Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
medRxiv (Medicine) 2026-06-22

An integrated AI-microfluidic platform reveals the broad persistence and developmental potential of rare sperm in non-obstructive azoospermia

Non-obstructive azoospermia (NOA) represents the most severe form of male infertility, severely limiting a patient's prospects for biological fatherhood when surgical retrieval fails. However, the true biological limits of NOA remain obscured by the inherent limitations of conventional gamete recovery protocols: standard centrifugation frequently causes substantial cell loss, masking extremely rare sperm, while surgical interventions are constrained by spatial sampling biases. Here we report SpermSeek, an integrated AI-guided microfluidic platform for real-time, non-destructive isolation of single sperm directly from semen. Operating at scalable throughput (0.36 mL/h), the system achieves 98.3% detection precision and a 95.5% target encapsulation efficiency, suppressing background debris. In a 59-patient NOA cohort, SpermSeek detected morphologically identifiable sperm in 64.4% (38/59) of cases, spanning diverse genetic etiologies, including AZFb/c microdeletions, and severe histopathological phenotypes, such as Sertoli-cell-only syndrome (SCOS). Notably, among a sub-cohort of 41 patients who remained consistently sperm-negative despite prior medical or micro-TESE interventions, our platform identified gametes in 53.7% (22/41) of these cases. Comprehensive safety profiling in healthy human donors and wild-type mice confirmed that processed sperm retain high DNA integrity and epigenomic concordance (r=0.98), supporting transgenerational developmental stability in mice. Furthermore, in a 26-patient validation cohort, SpermSeek recovered rare sperm in 11 cases. Utilizing gametes from a subset (n=5), we demonstrated their capacity to support early human embryogenesis, yielding high-quality cleavage-stage embryos with confirmed genomic euploidy. This work establishes a highly sensitive framework for re-examining the biological limits of human spermatogenesis, laying the foundation to expand autologous reproductive options for patients refractory to conventional retrieval protocols.

02.
medRxiv (Medicine) 2026-06-22

T Cell Receptor repertoire analysis reveals antigenic convergence and immunotherapeutic opportunities in Prostate Cancer

Background: The T-cell receptor {beta} (TCR{beta}) repertoire reflects antigen-driven adaptive immune responses and provides insight into tumor-immune interaction. In prostate cancer (PCa), the immunosuppressive tumor microenvironment limits effective T-cell activation, and the antigenic drivers shaping intratumoral TCR repertoires remains poorly defined. This study aimed to characterize matched tumor and peripheral TCR{beta} repertoires from treatment-naive PCa patients and to identify shared clonotypes and antigenic specificities associated with disease severity. Methods: Next-generation sequencing was used to profile TCR{beta} repertoires from matched tumor biopsies and peripheral blood mononuclear cells obtained from treatment-naive PCa patients. Repertoires clonality, diversity, and was assessed using established metrics. Antigenic convergence was evaluated using GLIPH2 to identify shared CDR3{beta} motifs and predicted tumor-associated antigen (TAA) recognition, followed by functional validation using IFN-{gamma} ELISpot and T-cell expansion assays. Results: Tumor-derived TCR{beta} repertoires displayed reduced richness and increased clonality compared with peripheral blood mononuclear cells, consistent with local antigen-driven expansion. High-grade tumors demonstrated greater interpatient clonotype sharing and motif-level convergence, indicative of recognition of common TAAs. GLIPH2 analysis associated expanded clonotypes with epitopes derived from prostate-specific G-protein coupled receptor (PSGR), prostate-specific membrane antigen (PSMA), and prostate-specific antigen (PSA). Functional validation confirmed that peptide pools containing PSGR- and PSMA-derived epitopes induced IFN-{gamma} production and antigen-specific T-cell proliferation in vitro. Conclusions: These findings reveal an oligoclonal, antigen-driven intratumoral TCR{beta} landscape and identify PSGR and PSMA as immunogenic, potentially actionable targets. Integration of TCR profiling with antigen discovery pipelines may support the development of TCR-based biomarkers and precision immunotherapeutic strategies in prostate cancer.

03.
arXiv (CS.CL) 2026-06-16

The Value Axis: Language Models Encode Whether They're on the Right Track

We investigate whether language models internally track the value of their current trajectory, defined as the likelihood that their ongoing strategy will achieve their goals. Using synthetic, in-context reinforcement learning data, we construct a "value" axis for Qwen3-8B. We find that activations along this axis distinguish between high vs. low verbalized confidence, rollouts without and with backtracking, and correct vs. corrupted code. Steering towards high value causally suppresses self-correction and reduces explanatory verbosity, while steering towards low value induces backtracking and exploration. We demonstrate that direct preference optimization (DPO) can increase the internal value of rewarded behaviors (e.g. use a certain word), causing the model to act more confidently after exhibiting them. Finally, we apply the value axis to study in-the-wild settings. For example, we find that Qwen assigns low value to politically sensitive chat queries after post-training and that supervised fine-tuning increases internal confidence within the training domain. Our results suggest that language models linearly encode an estimate of expected goal success that modulates their confidence in pursuing a direction.

04.
arXiv (CS.CV) 2026-06-16

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos

Generalist Vision-Language-Action models remain constrained by the scarcity of robotic data relative to the abundance of human video demonstrations. Existing Latent Action Models attempt to use video data but often suffer from visual entanglement, encoding noise rather than manipulation skills. To address this limitation, we propose Contrastive Latent Action Pretraining (CLAP), a framework that first uses Act-VAE to learn an executable action-token vocabulary from robot trajectories and then aligns human visual transitions with this vocabulary through contrastive learning. This alignment maps unlabeled human videos into a physically grounded latent action space rather than reconstructing appearance. Building on the aligned tokens, we train CLAP-NTP as an autoregressive VLA using robot demonstrations and pseudo-labeled human videos, preserving instruction following and object generalization. For deployment and target-domain adaptation, we further introduce a post-training strategy that combines CLAP-RF, a Rectified Flow action head for low-latency continuous action chunk prediction, with Knowledge Matching regularization to preserve pretrained semantic knowledge during fine-tuning. Extensive experiments show that CLAP achieves strong performance against competitive baselines while enabling effective skill transfer from human videos to robotic execution.

05.
arXiv (quant-ph) 2026-06-19

A Finite-Volume Scheme for the Continuum Extrapolation of Lattice Step-Scaling in (2+1)D Hamiltonian U(1) Gauge Theory

arXiv:2606.20029v1 Announce Type: cross Abstract: We propose a finite-volume scheme to perform controlled continuum extrapolations of the lattice step-scaling function, a key ingredient for determining the running coupling in a Hamiltonian lattice gauge theory in small volumes. As a testbed, we employ a dual Hamiltonian formulation of pure U(1) gauge theory in (2+1) dimensions and an operator basis that remains efficient toward weak coupling. We describe the implementation of static external charges on the spatial lattice and study, using matrix product states, the resulting confining string, from which we extract the static potential and a force-based renormalized coupling. Using the proposed finite-volume scheme, we demonstrate a stable continuum limit of the step-scaling function on the lattice sizes accessible to present Hamiltonian simulations. The method is readily extendable to other gauge groups and dimensions, providing a pathway toward Hamiltonian step-scaling studies in other theories.

06.
arXiv (math.PR) 2026-06-16

The Winner Takes It All

arXiv:2606.16885v1 Announce Type: cross Abstract: The winner-takes-all (WTA) process takes place on an arbitrary graph. There is an agent on each vertex of the graph, and active agents at neighboring vertices play games. In each game, a randomly chosen agent wins, while the loser is eliminated from subsequent games. The games are played at random times; each game finishes instantaneously, and the games cease when each active agent has only losers among its neighbors. On the one-dimensional lattice, the fraction of winners in the final state is $e^{-1}$, and we also determine the fractions $w_j$ of winners who won $j=0, 1, 2$ games. For the WTA process on a segment, we determine statistics of the total number of winners (the average, the variance, and all higher cumulants), the probabilities of reaching the final state with the minimum or maximum number of winners, and establish the behavior near the boundaries. For infinite regular trees with vertices of degree $d$, i.e., Bethe lattices with coordination number $d$, the fraction of winners is $(2/d)^{d/(d-2)}$.

07.
arXiv (quant-ph) 2026-06-12

Relativistic Locality from Electromagnetism to Quantum Field Theory

arXiv:2412.11532v2 Announce Type: replace Abstract: Electromagnetism is the paradigm case of a theory that satisfies relativistic locality. This can be proven by demonstrating that, once the theory's laws are imposed, what is happening within a region fixes what will happen in the contracting light-cone with that region as its base. The Klein-Gordon and Dirac equations meet the same standard. We show that this standard can also be applied to quantum field theory (without collapse), examining two different ways of assigning reduced density matrix states to regions of space. Our preferred method begins from field wave functionals and judges quantum field theory to be local. Another method begins from particle wave functions (states in Fock space) and leads to either non-locality or an inability to assign states to regions, depending on the choice of creation operators. We take this analysis of quantum field theory (without collapse) to show that the many-worlds interpretation of quantum physics is local at the fundamental level. We argue that this fundamental locality is compatible with either local or global accounts of the non-fundamental branching of worlds, countering an objection that has been raised to the Sebens-Carroll derivation of the Born Rule from self-locating uncertainty.

08.
arXiv (CS.AI) 2026-06-19

Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models

arXiv:2606.19635v1 Announce Type: cross Abstract: Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that "textualize" these signals directly or create discrete item representations often lead to excessively long prompts, substantial memory footprints, and high computational overhead. To overcome these limitations, we propose "Token Factory", a framework designed to transform traditional signals into "soft tokens" that can be directly processed by LRMs. This approach enables efficient integration and compression of heterogeneous input features, preventing prompt length explosion while enhancing model performance. We detail the architecture of Token Factory and present experimental results validating its effectiveness in a production-scale recommendation environment.

09.
arXiv (CS.AI) 2026-06-11

SAGE: Scalable AI Governance & Evaluation

arXiv:2602.07840v4 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present SAGE (Scalable AI Governance \& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language Policy, curated Precedent, and an LLM Surrogate Judge co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at 92$\times$ lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a 0.25\% lift in LinkedIn daily active users.

10.
medRxiv (Medicine) 2026-06-11

Validity and Limitations of the Empatica E4 Wristband for Autonomic and Thermoregulatory Sleep Monitoring Against Concurrent Polysomnography: A Wearanize+ Dataset Study

The Empatica E4 wristband provides continuous multi-modal physiological monitoring including blood volume pulse (BVP), electrodermal activity (EDA) and skin temperature (TEMP) but its validity for sleep-stage-specific autonomic and thermoregulatory monitoring has not been systematically evaluated against concurrent polysomnography (PSG). Using the Wearanize+ dataset which provides synchronised PSG, Empatica E4, and Zmax EEG recordings from 100 home-recorded participants; a systematic validation of Empatica E4 physiological signals against PSG ground truth across five sleep stages was conducted. Of 100 participants, 92 had Empatica data; 69 met Zmax EEG signal quality criteria and formed the analysis sample. Heart rate (HR) from the pre-computed Empatica HR channel showed valid stage-specific patterns (Wake: 70.9 bpm, N3: 61.2 bpm) and moderate inter-device MeanNN correspondence with PSG ECG (Spearman r=0.35-0.42 across stages). Skin temperature showed the expected thermoregulatory pattern (Wake: 33.92C, N3: 35.48C) and is recommended for downstream analyses. Tonic EDA showed an inverted stage pattern attributable to wrist sweat accumulation during deep sleep, representing a known confound for wrist-worn EDA during sleep. Phasic EDA showed plausible patterns and may be used with caution. These findings establish a validated feature set for Empatica E4 sleep research and directly inform multimodal psychiatric biomarker studies using the Wearanize+ dataset.

11.
arXiv (CS.CV) 2026-06-18

Urdu Katib Handwritten Dataset: A Historical Document Dataset for Offline Urdu Handwritten Text Recognition with CRNN-Based Baseline Evaluation

Automatic Handwritten Text Recognition (HTR) is inherently a challenging task, and its complexity is further increased when dealing with cursive scripts. Although significant efforts have been made on various cursive scripts, research regarding Urdu Handwritten Text Recognition (UHTR) has been relatively limited. This lag of research is primarily due to the unique challenges posed by its script, and the scarcity and unavailability of benchmark datasets. Therefore, to advance research in UHTR, this study presents a specialized real dataset called the Urdu Katib Handwritten Dataset (UKHD). To the best of our knowledge, this is the first offline Urdu handwritten text lines dataset specifically curated from the materials written by Katibs in historical times. It encompasses a diverse range of flat nib writing variations in the Nastalique calligraphic style. Additionally, the effectiveness of different CRNN-based hybrid models has been evaluated to identify the optimal architecture for Urdu Katib Handwriting Recognition (UKHR). Among the analyzed models, the CNN-BGRU-CTC model showed more robust performance, with low Character Error Rate (CER) and Word Error Rate (WER). This research work aims to support and encourage the research community in developing a robust recognition system for preserving Urdu handwritten literature.

12.
Nature (Science) 2026-06-17

Confined migration induces non-lethal DNA damage in developing neurons

Authors:

Migratory cells tend to have soft nuclei that deform and penetrate narrow spaces1,2. Extensive nuclear deformation during migration can cause nuclear-envelope rupture and DNA damage in cancer cells, which may contribute to malignant transformation during tumour progression3–6. However, the importance of DNA damage in physiological migration is less well understood. Here we demonstrate that the migration of neurons in developing cerebral and cerebellar cortices is accompanied by massive DNA double-stranded breaks (DSBs) due to mechanostress during passage through narrow interstitial spaces. In contrast to many other migratory cells, these DSBs occur without detectable nuclear envelope rupture. Confined migration increases topoisomerase-IIβ covalently bound DSBs, and these lesions are repaired through non-homologous end-joining during brain development without causing cell death. Genome sequencing revealed that DSBs tend to occur at transcriptionally inactive regions. The deletion of ligase IV at the onset of neuronal migration leads to persistent DSB accumulation in cerebellar neurons with moderate transcriptional changes in genes related to synaptic function, neuronal development and stress and immune responses. The mutant mouse develops mild motor deficits in later life, suggesting that the DNA damage generated during normal brain development poses a potential disease risk if left unrepaired. The migration of neurons in developing cerebral and cerebellar cortices is accompanied by massive DNA double-strand breaks due to mechanostress during passage through narrow interstitial spaces.

13.
arXiv (CS.AI) 2026-06-12

Algorithmic Constitutionalism

arXiv:2606.12437v1 Announce Type: cross Abstract: The increasing encroachment of artificial intelligence (AI) on social life raises significant risks for society, particularly within the infospheres created and controlled by companies such as Google, Facebook, Apple, and Amazon. This article examines these risks through an in-depth analysis of Facebook's content moderation regime, which is already partially governed by algorithms. We argue that the idea of ethical engineering, often proposed in the literature as a solution to the governance challenges posed by AI, is inadequate for several reasons. In response, we develop an alternative framework, which we term "algorithmic constitutionalism." Our approach rests on three pillars: (a) a layered architecture consisting of two levels of code: (i) an operative or object level and (ii) a meta level designed to protect the system's core principles from algorithmically initiated change; (b) algorithmic meta-reasoning, which enables the system to operate simultaneously at both levels so that it can monitor, verify, and potentially correct in real time operations at the object level that depart from principles protected at the meta-code level; and (c) correction through deliberation. The article elaborates the concept of algorithmic constitutionalism and demonstrates how it may be applied to Facebook's content moderation regime. As part of this analysis, we examine the tension between societal constitutionalism and algorithmic constitutionalism. Paradoxically, attempts to subject AI systems to external deliberative control may also enable AI agents to intervene in that process, potentially undermining its purpose. The article concludes by considering the implications of this argument for the European Digital Services Act, which entered into force in October 2022.

14.
arXiv (CS.CV) 2026-06-16

Power Battery Detection

Power batteries are essential components in electric vehicles, where internal structural defects can pose serious safety risks. We conduct a comprehensive study on a new task, power battery detection (PBD), which aims to localize the dense endpoints of cathode and anode plates from industrial X-ray images for quality inspection. Manual inspection is inefficient and error-prone, while traditional vision algorithms struggle with densely packed plates, low contrast, scale variation, and imaging artifacts. To address this issue and drive more attention into this meaningful task, we present PBD5K, the first large-scale benchmark for this task, consisting of 5,000 X-ray images from nine battery types with fine-grained annotations and eight types of real-world visual interference. To support scalable and consistent labeling, we develop an intelligent annotation pipeline that combines image filtering, model-assisted pre-labeling, cross-verification, and layered quality evaluation. We formulate PBD as a point-level segmentation problem and propose MDCNeXt, a model designed to extract and integrate multi-dimensional structure clues including point, line, and count information from the plate itself. To improve discrimination between plates and suppress visual interference, MDCNeXt incorporates two state space modules. The first is a prompt-filtered module that learns contrastive relationships guided by task-specific prompts. The second is a density-aware reordering module that refines segmentation in regions with high plate density. In addition, we propose a distance-adaptive mask generation strategy to provide robust supervision under varying spatial distributions of anode and cathode positions. The source code and datasets will be publicly available at \href{https://github.com/Xiaoqi-Zhao-DLUT/X-ray-PBD}{PBD5K}.

15.
arXiv (CS.AI) 2026-06-19

Process-Verified Reinforcement Learning for Theorem Proving via Lean

arXiv:2606.20068v1 Announce Type: new Abstract: While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structured feedback. This gap between structured processes and unstructured rewards highlights the importance of feedback that is both dense and sound. In this work, we demonstrate that the Lean proof assistant itself can serve as a symbolic process oracle, supplying both outcome-level and fine-grained tactic-level verified feedback during training. Proof attempts are parsed into tactic sequences, and Lean's elaboration marks both locally sound steps and the earliest failing step, yielding dense, verifier-grounded credit signals rooted in type theory. We incorporate these structured rewards into a GRPO-style reinforcement learning objective with first-error propagation and first-token credit methods that balances outcome- and process-level advantages. Experiments with STP-Lean and DeepSeek-Prover-V1.5 show that tactic-level supervision outperforms outcome-only baselines in most settings, delivering improvements on benchmarks such as MiniF2F and ProofNet. Beyond empirical gains, our study highlights a broader perspective: symbolic proof assistants are not only verifiers at evaluation time, but can also act as process-level reward oracles during training. This opens a path toward reinforcement learning frameworks that combine the scalability of language models with the reliability of symbolic verification for formal reasoning.

16.
arXiv (math.PR) 2026-06-15

Lehner's operator norm formulas, semidefinite programming, and spiked matrix models

arXiv:2606.14687v1 Announce Type: new Abstract: Lehner (1999) derived elegant formulas for the operator norm $\|\mathfrak{X}\|$ of operators of the form $\mathfrak{X} = \mathbf{A}_0 \otimes \mathfrak{1} + \sum_{i = 1}^n \mathbf{A}_i \otimes \mathfrak{m}_i$, also easily generalized to the spectral edge $\lambda_{\max}(\mathfrak{X})$, in terms of nonlinear optimization problems over positive definite matrices. Here the $\mathbf{A}_i$ are finite-dimensional Hermitian matrices, the $\mathfrak{m}_i$ are either free semicircular or free Rademacher families of operators, and $\mathfrak{1}$ is the identity operator. We first show that both of Lehner's nonlinear optimizations can be rewritten as linear semidefinite programs (SDPs), even in the Rademacher case where Lehner's optimization is not itself convex. We give the primal and dual forms of these SDPs, derive the complementary slackness relations and consequences thereof, and propose that the SDPs are more stable and accurate than the iterative numerical scheme proposed in Lehner's original work. We then apply the SDPs from the semicircular case to spiked matrix models, studied recently via Lehner's formula by Bandeira, Cipolloni, Schröder, and van Handel (2024). We give a new proof of the Baik–Ben Arous–Péché (BBP) transition they establish in models with isotropic (but possibly correlated) Gaussian noise by constructing feasible variables for the associated primal and dual SDPs. Combining our construction with a sensitivity interpretation of optimal dual variables, we study the fluctuations of leading eigenvectors of such models. We conjecture and give numerical evidence that these fluctuations are Gaussian but anisotropic and non-universal, and that their covariance may be computed in terms of the optimizer of the dual of Lehner's formula, which in turn is approximately the leading eigenmatrix of a completely positive operator associated to the covariance of the noise model.

17.
arXiv (math.PR) 2026-06-24

Uniform Sampling from High-dimensional Spectral Norm Balls

arXiv:2606.24134v1 Announce Type: new Abstract: Motivated by an application in machine learning optimization, this paper focuses on the challenges of sampling a matrix uniformly from the unit spectral norm ball. It is proven that all singular values of sampled matrices converge to 1 almost surely as the matrix dimensions increase. This result provides the theoretical justification for a proposed simple sampling method applicable for large dimension sizes matching matrices found in modern large language models. Experimental results demonstrate both the convergence of the singular values, as well as the exact and proposed approximate sampling methods.

18.
arXiv (CS.AI) 2026-06-16

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

arXiv:2606.15197v1 Announce Type: cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling methods improve modeling policies through large-scale annotated or curated training data, but are costly to adapt to new problem distributions. Meanwhile, one-shot generation remains brittle in hierarchical modeling, where early symbolic errors can propagate into invalid formulations. Test-time scaling offers a promising alternative by enabling structural exploration with additional instance-level computation; however, existing search-based methods typically rely on a fixed policy, causing repeated rollouts to inherit similar modeling biases and providing limited credit assignment for intermediate decisions. To address these limitations, we propose StarOR, a synergistic search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling. StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node. By using MCTS-generated siblings as local comparison sets, StarOR transforms search-time exploration into instance-specific policy refinement. Moreover, an unsupervised multi-faceted reward system provides fine-grained feedback for intermediate formulation decisions without ground-truth labels. Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone, outperforming existing methods and the frontier LLMs.

19.
arXiv (CS.LG) 2026-06-16

ExpRL: Exploratory RL for LLM Mid-Training

arXiv:2606.17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In practice, models are often primed for RL through mid-training on curated reasoning traces that teach useful primitive skills such as decomposition, verification, or self-correction. Although effective, this strategy requires manually specifying what the model should learn, and it remains unclear whether such primitive coverage is enough for much harder problems, which require combining these skills into broader solution strategies. We study a more automated approach: RL-based mid-training using large corpora of human-written question-answer data. Rather than treating reference solutions as targets to imitate, our method, ExpRL, uses them as reward scaffolds: references are hidden from the policy and used only to construct problem-specific grading rubrics for judging on-policy reasoning traces. The policy samples from the original problem prompt, while an LLM judge compares the sampled reasoning trace against the reference solution and assigns outcome-level or process-level dense rewards. This lets ExpRL reinforce partial progress, useful intermediate reductions, and productive reasoning behaviors that sparse final-answer rewards often fail to upweight. On challenging math reasoning tasks, ExpRL yields stronger RL priming than SFT, sparse-reward GRPO, and self-distillation, and provides a better initialization for subsequent sparse-reward RL. Additional mixed-domain experiments further suggest that ExpRL can extend beyond the original math-only setting.

20.
arXiv (CS.CL) 2026-06-16

G-Loss: Graph-Guided Fine-Tuning of Language Models

Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operate only within local neighborhoods and fail to account for the global semantic structure. We present G-Loss, a graph-guided loss function that incorporates semi-supervised label propagation to use structural relationships within the embedding manifold. G-Loss builds a document-similarity graph that captures global semantic relationships, thereby guiding the model to learn more discriminative and robust embeddings. We evaluate G-Loss on five benchmark datasets covering key downstream classification tasks: MR (sentiment analysis), R8 and R52 (topic categorization), Ohsumed (medical document classification), and 20NG (news categorization). In the majority of experimental setups, G-Loss converges faster and produces semantically coherent embedding spaces, resulting in higher classification accuracy than models fine-tuned with traditional loss functions.

21.
arXiv (CS.LG) 2026-06-16

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

arXiv:2606.16236v1 Announce Type: new Abstract: Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training. Existing techniques such as domain randomization (DR) mitigate this, but require access to diverse training environments and full trajectory observability, assumptions that fail in privacy-preserving or restricted scenarios where only scalar performance metrics are available. We propose Generalization via Evolutionary Reward Shaping (GERS), a bilevel optimization approach to improve generalization on unseen test environments using only scalar feedback from validation environments. At the lower level, an RL agent guided via a reward function shaped by the upper level learns a policy on a limited set of training environments with accessible trajectory data; at the upper level, CMA-ES optimizes the reward shaping parameters to maximize the cumulative unshaped reward on separate validation environments for which trajectory access is unavailable. Results on continuous control tasks indicate that GERS outperforms the standard RL baseline on unseen test environments. GERS performance is comparable to DR, despite DR treating the combined set of training and validation environments of GERS as a single training set that requires trajectory access, whereas GERS cannot access validation trajectories. These results confirm that GERS effectively enhances generalization under restricted data access constraints.

22.
arXiv (CS.LG) 2026-06-24

Learning the Koopman Operator using Attention Free Transformers

arXiv:2606.23957v1 Announce Type: new Abstract: Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and amplitude errors on systems with switching, continuous spectra, or strong transients. We introduce two complementary components that make Koopman predictors more robust. First, we add an attention-free latent memory (AFT) block that aggregates a short window of past latents to produce a corrected latent before each Koopman update. Unlike multi-head attention, AFT operates in linear time and adds only $\approx$30k parameters ($3d^2 + T^2$, fewer than matched multi-head attention), yet captures the local temporal context needed to suppress error divergence. Second, we propose dynamic re-encoding: lightweight, online change-point triggers (EWMA, CUSUM, and sequential two-sample tests) that detect latent drift and project predictions back onto the autoencoder manifold. Across three benchmark systems – Duffing oscillator, Repressilator, IRMA – our model consistently reduces error accumulation compared to a Koopman autoencoder and matched-capacity multi-head attention. We also compare against GRU and Transformer autoencoders, evaluated both from initial conditions and with a 50-step context, and find that Koopman+AFT (with optional re-encoding) attains markedly lower long-horizon error while maintaining lower inference latency. We report improvements over horizons up to 1000 steps, together with ablations over trigger policies. The result is a fast, compact predictor that stays on the learned manifold over long horizons.

23.
arXiv (CS.AI) 2026-06-15

Metabolic cost of information processing in Poisson variational autoencoders

arXiv:2602.13421v2 Announce Type: replace-cross Abstract: Computation in biological systems is fundamentally energy-constrained, yet standard theories of computation treat energy as freely available. Here, we argue that variational free energy minimization under a Poisson assumption offers a principled path toward an energy-aware theory of computation. Our key observation is that the Kullback-Leibler (KL) divergence term in the Poisson free energy objective becomes proportional to the prior firing rates of model neurons, yielding an emergent metabolic cost term that penalizes high baseline activity. This structure couples an abstract information-theoretic quantity – the *coding rate* – to a concrete biophysical variable – the *firing rate* – which enables a trade-off between coding fidelity and energy expenditure. Such a coupling arises naturally in the Poisson variational autoencoder (P-VAE) – a brain-inspired generative model that encodes inputs as discrete spike counts and recovers a spiking form of *sparse coding* as a special case – but is absent from standard Gaussian VAEs. To demonstrate that this metabolic cost structure is unique to the Poisson formulation, we compare the P-VAE against Grelu-VAE, a Gaussian VAE with ReLU rectification applied to latent samples, which controls for the non-negativity constraint. Across a systematic sweep of the KL term weighting coefficient $\beta$ and latent dimensionality, we find that increasing $\beta$ monotonically increases sparsity and reduces average spiking activity in the P-VAE. In contrast, Grelu-VAE representations remain unchanged, confirming that the effect is specific to Poisson statistics rather than a byproduct of non-negative representations. These results establish Poisson variational inference as a promising foundation for a resource-constrained theory of computation.

24.
arXiv (CS.AI) 2026-06-11

T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking

arXiv:2606.11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures. The primary technical challenge lies in ensuring watermark robustness against various post-processing attacks on the watermarked model. Model extraction attacks emerge as the most severe threat, where adversaries exploit prediction outputs to train surrogate models that illegally replicate the original model's functionality. In this work, we propose a rehearsal-based watermark embedding framework to enhance the robustness of model watermarks against model extraction attacks. By simulating the extraction process, our method leverages the loss of a simulated stolen model on a trigger set as a training signal to fine-tune the watermark knowledge within the target model. This fine-tuning step encourages the watermark to be embedded in a way that boosts transferability, thereby increasing its chances of persisting and remaining detectable in stolen models. Comprehensive experiments conducted under diverse settings demonstrate that the proposed method significantly improves the robustness of model watermarks against both model extraction and subsequent watermark removal attacks.

25.
medRxiv (Medicine) 2026-06-24

Cortisol Stress Response is Associated with Iron Status in Pregnancy

Background: Iron deficiency (ID) affects up to 40% of pregnant women in the third trimester, even in highly resourced and iron-supplemented populations, with adverse consequences for maternal health and long-term offspring development. Psychological stress may compromise iron status through hypothalamic-pituitary-adrenocortical (HPA) axis dysregulation and inflammation, but no study has directly examined cortisol in relation to iron status across human pregnancy. Objective: This longitudinal study examined associations between HPA function and maternal iron status across pregnancy and tested whether IL-6 and CRP mediated the relationship between cortisol and ferritin across gestation. Methods: One hundred sixty-eight pregnant Black women with Medicaid insurance completed up to four laboratory assessments across pregnancy. Salivary cortisol was measured before and in response to the Trier Social Stress Test, yielding basal and reactive cortisol indices. Serum ferritin, IL-6, and CRP were collected at each visit. Trimester-specific regression models examined cortisol reactivity in relation to ferritin; linear mixed-effects models with moderated mediation tested whether basal cortisol predicted ferritin via inflammation. Results: Higher cortisol reactivity was associated with lower ferritin specifically in the third trimester (std. {beta} = -0.197, p = .004). Higher basal cortisol predicted a steeper IL-6 rise across gestation (p = .002), and IL-6 was positively associated with ferritin (b = 0.236, p = .006), consistent with inflammatory iron sequestration. The indirect effect of basal cortisol on ferritin via IL-6 was statistically significant, and higher basal cortisol was negatively associated with cortisol reactivity in the third trimester. No pathway was observed through CRP. Conclusion: Greater cortisol reactivity predicted lower third-trimester ferritin, a pattern that suggests cumulative iron depletion, atypically sustained HPA reactivity in late pregnancy, or both. To our knowledge, this is the first prospective study linking cortisol reactivity to iron status across human pregnancy, identifying maternal stress physiology as a novel target for understanding and addressing gestational iron deficiency.