training pipeline that provides step-level process rewards without training an explicit PRM. ProcessThinker first rewrites reasoning traces into a step-tagged format for cold-start supervised fine-tuning, then applies GRPO with a standard format reward and our rollout-based process reward. Concretely, for each intermediate step, we sample multiple continuations from that step and use the empirical success rate (final-answer verification) as the step reward. This gives dense credit assignment and encourages reasoning steps that more reliably support a correct conclusion, helping reduce inconsistent or self-contradictory progress across steps -- a key issue in logical reasoning. Across four challenging video benchmarks (Video-MMMU, MMVU, VideoMathQA, and LongVideoBench), ProcessThinker consistently improves over the baseline model Qwen3-VL-8B-Instruct

Biomedical findings often seem to conflict across studies, but many of these differences are context-dependent rather than true contradictions. Variations in cohort, geography, assay protocol, disease subtype, and clinical setting can make both claims locally valid. Existing NLI and scientific claim-verification benchmarks reduce such cases to entailment, contradiction, or neutral, failing to capture the contextual structure behind divergence. To address this, we introduce BioDivergence, an evaluation framework with a six-class conflict taxonomy, a 13-axis divergence ontology, and four structured outputs per claim pair: conflict type, divergence axes, dominant confounder, and reconciliation explanation. We release BioDivergence-Silver-v1.0, an article-disjoint silver benchmark of 11,865 claim pairs across five biomedical domains, alongside a legacy deduplicated variant for comparison. Results show notable ranking differences between the two variants, with the fine-tuned reference model dropping about 12 points under the article-disjoint setting, while Mistral-7B-Instruct-v0.3 achieves 0.5523 accuracy and 0.3894 contextual-F1 on the 842-example primary test set. BioDivergence offers a more faithful way to distinguish contextual divergence from direct contradiction and to separate article-level memorization from genuine task learning.

We present SemantiClean, a modular framework for extracting structured semantic signals from e-commerce session data and driving pluggable inference targets including purchase intent, customer segmentation, and product affinity through a shared element library. Unlike conventional end-to-end predictors that optimise solely for accuracy, SemantiClean prioritises auditability, structural governance, and sigma=0 reproducibility, explicitly trading marginal predictive gains for element-level transparency and defensible decision trails. Built upon the Online Shoppers Purchasing Intention (OSPI) dataset, the framework organises twenty-four behavioural elements into a four-layer architecture (Functional, Interaction, Systemic, Contextual) and enforces signal quality through three anti-inflation mechanisms: RedundancyGroup contribution caps, TieredPenaltyCalculator bias penalties, and AdaptiveConstraintMode cold-start protection.This report introduces the LLM-Integrated Semantic Inference Engine, a fully implemented two-phase LLM-driven inference architecture that leverages complete element metadata at inference time. All quantitative results reported herein are produced by this engine. Deterministic engine outputs remain fully reproducible (sigma=0); LLM-dependent results (E8, E10) are subject to controlled output variability under fixed provider/model/temperature settings. The gender inference target remains non-functional in the current implementation and is excluded from all quantitative results.

Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization. Recent work attributes this issue to pathological gradient scaling and proposes Dynamic Fine-Tuning (DFT) to correct it at the token level. However, DFT assumes all demonstrations are equally suitable learning targets, an assumption violated by the strong heterogeneity of large-scale instruction data, where demonstration-policy mismatch induces high-variance updates at the sample level. We introduce Compatibility-Aware Dynamic Fine-Tuning (CADFT), a principled extension of DFT that controls sample-level optimization variance. CADFT derives a dynamic, policy-dependent compatibility signal from model likelihoods to modulate supervised updates, suppressing high-variance gradients from incompatible demonstrations. We further propose a delayed, low-frequency compatibility-guided rewriting strategy to transform persistently incompatible demonstrations into learnable targets. We show that CADFT can be interpreted as a variance-controlled estimator that generalizes token-level stabilization in DFT to the sample level. Extensive experiments demonstrate improved stability, generalization, and cold-start reinforcement learning initialization, while remaining fully supervised and independent of explicit reward modeling.

Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements. We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct. We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either. The direction accordingly reduces agreement with factually correct statements (e.g. that the Earth is round) as well as sycophantic ones. All other static properties of the two activation groups are matched, suggesting the behavioural dissociation arises from generation dynamics or from finer-grained structure that residual-stream analysis cannot resolve. The pattern illustrates a general gap: representations that are readable from activations may not be writable through them.

Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document formats and the limitations of traditional rule-based methods. This study benchmarks state-of-the-art Large Language Models (LLMs) for automated SDS data extraction, comparing text-based and multimodal processing pipelines. We systematically evaluate four models: Gemini 1.5 Pro, GPT-4o, Claude 3.7 Sonnet, and Llama 3.1-70B, across three prompting strategies: zero-shot, few-shot, and chain-of-thought. The evaluation framework assessed accuracy, latency, and cost across more than 50,000 extracted data fields. Results show that text-based extraction consistently outperforms multimodal processing across all metrics. Gemini 1.5 Pro combined with a Chain-of-Thought prompt achieved the highest accuracy (84%), outperforming GPT-4o (81%) and Claude 3.7 Sonnet (79%). However, no model surpassed the 90% accuracy threshold commonly required for reliable real-world deployment. These findings indicate that general-purpose LLMs are not yet robust enough for unsupervised industrial use, though performance suggests strong potential with task-specific fine-tuning. Future research should focus on domain-adapted training, model calibration, and the integration of Human-in-the-Loop verification to ensure safety-critical reliability.