When drug discovery fails: scientists share their frustrations with the process
In clinical trials, there are many times (and ways) a therapeutic can come up short. In clinical trials, there are many times (and ways) a therapeutic can come up short.
Academic Intelligence · Curated Daily
AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。
In clinical trials, there are many times (and ways) a therapeutic can come up short. In clinical trials, there are many times (and ways) a therapeutic can come up short.
The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations. In particular, it suggests that there is no benefit in enhancing the signal or encoding it before addressing a classification problem. This assertion can be proven to be true for the case of the optimal Bayes classifier. However, in practice, it is common to perform "low-level" tasks before "high-level" downstream tasks despite the overwhelming capabilities of modern deep neural networks. In this paper, we aim to understand when and why low-level processing can be beneficial for classification. We present a comprehensive theoretical study of a binary classification setup, where we consider a classifier that is tightly connected to the optimal Bayes classifier and converges to it as the number of training samples increases. We prove that for any finite number of training samples, there exists a pre-classification processing that improves the classification accuracy. We also explore the effect of class separation, training set size, and class balance on the relative gain from this procedure. We support our theory with an empirical investigation of the theoretical setup. Finally, we conduct an empirical study where we investigate the effect of denoising and encoding on the performance of practical deep classifiers on benchmark datasets. Specifically, we vary the size and class distribution of the training set, and the noise level, and demonstrate trends that are consistent with our theoretical results.
Pretraining large language models (LLMs) typically requires centralized clusters with thousands of high-memory GPUs (e.g., H100/A100). Recent decentralized training methods reduce communication overhead by employing federated optimization; however, they still need to train the entire model on each node, remaining constrained by GPU memory limitations. In this work, we propose SParse Expert Synchronization (SPES), a memory-efficient decentralized framework for pretraining mixture-of-experts (MoE) LLMs. SPES trains only a subset of experts per node, substantially lowering the memory footprint. Each node updates its local experts and periodically synchronizes with other nodes, eliminating full-parameter transmission while ensuring efficient knowledge sharing. To mitigate limited per-expert data utilization under sparse expert updates, we introduce an expert-merging warm-up strategy, where experts exchange knowledge early in training, to rapidly establish foundational capabilities. With SPES, we train a 2B-parameter MoE LLM using 16 standalone 48GB GPUs over internet connections, which achieves competitive performance with centrally trained LLMs under similar computational budgets. We further demonstrate scalability by training a 7B model from scratch and a 9B model upcycled from a dense checkpoint, both of which match prior centralized baselines. Our code is available at https://github.com/zjr2000/SPES.
We introduce MM++ (Multilayer Mahalanobis++), a fully unsupervised, strictly post-hoc, and scale-invariant framework for Out-of-Distribution (OOD) detection. To address the trade-off between scale invariance and hierarchical expressivity, MM++ constructs a principled joint feature space. It first identifies discriminative intermediate layers by measuring entropy density drops, which mark the boundaries of sharp semantic compression. By fusing these selected layers with the terminal representation, the framework captures latent cross-layer correlations while mitigating early-layer noise. Crucially, a Ledoit-Wolf regularized tied covariance matrix stabilizes this unified space, enabling reliable distance estimation. Requiring no auxiliary OOD data, classifier fine-tuning, or architectural modifications, MM++ delivers robust performance across distinct architectures for both near- and far-OOD detection.
Objective: We examined the link between cohabitation with a partner and nighttime smartphone use through the social control of health behavior theory. Background: Nighttime smartphone use is a behavioral risk factor for sleep problems. While previous research has predominantly focused on individual-level risks of sleep disturbances, the role of social context remains underexplored. Theoretical frameworks, specifically the Social Control of Health Behavior, suggest that social relationships regulate health-related behaviors; however, it is unclear how far this regulation extends to modern digital behaviors among couples. Method: We analyzed survey data from three waves of the SmartSleep Study (2018, 2020, and 2023; total N = 25,028), including a longitudinal follow-up subset (N = 1,003). We tested multivariate associations between living with a partner, changes in cohabitation status and frequent nighttime smartphone use by fitting generalized linear mixed-effects models. Additionally, we mapped the complex interplay between indicators of social integration, social support, smartphone use, and sleep quality using hierarchical clustering of non-linear correlations. Results: Cohabiting participants had lower odds of frequent nighttime smartphone use compared to those living alone (OR = 0.66; 95% CI: 0.61, 0.72). This lower risk was driven primarily by cohabitation with a partner (OR = 0.49; 95% CI: 0.36, 0.66). Longitudinal analysis supported these findings, showing that sustained cohabitation was associated with less frequent nighttime use (OR = 0.56; 95% CI: 0.38, 0.82). Clustering analysis revealed that indicators of social integration and support clustered with favorable sleep quality. Conclusion: Our findings suggest that the health-protective effects of cohabitation with a partner extend to digital behaviors. Consistent with social control of health behavior theory, the presence of a partner appears to reduce frequent nighttime smartphone use, highlighting the critical importance of considering social context when addressing digital health hygiene and promoting sleep.
Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent reasoning remains difficult because outcome supervision provides weak learning signals and leaves latent trajectories prone to semantic drift. In this work, we analyze Latent CoT from an information-theoretic perspective and identify this failure as a dual collapse: gradient attenuation along the optimization path and representational drift in the latent space. We further decompose process supervision into two complementary dimensions: Trajectory Supervision, which injects dense stepwise reasoning signals, and Space Supervision, which preserves the semantic structure of the latent manifold. Our analysis shows that rigid geometric compression can collapse the reasoning space, whereas generative reconstruction provides a more flexible semantic anchor that better preserves information capacity. To measure these effects, we introduce the Unified Latent Probe (ULP), which quantifies the mutual information between latent trajectories and explicit reasoning steps. Experiments reveal a clear Information-Performance Binding: reasoning accuracy depends on the information fidelity preserved in the latent chain. These findings provide a principled framework for latent reasoning supervision and suggest shifting from geometric imitation toward mutual information maximization. Our code is available at \href{https://github.com/EIT-NLP/Supervision-in-Latent-CoT}{this repository}.
arXiv:2606.20238v1 Announce Type: new Abstract: Estimating nonlinear properties of quantum states is a central task in quantum information science. Multivariate traces, $\mathrm{tr}(\rho_1 \cdots \rho_K)$, and nonlinear observables such as $\mathrm{tr}(\rho^K)$, for integer $K$, can be accessed through collective measurements on multiple state copies, but standard protocols based on swap tests require coherent operations on the full Hilbert space and become experimentally unfeasible for large systems. In this work, we introduce a framework for multi-copy measurements based on random projections onto lower-dimensional subspaces prior to the collective measurement, which is then performed only on the reduced Hilbert space. This procedure yields a tunable tradeoff between coherent quantum resources and statistical sampling overhead, allowing the amount of coherent processing to be matched to the capabilities of the underlying hardware. We derive explicit formulas relating the Haar-averaged projected moments to multivariate traces of the original states and analyze the sampling overhead induced by the projection procedure. Specifically, after compressing an $n$-qubit state to a reduced $q$-qubit subspace, estimating $\mathrm{tr}(\rho^K)$ requires approximately $O(2^{(n-q)(K-1)})$ copies of $\rho$, with each qubit projected out increasing the sampling cost by a factor of $2^{K-1}$. Our results establish how coherent multi-copy operations can be traded for additional state copies, enabling multi-copy quantum protocols to be optimized for the available hardware resources.
arXiv:2605.20443v3 Announce Type: replace Abstract: The recent posting arXiv:2605.02621 [14], commenting on the article rspa.2025.0413 [7], argues that the proof of Lemma 3.1 in [7] is missing the spatial derivative of the density, which would lead to a Bohm-like quantum potential. This technical note shows why the propagated density is independent of space in the Feynman propagator construction of Lemma 3.1. This is done by extending the proof of Lemma 3.1 explicitly with Bohm-like quantum potential terms along the stationary action paths, and then showing that these terms are exactly zero. In [7], this property can also be verified directly on most examples (double slit, Aharonov-Bohm, potential well, harmonic oscillator, tunneling, EPR, QED), as well as in the derivations of the Pauli, Dirac, and Maxwell equations. For more general nonlinear actions, a time rescaling may be required to guarantee this space independence along stationary paths. In the hydrogen atom example, this time rescaling can be computed in closed form. In contrast to the general wave of the Madelung solution [9] Lemma 3.1 of [7] is defined first for a propagator, and a general wave is then constructed in a second step. Recall that a propagator is a specific quantum wave, which is initialized at $t=0$ with a Dirac impulse at a given initial position or momentum. In turn, a general wave is constructed in a second step by superposing a distribution of initial conditions using the propagator. This key difference is why the Bohm-like quantum potential terms disappear in the construction [7] (specifically, in the first step) while the Bohm potential in the Madelung analysis does not. This fundamental difference is also consistent with the fact that the wave construction in [7] extends naturally to relativistic contexts, while Bohmian non-locality notoriously prevents such extensions. Keywords - Response to arXiv:2605.02621, in relation to rspa.2025.0413
Background Despite widespread vaccination, pertussis remains a poorly controlled disease globally and results in substantial annual morbidity and mortality, particularly in young children. Controlled human infection models (CHIMs) using the causative agent Bordetella pertussis are promising systems to enable the study of pertussis disease pathogenesis and immunology and to rapidly assess vaccines and therapeutics. While a pertussis CHIM that produces asymptomatic infection has been established in Europe, the development of a CHIM that leads to symptomatic illness would be advantageous for evaluating vaccine efficacy against both infection and disease. Methods Healthy participants 18-40 years of age were inoculated intranasally with one of eight doses (ranging from 104 to 108 colony forming units (CFU)) of the pertactin-producing B. pertussis isolate D420 at the challenge facility within the Canadian Center for Vaccinology (Nova Scotia, Canada). The study occurred in two stages. In stage one, the B. pertussis dose was escalated in cohort groups of five to six participants until reaching an endpoint where 70-90% of participants exhibited mild (non-severe, Grade 1 or 2) symptomatic infection, defined as the Human Infectious Dose 70-90 (HID70-90). In stage two, additional challenges were conducted for doses below, at, and above the identified HID70-90 to characterize the emerging pertussis model. For all challenge doses, participants were closely monitored during an inpatient stay of up to 24 days and post-discharge for laboratory-confirmed infection, pertussis symptoms, safety, and IgG antibody responses to four B. pertussis antigens including pertussis toxin, filamentous hemagglutinin, fimbriae, and pertactin. All participants received a five-day course of azithromycin, where timing of initiation depended on B. pertussis testing and symptoms. The study was conducted between July 4, 2022 and March 19, 2025. Findings Seventy-five participants were inoculated with one of the eight B. pertussis D420 challenge doses and completed the inpatient stay. From the stage-one dose escalation, we found that 107 CFU of B. pertussis D420 was the lowest dose that achieved the HID70-90, where 9 of 12 participants (75.0%) exhibited mild symptomatic infection. Following stage-two challenges, 16 of 22 total participants at 107 CFU (72.7%) developed mild symptomatic infection, thus verifying the HID70-90. The symptomatic infection rate below the HID70-90 at 5x106 CFU of D420 was 20.0% and above the HID70-90 at 5x107 and 108 CFU were 58.3% and 55.6%, respectively. Symptoms with elevated frequency for symptomatic infection (relative to background symptoms in non-infected) included nasal congestion, runny nose, fatigue, malaise, and cough. At the HID70-90, 50% of symptomatic infections included cough. Serological analyses of the four highest (stage-two) challenge doses (5x106, 107, 5x107, 108 CFU) revealed that antibody titres increased over time post-challenge. Seroconversion for at least one of the four studied antibodies was nearly twice as common for symptomatic (70.0%) than asymptomatic (35.7%) infection and was absent (0%) for non-infected. All infections were cleared following azithromycin treatment (100%) and there were no study-related serious adverse events. Interpretation A safe and reproducible symptomatic pertussis CHIM was achieved, providing a model for research on pertussis disease pathogenesis and immunology and for assessing vaccines and therapeutics. (Clinicaltrials.gov, NCT05136599).
Background. Self-exciting (Hawkes) point processes are a natural model for the temporal clustering of human physical activity (PA) recorded by accelerometers, yet they have seldom been used in this setting—in part because the usual maximum-likelihood fitting is challenging due to potential estimation bias and convergence failures on these data. A moment-based alternative—estimating the Hawkes branching ratio from the dispersion index, the variance-to-mean ratio of event counts—is kernel-independent and computationally trivial, but it has not been evaluated for accelerometry or adapted to the intensity-marked recordings accelerometers provide. Methods. Treating each minute above a sedentary threshold as an event, we estimated the Hawkes branching ratio $n$ by maximum likelihood and, as a kernel-independent and far cheaper alternative, from the dispersion index. We compared four dispersion-based estimators—event-count-based, intensity-mark-weighted using the mark-moment ratio, and time-of-day (TOD) adjusted variants of each—against the marked and unmarked maximum-likelihood estimates. Estimators were evaluated for mutual agreement, goodness of fit, and finite-window results in two National Health and Nutrition Examination Survey (NHANES) accelerometry cohorts (hip-worn, $n=2{,}560$; wrist-worn, $n=3{,}132$). We related the resulting temporal clustering measures to all-cause mortality using survey-weighted Cox models, adjusting for PA frequency, Peak30 (the average of the 30 highest PA values), and demographic covariates. Results. Event-count-based dispersion estimates agreed strongly with maximum-likelihood branching ratios ($rapprox0.74$ in both cohorts); the intensity-marked variant incorporating PA intensity variability agreed less well. Marked and unmarked Hawkes models yielded similar excitation and decay parameters, suggesting PA intensity added little clustering information beyond event timing. In the survival analysis, temporal clustering was associated with all-cause mortality independently of PA frequency and Peak30; the direction of association differed between the hip- and wrist-worn cohorts. Conclusions. A scalable dispersion-index estimator recovers the Hawkes branching ratio and matches maximum-likelihood estimates without requiring kernel specification or iterative optimization. It offers a practical tool for quantifying temporal clustering in accelerometry, enabling decomposition of temporal PA patterns into its exogenous initiation and endogenous persistence. Such temporal patterns carry health-relevant information beyond PA intensity and volume. Keywords: dispersion index; Hawkes process; branching ratio; temporal clustering; point process estimation; accelerometry; mortality
Seroprevalence surveys reveal the extent of humoral immunity against pathogens such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and under some circumstances represent cumulative incidence of prior infection. However, antibody waning - or seroreversion - biases these estimates by reducing assay sensitivity in a time-varying manner. Because assay sensitivity decays over time, naively using serosurveys can substantially bias estimates of SARS-CoV-2 cumulative incidence and fatality rates. The Bayesian assay-specific, time-varying sensitivity adjustment developed in this paper can reliably correct for this bias and account for the delay between infection and serosurvey. In seroprevalence studies conducted in the United States in 2020, adjusting for time-varying sensitivity increased cumulative incidence by up to 1.4-fold, with an adjustment of 1.08 for a national study. Our estimates contrast with a previously published 2-fold adjustment that did not account for assay design. This suggests that previous analyses overestimated cumulative incidence by applying seroreversion corrections that did not account for assay-specific effects, or underestimated cumulative incidence by not applying seroreversion corrections. These biases imply fatality rate underestimation and overestimation, respectively. Our model provides a framework for design-specific time-varying sensitivity corrections in seroprevalence surveys for other pathogens.
arXiv:2601.02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.g., sycophancy, hallucination) in Large Language Models (LLMs) is critical for AI safety, yet remains a persistent challenge. Existing solutions face a dilemma: manual prompt engineering is intuitive but unscalable and imprecise, while automatic optimization methods are effective but operate as "black boxes" with no interpretable connection to model internals. We propose a novel framework that adapts gradient ascent to LLMs, enabling targeted prompt discovery. In specific, we propose two methods, RESGA and SAEGA, that both optimize randomly initialized prompts to achieve better aligned representation with an identified persona direction. We introduce fluent gradient ascent to control the fluency of discovered persona steering prompts. We demonstrate RESGA and SAEGA's effectiveness across Llama 3.1, Qwen 2.5, and Gemma 3 for steering three different personas, sycophancy, hallucination, and myopic reward. Crucially, on sycophancy, our automatically discovered prompts achieve significant improvement (49.90% compared with 79.24%). By grounding prompt discovery in mechanistically meaningful features, our method offers a new paradigm for controllable and interpretable behavior modification. We release our scripts for RESGA and SAEGA in this github repo: https://github.com/HarshSaini10/RESGA_SAEGA.
arXiv:2601.17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data. The inference interface thus acts as a side channel for privacy leakage. We introduce Robust Privacy (RP), an inference-stage privacy notion inspired by certified robustness: if a model's prediction is provably invariant within a radius-R neighborhood around an input x with confidence at least $1-\alpha$, then x enjoys $(R,\alpha)$-Robust Privacy, under which we prove that any adversary observing the released prediction has at most $\alpha/2$ advantage in distinguishing x from any input within distance R of x. Building on RP, we formalize Robust Attribute Privacy (RAP), an attribute-level privacy notion that characterizes the set of sensitive-attribute values that remain compatible with a released prediction. On a classification task, RP increases the median length of the RAP-compatible inference interval from 23.50 to 29.96, reducing attribute-inference precision. Model inversion attacks, often treated as a training-stage threat, in fact rely on fine-grained signals leaked through the inference interface; RP masks these signals at the inference stage, reducing attack success rate (ASR) from 73% to 4% on a black-box inversion attack. This direct targeting of the leakage channel enables RP to dominate DP-SGD and randomized response in the privacy-utility tradeoff space: RP retains 98.4% accuracy at 21% ASR, whereas DP-SGD must drop accuracy to 61.7% to reach a comparable ASR. Across both experiments, increasing the smoothing sample size N strengthens privacy and improves utility together. Finally, we examine model distillation as a scope boundary and show that RP mitigates attribute-level and instance-level inference-stage privacy leakage, but not function-level extraction through model distillation.
Generating explicit 3D city assets from a single satellite image is important for digital twins, urban simulation, and geospatial intelligence. Unlike satellite-to-street-view synthesis, the task requires a reusable textured mesh with plausible geometry and controllable appearance rather than a 3D proxy optimized only for rendering a small set of images or videos. The ICCV Sat2City framework made a first step by conditioning cascaded sparse-voxel latent diffusion on satellite-derived height maps, but its appearance was random, its training data were synthetic, and its task-specific VAE did not scale well to noisy real-world reconstructions. We present Sat2City v2, a journal extension that adapts a pretrained native structured-latent 3D foundation model to weakly aligned satellite images and textured meshes. We build a real-world dataset with 16,241 satellite-mesh pairs across 24 regions in 9 cities. Instead of learning a 3D representation from noisy city meshes, Sat2City v2 encodes each mesh into a pretrained native 3D latent space, fine-tunes a satellite-conditioned geometry flow, and uses the decoded shape to anchor satellite-conditioned texturing. This retains Sat2City's geometry-to-appearance cascade while enabling appearance-controllable generation from the satellite input. Experiments on metric-scale DSM reconstruction and generative city-asset benchmarks for geometry and appearance show that Sat2City v2 achieves the best overall performance among evaluated baselines. Overall, Sat2City v2 advances satellite-to-city generation from rendering-oriented 3D proxies to explicit textured mesh assets, supported by, to the best of our knowledge, the first documented satellite-mesh paired dataset collected from matched geographic crops for this asset-level task. Project page: https://ai4city-hkust.github.io/Sat2City-v2/
arXiv:2606.23800v1 Announce Type: new Abstract: Matchgate circuits realize free-fermion dynamics: they are efficiently classically simulable, yet cannot on their own generate the generic randomness required for universal computation or unitary design formation. We study a controlled route beyond this integrable limit by doping matchgate circuits with non-Gaussian gates-physically, the injection of fermionic interactions into an otherwise free system. Using the matchgate commutant framework, we obtain analytic control over unitary $2$-design formation. For globally scrambled dynamics, the design problem maps exactly onto a classical birth-death Markov chain with an Ornstein-Uhlenbeck continuum limit, recasting the emergence of quantum randomness in terms of spectral gaps and mixing times and yielding rigorous bounds on the number of non-Gaussian gates needed for approximate $2$-designs. These bounds hold for a broad class of parity-preserving non-Gaussian gates, independently of microscopic details, with numerics indicating that the same mechanism governs higher-order designs. Used as local building blocks in a glued-circuit architecture, they yield approximate parity-preserving $2$-designs in polylogarithmic depth with a sparse non-Gaussian gate count, with implications for Page-like entanglement growth and fermionic classical-shadow protocols. Finally, locality reshapes this picture: in local brickwork dynamics, design formation is diffusion-limited and far slower. Our results establish doped matchgate circuits as a controlled, analytically tractable route from free fermions to interaction-generated quantum designs.
arXiv:2606.23743v1 Announce Type: cross Abstract: Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration methods have been proposed, a central challenge is that the most effective acceleration strategy is highly instance-specific: a recipe that works well for one combination of model, hardware, and inference configuration often does not transfer to another. Different models vary in architecture, numerical sensitivity, and attention concentration patterns. Inference settings differ in spatial and temporal resolution and video duration, while hardware platforms differ in memory hierarchy, supported numerical formats, and kernel throughput. These factors create a large tuning space, making manual performance engineering costly. We present Sol Video Inference Engine, an agentic, native, training-free acceleration framework for video diffusion models. It organizes five broadly applicable techniques, cache, sparse attention, token pruning, quantization, and kernel fusion, into an agentic acceleration stack for instance-specific optimization. For a concrete deployment target defined by a model, hardware platform, and serving configuration, parallel skill agents optimize the implementation of each technique, an agent integrator composes them into a global acceleration stack, and a human validator provides feedback on generation quality. We instantiate this workflow on three video models with different sizes and architectures: 64B Cosmos3-Super, 22B LTX-2.3, and 2B SANA-Video. With little human effort, the full stack achieves more than 2x end-to-end acceleration while maintaining near-lossless VBench quality, demonstrating the effectiveness of the agent framework for video diffusion acceleration.
arXiv:2603.13751v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have achieved notable success in modeling dynamical systems governed by partial differential equations (PDEs). To avoid computationally expensive retraining under new physical conditions, parameterized PINNs (P$^2$INNs) commonly adapt pre-trained operators using singular value decomposition (SVD) for out-of-distribution (OOD) regimes. However, SVD-based fine-tuning often suffers from rigid subspace locking and truncation of important high-frequency spectral modes, limiting its ability to capture complex physical transitions. While parameter-efficient fine-tuning (PEFT) methods appear to be promising alternatives, applying conventional adapters such as LoRA to P$^2$INNs introduces a severe Pareto trade-off, as additive updates increase parameter overhead and disrupt the structured physical manifolds inherent in operator representations. To address these limitations, we propose Manifold-Orthogonal Dual-spectrum Extrapolation (MODE), a lightweight micro-architecture designed for physics operator adaptation. MODE decomposes physical evolution into complementary mechanisms including principal-spectrum dense mixing that enables cross-modal energy transfer within frozen orthogonal bases, residual-spectrum awakening that activates high-frequency spectral components through a single trainable scalar, and affine Galilean unlocking that explicitly isolates spatial translation dynamics. Experiments on challenging PDE benchmarks including the 1D Convection–Diffusion–Reaction equation and the 2D Helmholtz equation demonstrate that MODE achieves strong out-of-distribution generalization while preserving the minimal parameter complexity of native SVD and outperforming existing PEFT-based baselines.
arXiv:2606.12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judging a method, its feasibility, and its empirical promise. We therefore study a cleaner upstream object: the research question (RQ). RQ generation is a prerequisite for scientific ideation, and RQs can be compared against questions pursued in real papers. We introduce RQ-Bench, a benchmark built from recent arXiv papers. For each paper, we reconstruct author-anchored RQs from its cited background, gaps, and contributions. These RQs are not the only valid questions for the same background. They are author-anchored reference points for testing novelty judgments. We evaluate model-generated RQs with standalone LLM judging, comparative LLM judging, and human expert evaluation. LLM judges consistently rate model-generated RQs as highly novel, producing a novelty mirage; in comparative evaluations, this preference becomes even stronger. Domain experts, however, reach the opposite conclusion and prefer the author-anchored reference questions. We further find that many generated RQs are narrow or source-bound, a dimension that LLM judges often miss unless explicitly tested. Overall, the contradictory novelty evaluations between LLM judges and human experts raise a serious concern about the reliability of using LLMs to assess the scientific novelty of research questions.
arXiv:2602.10132v3 Announce Type: replace-cross Abstract: Development and operation of commercially viable fusion energy reactors such as tokamaks require accurate predictions of plasma dynamics from sparse, noisy, and incomplete sensors readings. The complexity of the underlying physics and the heterogeneity of experimental data pose formidable challenges for conventional numerical methods, and highlight the promise of modern data-native approaches. A major obstacle in realizing this potential is, however, the lack of curated, openly available datasets and standardized benchmarks. Existing fusion datasets are scarce, fragmented across institutions, facility-specific, and inconsistently annotated, which limits reproducibility and prevents a fair and scalable comparison of AI approaches. In this paper, we introduce TokaMark, a structured benchmark to evaluate AI models on real experimental data collected from the Mega Ampere Spherical Tokamak (MAST). TokaMark provides a comprehensive suite of tools designed to unify access to multi-modal fusion data and standardize evaluation protocols. The benchmark includes a curated list of 14 tasks spanning a range of physical mechanisms, exploiting a variety of diagnostics and covering multiple operational use cases. A baseline model is provided to facilitate transparent comparison and validation within a unified framework. By establishing a unified benchmark, TokaMark aims to accelerate progress in data-driven AI-based plasma modeling, contributing to the broader goal of achieving sustainable and stable fusion energy. The dataset, benchmark, documentation, and tooling are open-sourced under https://github.com/UKAEA-IBM-STFC-Fusion-FMs/tokamark_baseline.
Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly on models internal parametric knowledge, without explicit grounding in external normative principles. This often leads to inconsistent judgments in socially nuanced contexts, limited interpretability, and redundant reasoning across turns. To address this, we propose RoTRAG, a retrieval augmented framework that incorporates concise human written moral norms, called Rules of Thumb (RoTs), into LLM based harm assessment. For each turn, RoTRAG retrieves relevant RoTs from an external corpus and uses them as explicit normative evidence for turn level reasoning and final severity classification. To improve efficiency, we further introduce a lightweight binary routing classifier that decides whether a new turn requires retrieval grounded reasoning or can reuse existing context. Experiments on ProsocialDialog and Safety Reasoning Multi Turn Dialogue show that RoTRAG consistently improves both harm classification and severity estimation over competitive baselines, with an average relative gain of around 40% in F1 across benchmark datasets and an average relative reduction of 8.4% in distributional error, while reducing redundant computation without sacrificing performance.
arXiv:2606.23697v1 Announce Type: cross Abstract: Semantic segmentation of code written in a C-family language remains a challenging problem, due to the language's complex syntax, macro expansion, and irregular structural patterns. Existing chunking methods, such as fixed-sized windows, heuristic splitting, and syntax-based tools, often fail to capture meaningful functional units, limiting the efficacy of retrieval and other downstream LLM driven tasks. In this paper, we address the problem of chunking in C-related languages. First, we define a set of code chunk categories. Second, we train an LLM-based classifier to a) identify chunk boundaries, and b) assign each chunk a descriptive functional attribute (a category), which can be useful for downstream tasks. By leveraging the LLM's ability to capture semantic context within the code, we assume flexible chunk boundaries, allowing to adapt to the specific structure and context of each instance. Third, we introduce SemChunk-C, a family of lightweight language models for semantic chunking of C-related files (.c, .cpp, .h, .cs, etc.). These models are based on the first four Ettin encoders [1] with 17M, 32M, 68M, and 150M parameters. Despite their relatively small size, they are capable of identifying cohesive code units, such as data structures, interface blocks, and other components. Furthermore, we demonstrate the robustness of our approach on real-world code, including challenging constructs such as nested definitions and macros. We test our approach on various datasets, and show that it achieves high boundary accuracy and semantic coherence, matching or outperforming chunkers that are based on much larger code-oriented LLMs. We also validate the improved performance of the downstream tasks on a few curated benchmarks.
Linguistics olympiad problems (LOPs) are a category of self-sufficient puzzles consisting of a scaled-down corpus representative of certain linguistic phenomena, from which the solver must deduce a primitive set of rules of the language and then translate a new set of elements. The linguistics olympiads (LOs) have become a worldwide phenomenon with 43 different territories taking part in the International Linguistics Olympiad (IOL) 2025. While the typology and solving strategies of LOPs have been analysed, their scientific facet and connections to academic linguistics have yet to be explored. LOPs are directly connected to many linguistic fields, e.g., linguistic typology, linguistic relativity, and linguistics fieldwork. Recently, LOPs have become a research focus as benchmarks for large language models, thus highlighting their usefulness in computational linguistics. Nevertheless, they have not yet been integrated into mainstream linguistics research. This paper attempts to open new directions of including this particular type of puzzle in academic research by offering a structured evaluation of LOPs as linguistic data sources and proposes criteria for their responsible use in academic research. Starting from a set of over 1800 LOPs, this study critically examines the potential of LOPs as a novel corpus for linguistics research by discussing their strengths and limitations as tools, as well as the areas of linguistics into which these problems could fit. This work forms the foundation for a broader initiative aimed at bridging the gap between LOs and academic linguistics, by establishing a robust theoretical framework for LOPs.
arXiv:2606.18812v1 Announce Type: cross Abstract: Foundation models for language and vision are powered by internet-scale data, while structured domains (tabular prediction, time-series forecasting, graph learning, reinforcement learning) are not. The substitute is synthetic data, which shifts the burden from collection to prior design. Such priors already exist for many structured tasks: TabPFN and its successors solve tabular classification with a transformer pretrained on a synthetic Bayesian prior. We make two points. First, reinforcement learning is the conspicuous gap: sampling a synthetic MDP is as feasible as sampling a synthetic tabular dataset, yet no in-context RL work treats prior design as a primary objective. Second, MDPs admit a fixed-size sufficient statistic, independent of the episodes observed and tabular in shape, which makes them directly amenable to the attention-based architectures used for tabular foundation models, with a policy head replacing the supervised target. Together these define the agenda for an RL foundation model. As a proof of concept, we train one model entirely on synthetic MDPs and show that, with no task-specific tuning, it solves held-out tabular benchmarks in context, both online and offline: online, in far fewer episodes than UCB-VI and tabular Q-learning, and offline, competitively with VI-LCB.
arXiv:2509.25148v2 Announce Type: replace Abstract: Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavioral anchor but can overfit to static demonstrations, whereas RL encourages exploration but may drift from expert behavior or exploit imperfect rewards. We propose AAPA (Adversarially Anchored Preference Alignment), a plug-in framework that augments existing post-training objectives with a sentence-level adversarial anchoring signal. AAPA compares policy rollouts with offline, pre-collected expert responses using a fixed lightweight discriminator, and therefore requires neither online teacher inference nor discriminator co-training during policy optimization. The same anchoring term can be added to SFT, GRPO, and CHORD while preserving their original training pipelines. Experiments on instruction-following benchmarks show that AAPA consistently improves the corresponding base objectives across model scales. In particular, the staged AAPA configuration improves over a strong GRPO baseline by 5.77\% on \texttt{Qwen3-0.6B} and 3.75\% on \texttt{Qwen3-4B}. Further analyses on response length, log-probability distributions, and discriminator variants suggest that adversarial anchoring provides a stable semantic grounding signal for preference optimization. Code is available at \url{https://github.com/IsFaqq/AAPA}.
arXiv:2606.11963v1 Announce Type: new Abstract: Neural operators provide a powerful framework for learning solution mappings of partial differential equations directly in function space. However, many existing architectures still struggle to represent nonlinear time-dependent systems that involve multi-scale structures, long-range interactions, and stable long-time evolution. In this work, we introduce the Hierarchical Adaptive Multi-scale Neural Operator (HAMNO), a neural-operator architecture that combines local convolutional representations, global spectral operators, and hierarchical encoder-decoder processing. The central component of HAMNO is a data-dependent gating mechanism that adaptively balances local and global information at each spatial location, allowing the model to resolve fine-scale features while preserving long-range dependencies. We further develop a physics-informed extension, PI-HAMNO, based on a multi-objective loss strategy that combines data fitting with strong- and weak-form physics constraints. The strong-form term penalizes the domain-integrated squared PDE residual in physical coordinates, while the weak-form term is constructed by multiplying the governing residual by finite-element test functions and evaluating the resulting element integrals using centroid-based tetrahedral quadrature. The framework is evaluated on non-periodic Allen-Cahn (AC), Cahn-Hilliard (CH), and Swift-Hohenberg (SH) equations defined on cubic domains. Across long-horizon rollout, data-limited training, out-of-distribution initial-condition shifts, and random-seed variations, HAMNO improves predictive accuracy over standard neural-operator baselines, while PI-HAMNO further enhances stability, physical consistency, and data efficiency. The implementation is publicly available at https://github.com/MBamdad/HAMNO .