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

Malliavin Calculus for the stochastic Cahn-Hilliard equation driven by fractional noise

arXiv:2601.10490v2 Announce Type: replace Abstract: The stochastic partial differential equation analyzed in this work is the Cahn-Hilliard equation perturbed by an additive fractional white noise (fractional in time and white in space). We work in the case of one spatial dimension and apply Malliavin calculus to investigate the existence of a density for the stochastic solution $u$. In particular, we show that $u$ admits continuous paths almost surely and construct a localizing sequence through which we prove that its Malliavin derivative exists locally, and that its law is absolutely continuous with respect to the Lebesgue measure on $\bf R$, establishing thus that a density exists. A key contribution of this work is the analysis of the stochastic integral appearing in the mild formulation: we derive sharp estimates for the expectation of the $p$-th power ($p \geq 2$) of the $L^{\infty}(D)$-norm of this stochastic integral as well as for the integral involving the $L^{\infty}(D)$-norm of the operator associated with the kernel appearing in the integral representation of the fractional noise, all of which are essential for this study.

02.
arXiv (quant-ph) 2026-06-19

All-valid-state HOBO encoding for constrained combinatorial optimization on NISQ devices

arXiv:2606.20017v1 Announce Type: new Abstract: Continued advancements in quantum computing have stimulated growing interest in translating quantum technologies into real-world applications. Consequently, the investigation of practically motivated NP-hard problems is of significant value. This study investigates the performance of a variational quantum eigensolver (VQE) in addressing the traveling salesperson problem (TSP) through noiseless simulations representative of noisy intermediate-scale quantum (NISQ) devices using higher-order binary optimization (HOBO) encodings. We construct a HOBO Hamiltonian with an efficient binary representation and propose an all-valid-state HOBO (AVS-HOBO) scheme based on cyclic mapping that eliminates one penalty term and reuses states that would otherwise be invalid. Using TSP instances of up to 20 cities, we compare the original HOBO and AVS-HOBO encodings from multiple perspectives, including the energy convergence behavior and the approximation, tour-length, and feasibility ratios. In addition to simulations, we perform computations on real quantum hardware with different device architectures, where we not only compare the performances of different chips but also investigate the effects of different error-mitigation methods on actual quantum machines. The results indicate that AVS-HOBO encoding enhances the practical reliability of VQE on NISQ devices and improves scalability for larger TSP instances, with broader applicability to constrained quantum optimization problems.

03.
arXiv (math.PR) 2026-06-24

Sparsity-adaptive concentration inequalities for random polynomials

arXiv:2606.24090v1 Announce Type: new Abstract: We prove concentration inequalities for polynomials of independent, sparse $\alpha$-sub-exponential random variables. Specifically, we consider $X_i=\delta_i\xi_i$, where the Bernoulli selectors $\delta_i$ are independent with parameters $p_i$, and the variables $\xi_i$ are independent \(\alpha\)-sub-exponential random variables (not necessarily centered). For any polynomial $f:\mathbb R^n\to\mathbb R $ of degree at most $D$ and any $0

04.
Nature Biotechnology 2026-06-05

Structural motif search across the protein universe with Folddisco

Authors:

Detecting similar protein structural motifs in large structure collections is computationally expensive. We developed Folddisco, a fast structural motif search tool that uses an index of position-independent geometric features, including side-chain orientation, combined with a rarity-based scoring system. Folddisco is 20-fold faster in querying and fourfold more storage-efficient than existing methods while improving accuracy. Folddisco is freely available online ( https://folddisco.foldseek.com ), along with a webserver ( https://search.foldseek.com/folddisco ). Folddisco enables protein structural motif search in million scale databases.

05.
arXiv (CS.CV) 2026-06-16

When the Past Matters: FlashBack Memory for Precipitation Nowcasting

Accurate precipitation nowcasting is crucial for disaster mitigation and socio-economic planning, yet existing methods often struggle with false alarms, missed events, and long range dependency modeling at high spatiotemporal resolution. To address these challenges, we propose FlashBack Memory (FB), a module that dynamically retrieves key historical states and integrates them via an adaptive fusion gate, enhancing the spatiotemporal representation capability of recurrent-based models. We incorporate FB into PredRNN, PredRNNpp, MIM, MotionRNN, and PredRNN-V2, and evaluate on CIKM2017, Shanghai2020, and SEVIR datasets. Experimental results demonstrate that FB significantly improves MSE, MAE, SSIM, and CSI metrics, particularly for high-intensity rainfall and long-sequence predictions, while reducing false alarms and missed events and enhancing temporal consistency and spatial localization. The proposed method provides a general and efficient memory enhancement mechanism, improving the overall performance of recurrent-based precipitation nowcasting models.

06.
Nature (Science) 2026-06-24

Zero-shot design of drug-binding proteins via neural iterative selection−expansion

Authors:

The design of proteins that bind to small molecules has been challenging because it requires simultaneous optimization of the protein sequence, protein structure and ligand conformation1–7. Current deep-learning algorithms have struggled to navigate this landscape, precluding the zero-shot design of binders. Here we show that by combining two neural networks in an iterative design algorithm, small-molecule binding proteins can be created from scratch with high accuracy. We trained a graph neural network—ligand-aware sequence engineering message-passing neural network (LASErMPNN)—to design compatible protein sequences for an input protein backbone and docked ligand. We paired  LASErMPNN with a structure predictor that models a three-dimensional protein–ligand complex for an input protein sequence and ligand identity. The closed-loop iteration of these reciprocal networks optimized sequence–structure–ligand compatibility, and outperformed a comparable design loop using a physics-based energy function. We used our strategy, termed neural iterative selection–expansion (NISE), to design proteins that, using different folds, specifically bind to two chemically distinct small-molecule drugs, exatecan and apixaban, with success rates of 100% and 83%, respectively. The tightest NISE binders had nanomolar-to-picomolar affinities, surpassing those of the next-leading method by 70-fold for exatecan and nearly 10,000-fold for apixaban. LASErMPNN then suggested two amino-acid substitutions that improved the affinity of the tightest exatecan binder by 100-fold without any experimental input. The optimized binder protected the labile lactone ring of exatecan from hydrolysis for days. Our work describes a general recipe for using neural networks to automate the design of small-molecule binding proteins for applications in drug delivery, sensing and catalysis.  By pairing two neural networks in an iterative optimization algorithm, small-molecule binding proteins can be designed from scratch with high accuracy, affinity and success rates, showing promise for applications in drug delivery and sequestration.

07.
arXiv (CS.LG) 2026-06-17

Overcoming the Incentive Collapse Paradox

arXiv:2603.27049v2 Announce Type: replace-cross Abstract: AI-assisted task delegation is increasingly common, yet human effort in such systems is costly and typically unobserved. Recent work by Bastani and Cachon (2025); Sambasivan et al. (2021) shows that accuracy-based payment schemes suffer from incentive collapse: as AI accuracy improves, sustaining positive human effort requires unbounded payments. We study this phenomenon in a budget-constrained principal-agent framework with strategic human agents whose output accuracy depends on unobserved effort. Our first contribution is a general impossibility result showing that incentive collapse is not merely a limitation of simple linear payments, but arises for any payment rule based only on observed task accuracy.To overcome this barrier, we propose a sentinel-auditing payment mechanism that enforces a strictly positive and controllable level of human effort at finite cost, independent of AI accuracy. Building on this incentive-robust foundation, we develop an incentive-aware active statistical inference framework that jointly optimizes (i) the auditing rate and (ii) active sampling and budget allocation across tasks of varying difficulty to minimize the final statistical loss under a single budget. Experiments demonstrate improved cost-error tradeoffs relative to standard active learning and auditing-only baselines.

08.
arXiv (CS.CL) 2026-06-16

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are often non-injective with respect to semantic content: distinct reasoning paths receive identical rewards. This leads to a Diversity-Quality Inconsistency, where the policy collapses into a narrow set of dominant modes while ignoring equally valid but structurally novel strategies. To bridge this gap, we propose Diversity-aware Reward Adjustment (DRA), a theoretically grounded framework that calibrates the reward signal using the semantic density of sampled groups. By leveraging Submodular Mutual Information (SMI), DRA implements an Inverse Propensity Scoring (IPS) mechanism that effectively de-biases the gradient estimation. This creates a repulsive force against redundancy, driving the policy to achieve better coverage of the high-reward landscape. Our method is plug-and-play and integrates seamlessly with GRPO variants. Empirical evaluations on five math benchmarks demonstrate that DRA-GRPO consistently outperforms strong baselines, achieving an average accuracy of 58.2% on DeepSeek-R1-Distill-Qwen-1.5B with only 7,000 training samples and $55 cost, highlighting the critical role of diversity calibration in data-efficient alignment. The code is available at https://github.com/xiwenc1/DRA-GRPO.

09.
bioRxiv (Bioinfo) 2026-06-11

TifBERT: a self-supervised foundation model for normalization-robust bulk RNA-seq representation learning

Bulk RNA sequencing remains central to translational genomics, yet foundation-model development has largely focused on single-cell data. Existing transformer approaches for bulk RNA-seq often rely on expression discretization, numerical reconstruction, external gene embeddings, or restricted gene sets, limiting robustness across normalization schemes and cohorts. Here, we introduce TifBERT, a self-supervised framework for full-transcriptome bulk RNA-seq representation learning. TifBERT converts each unordered expression profile into a sample-specific gene sequence using term frequency-inverse document frequency (TF-IDF) ordering, prioritizing genes that are both highly expressed within a sample and selectively expressed across the cohort. It is then pretrained using masked gene modeling, predicting gene identities from transcriptomic context rather than reconstructing expression values. Pretrained on harmonized TCGA Pan-Cancer data spanning five RNA-seq normalization schemes, TifBERT learns contextual representations across approximately 10,000 genes without expression binning, landmark-gene restriction, or external biological embeddings. Across 33 TCGA cancer types, TifBERT achieved 90.83% accuracy, 0.996 macro AUC-ROC, and 0.903 MCC. It also captured pathway-level biology, achieving mean sample-wise and pathway-wise Pearson correlations of 0.754 and 0.762 across 1,387 PARADIGM pathway activities. Independent evaluation on GTEx healthy tissues showed preservation of tissue-level transcriptomic structure without retraining. In comparison with existing models, TifBERT achieves competitive subtype discrimination with substantially greater stability and produces markedly richer embedding geometry (effective rank 95.6 versus 6.3), without requiring expression discretization or in-distribution pretraining exposure. Together, TifBERT provides a scalable, normalization-independent foundation model for reusable bulk transcriptomic representation learning

10.
arXiv (CS.AI) 2026-06-15

TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation

arXiv:2606.14551v1 Announce Type: cross Abstract: Robots under autonomous operation may require decisions based on evidence that is no longer visible. We study delayed-evidence tasks, where an early cue disappears before a later decision point, so visually similar observations can require different actions. In these settings, the current observation is not a sufficient state for control. We introduce TRAjectory-routed Causal Evidence (TRACE), a memory framework for visuomotor imitation policies. TRACE stores task-relevant visual and robot-state evidence, such as object identity, target choice, or route-dependent state, in a fixed-size latent memory that remains bounded over long episodes. Instead of indexing memory by raw time or manually provided task labels, TRACE uses path signatures: compact, order-sensitive features of the executed robot-state trajectory. These signatures do not store the visual cue itself; rather, they provide trajectory-conditioned keys for writing and retrieving the evidence stored when the cue was visible. When the robot later reaches an ambiguous observation, the policy conditions on TRACE memory to recover the missing context and choose the correct branch. TRACE attaches through lightweight adapters to policies, without changing the policy backbone, action head, or imitation objective. Across real-world long-horizon manipulation tasks with visually ambiguous branch points, TRACE improves branch selection and task success over alternative baselines, including short-history and recurrent memory. Project page: https://jeong-zju.github.io/trace

11.
arXiv (CS.LG) 2026-06-11

Last-Iterate Convergence of Optimistic Multiplicative Weight Update

arXiv:2606.11773v1 Announce Type: cross Abstract: Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative-Weights Update (OMWU) are two very popular algorithms to solve convex/concave saddle-point problems, where OMWU is the non-Euclidean, entropic version of OGDA. It is known since the '80s that the last iterate of OGDA asymptotically converges to a saddle point in smooth problems. On the other hand, it is unknown if OMWU has the same property. In this paper, I show that OMWU converges asymptotically for smooth convex-concave saddle-point problems, with a small enough constant learning rate. The result does not require uniqueness, strict complementarity, an error bound, or initialization near a solution. The main new ingredient is a boundary argument showing that every cluster point satisfies the inactive-coordinate KKT inequalities. The boundary argument was discovered with assistance from ChatGPT and is documented in the appendix.

12.
bioRxiv (Bioinfo) 2026-06-10

Promera: a unified model for biomolecular structure prediction, filtering, and design

Generative models have become staple tools for modeling and designing biomolecular structures. However, although these tools have improved in structural prediction accuracy, their ability to filter designed binders—an essential use case—remains insufficient; whereas design methods have focused more on unconstrained binder generation rather than capabilities enabled by controllable design. We introduce Promera, a unified generative model that combines all-atom structure prediction with improved filtering and controllable design. We find that Promera's confidence metrics are more accurate for filtering binders from non-binders for both miniproteins and nanobodies, while its co-folding performance surpasses popular open-source models (OpenFold3-p2, Boltz-2) on therapeutically relevant categories. As a design model, Promera generates binders by predicting masked protein sequences with optional epitope, paratope, and template constraints. Remarkably, our nanobody designs match the in silico success rates from backprop-based techniques (mBER) when evaluated under co-folding confidence filters. We further provide two in silico demonstrations of the the versatile capabilities of our design method: epitope targeting of the Andes hantavirus glycoprotein with VHHs and active state stabilization of the beta-2 andrenergic GPCR. We conclude by proposing a scaling law for co-folding models, suggesting a path for further performance improvement.

13.
arXiv (CS.AI) 2026-06-25

Exploring Information Seeking Agent Consolidation

arXiv:2602.00585v2 Announce Type: replace Abstract: Information-seeking agents have emerged as a powerful paradigm for knowledge-intensive tasks, yet today's systems remain specialized for the open web, documents, or local knowledge bases, hindering scalable and cross-domain deployment. We present the first systematic empirical study of consolidating these information-seeking agents into a single foundation agentic model. We compare two paradigms – data-level mixing, which trains a unified model on a mixture of datasets, and parameter-level merging, which merges independently trained experts in parameter space – across 3 training scenarios, evaluating 26 representative parameter-level methods on 10 benchmarks. To compare across heterogeneous benchmarks, we introduce a geometric Composite Score and an Imbalance Score that describe overall performance and task skew. Our analysis shows that (i) well-designed parameter-level merging attains parity with data mixing at a fraction of its training cost and is order-agnostic; (ii) parameter-level merging structurally preserves out-of-domain capabilities that data mixing universally forgets; and (iii) cross-scenario stability is strongly tied to consolidation quality. We distil our observations into a method-selection guide and design principles for next-generation merging operators.

14.
arXiv (math.PR) 2026-06-24

History estimation in random recursive trees: Pointwise approach via iterated Jordan centralities

arXiv:2606.24465v1 Announce Type: new Abstract: We study the problem of estimating the arrival times of vertices in a uniform random recursive tree from its unlabeled structure. We adopt a pointwise perspective and analyze the distribution of the relative estimation error, and derive tail bounds that are uniform in both the vertex and the tree size. For the ranking induced by Jordan centrality, the probability that the estimate exceeds the true arrival time by a factor $S$ decays on the order of $1/S$, while the probability of underestimating the arrival time by a factor $1/S$ decays exponentially in $S$. We introduce a refined centrality measure whose overestimation tail decays on the order of $(\log S)/S^{2}$, at the cost of a heavier lower tail of order $1/S^{2}$. These results reveal a tradeoff between upper- and lower-tail performance in arrival-time estimation that is invisible to the previously studied risk functional. Nevertheless, the refined centrality measure attains the optimal order of the risk for all its parameter values.

15.
medRxiv (Medicine) 2026-06-19

Rumination as a cognitive vulnerability factor in perinatal bereavement: evidence from the CARING study

Purpose. Perinatal loss is associated with a high risk of persistent psychological distress, including prolonged grief, depression, anxiety, and post-traumatic stress symptoms. Cognitive processes such as rumination may play a crucial role in maintaining and amplifying distress following loss, yet their specific contribution in perinatal bereavement remains underexplored. Methods. The CARING (Cognitive Analysis and Rumination INvestigation in perinatal Grief) study employed a cross-sectional design involving 298 parents who experienced perinatal loss within the previous five years. Participants completed an anonymous online survey including measures of depressive rumination (Ruminative Response Scale, RRS), angry rumination (Anger Rumination Scale, ARS), perinatal grief (Perinatal Grief Scale, PGS), general psychopathology (SCL-90), and post-traumatic stress symptoms (NSESSS). Non-parametric analyses were conducted to examine associations between rumination patterns and psychological outcomes. Results. Higher levels of rumination were significantly associated with greater perinatal grief, depressive and anxiety symptoms, and post-traumatic stress. Depressive rumination showed consistently stronger associations with all outcomes compared to angry rumination. Participants presenting both depressive and angry rumination exhibited the highest levels of grief intensity, psychological distress, and PTSD symptoms, suggesting a graded relationship between rumination patterns and severity of distress. Rumination levels were not significantly associated with gestational age at loss or with having received psychological support. Conclusions. Rumination, particularly in its depressive form, appears to function as a transdiagnostic cognitive vulnerability factor in perinatal bereavement. These findings highlight rumination as a potential target for early screening and tailored psychological interventions aimed at reducing long-term distress following perinatal loss.

16.
arXiv (CS.CV) 2026-06-17

Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model

Visual information helps resolve ambiguity in coreference resolution, leading to notable performance gains. However, existing Multi-modal Coreference Resolution (MCR) methods require training with (partially) annotated data from the target dataset before they can be applied, preventing their direct usability and raising concerns about generalization. While Vision-Language Large Models (VLLMs) with billions of parameters offer promising zero-shot capabilities, they remain largely inaccessible. Their massive size limits deployability, and many are only accessible through paid APIs. In this paper, we propose a plug-and-adapt method that strategically adapts a carefully pre-trained alignment model for immediate use in MCR tasks, designed to eliminate the need for training on scarce benchmark datasets or relying on resource-intensive VLLMs. Specifically, we first pre-train a fine-grained alignment model between textual and visual contextual information using vision-language alignment datasets. We then repurpose the alignment model to MCR through similarity aggregation by fusing visual and categorical cues with evidence theory, thereby enhancing effectiveness. Experiments on the Coreference Image Narratives (CIN) benchmark dataset demonstrate the effectiveness of our method, achieving a 5.31\% and 2.12\% improvement in CoNLL F1 over SOTA dedicated methods and popular VLLMs, respectively. We further evaluate our method on a masked CIN dataset for robustness testing and on a specially constructed VCR-MCR dataset for generalization assessment, with results confirming both capabilities.

17.
arXiv (math.PR) 2026-06-25

An RDT based approach to large deviations of Wishart and Wigner matrices spectral edges

arXiv:2606.25501v1 Announce Type: new Abstract: We present a novel methodology for studying large deviations principles (LDPs) of random matrices. By utilizing a partially lifted variant of random duality theory (RDT), we develop a generic LDP framework that completely circumvents traditional random matrix theory (RMT) methods. To demonstrate the framework's simplicity and accuracy, we apply it to the Wishart and Wigner GOE classical statistical ensembles. In both cases, we obtain elegant LDP characterizations of the upper and lower spectral edges that fully match the results achieved through traditional Coulomb gas methodologies in [85,95].

18.
arXiv (CS.AI) 2026-06-25

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

arXiv:2606.25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors. An emerging alternative for discrete user representation – using LLMs to generate text-based user tokens – captures topical co-occurrences rather than deep sequential behavior dynamics and produces outputs that are difficult to ground to item attributes. Meanwhile, Semantic ID (SID) based item tokenization has proven effective for improving generalization in generative recommendation, yet discrete SID-based representations for users remain largely unexplored. We propose TokenMinds, an industrial-scale system that extends the PLUM framework from item retrieval to user modeling, generating both discrete SID-based user tokens and dense user embeddings via an encoder-decoder architecture adapted from pre-trained LLMs. This dual-output design provides the complementary benefits of discrete, semantically grounded user representations while maintaining compatibility with existing downstream models that rely on dense embeddings. Additionally, the shared SID vocabulary naturally extends to cross-scenario modeling: by unifying long-form and short-form video behaviors into a single model, we substantially reduce training and serving costs. We validate TokenMinds through extensive offline experiments and live launches on multiple YouTube surfaces, served on full user traffic (billions of users) via an asynchronous infrastructure that decouples representation generation from downstream scoring. Focusing on ranking as the primary downstream use case, our results confirm the practical viability of SID-based user tokens at industrial scale and demonstrate that tokens and dense embeddings provide complementary value across different production ranking systems.

19.
arXiv (CS.LG) 2026-06-25

Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods

arXiv:2606.25335v1 Announce Type: new Abstract: Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances. We trace this issue to stagnant neurons, units whose gradient updates become negligibly small relative to their weights, thereby hindering learning. While existing plasticity injection methods exist, they prove ineffective for such neurons. To address this, we propose Knowledge-retentive Neuron-level PlastIcity Focusing InjEction (KNIFE), a novel method that directly targets stagnant neurons. KNIFE replaces each stagnant neuron with a composite unit comprising three specialized components: a frozen knowledge neuron to preserve acquired knowledge, a re-initialized active neuron to restore learning capacity, and a compensation neuron to ensure the combined output matches the original, thus maintaining previous learned cooperation knowledge. Extensive experiments on SMACv2, predator-prey, and matrix games demonstrate that KNIFE significantly outperforms state-of-the-art plasticity injection methods.

20.
arXiv (CS.LG) 2026-06-12

Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training

arXiv:2601.17654v2 Announce Type: replace Abstract: The computing demand of AI is growing at an unprecedented rate, but energy supply is not keeping pace. As a result, energy has become an expensive and contended resource that requires explicit management and optimization. Although recent works have made significant progress in large model training optimization, they focus on optimizing either dynamic or static energy consumption. We find that fine-grained kernel scheduling and frequency scaling jointly and interdependently impact both dynamic and static energy consumption. Based on this finding, we design Kareus, a training system that pushes the time-energy tradeoff frontier by optimizing both aspects. Kareus decomposes the intractable joint optimization problem into local, partition-based subproblems. It then uses a multi-pass multi-objective optimization algorithm to find execution schedules that push the time-energy tradeoff frontier. Compared to the state of the art, Kareus reduces training energy by up to 28.3% at the same training time, or reduces training time by up to 27.5% at the same energy consumption.

21.
arXiv (quant-ph) 2026-06-12

Matrix phase-space representations for gaussian boson sampling

arXiv:2503.12749v2 Announce Type: replace Abstract: We introduce coherent matrix phase-space distributions. These use conservation laws and symmetries to improve the accuracy and speed of quantum phase-space representations. As an example, this is applied to validation of low-loss Gaussian boson sampling (GBS) quantum computational advantage experiments, where classical generation of the random photon-number counts is exponentially hard. Large improvements in sampling errors are demonstrated compared to previous methods. Matrix phase-space representations also provide a large numerical speed-up, due to their (at worst) quadratic scaling, compared to other methods for validating total count probabilities of large-scale, low-loss GBS networks.

22.
arXiv (CS.CL) 2026-06-12

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models

The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-step ``slow thinking'' reasoning, unlocking state-of-the-art performance in complex mathematical and logical tasks. However, the field faces the fundamental gap between token-level behavioral analysis and internal reasoning mechanisms, and the instability of reinforcement learning (RL) for reasoning optimization relying on costly external verifiers. We identify and formally define Entropy-Gradient Inversion, a robust negative correlation between token entropy and logit gradients that acts as a definitive geometric fingerprint for LRM reasoning capability. Building on this, we propose Correlation-Regularized Group Policy Optimization (CorR-PO), which embeds this inversion signature into RL reward regularization. Extensive experiments on various reasoning benchmarks across multiple model scales show CorR-PO consistently outperforms state-of-the-art baselines, confirming that stronger inversion directly correlates with superior reasoning performance.

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

Rethinking One-Step Image Editing through ChordEdit: Reproduction, Simplification, and New Insights

One-step image editing is important for making text-guided editing fast, practical, and easy to deploy, but its underlying mechanism is still not fully understood. We revisit ChordEdit through reproduction, ablation, and simplification. Our analysis shows that a) the chord window $\delta$ largely acts as an effective timestep shift from $t$ to $t - \delta$; b) chord transport acts on high-noise images and mainly performs low-frequency semantic editing; and c) proximal alignment acts on low-noise images and complements it by adding high-frequency target details. In this view, ChordEdit naturally decomposes editing into a coarse low-frequency transport stage and a fine high-frequency alignment stage. These findings suggest a path toward prompt-conditioned dynamic timestep selection for adaptive image editing. All code and results can be found at \href{https://github.com/Harvard-AI-and-Robotics-Lab/ChordEdit-Reproduction}{link}.

24.
bioRxiv (Bioinfo) 2026-06-15

AliceDB database and pipeline for identification of natural protein variants based on mass spectrometry measurement data

The natural variation that distinguishes living organisms within a single species is currently being studied intensively, primarily at the genetic level. Unfortunately, studies of natural variants at the level of protein gene products are not very common, mainly due to the lack of appropriate databases and bioinformatics tools. The main research technique used to study proteomes/peptidomes is mass spectrometry (MS). A classic method for interpreting raw mass spectrometry data in proteomic/peptidomic studies involves the use of databases containing representative (canonical) sequences that define the proteome of the organism under study. In this paper, we present the AliceDB database, which contains information on over 7 million natural variants of protein sequences described in the scientific literature for Homo sapiens. The data contained in the AliceDB database can be utilized using widely available and commonly used software for interpreting proteomic data. Test results regarding the use of the AliceDB database for the interpretation of proteomic data indicate that accounting for the presence of natural variants increases both the number and quality of identified proteins. Furthermore, it is easy to identify protein sequence variants that may, for example, be of significance in medicine.

25.
arXiv (CS.LG) 2026-06-19

An adaptive framework for the axisymmetric pulsar magnetosphere using physics-informed Kolmogorov-Arnold networks

arXiv:2606.10686v2 Announce Type: replace-cross Abstract: The pulsar magnetosphere has only recently been addressed using Physics-Informed Neural Networks (PINNs), by deploying a domain-decomposition approach and treating the separatrix and equatorial current sheet as infinitesimally thin discontinuities. However, this baseline requires extensive manual hyperparameter tuning, achieves limited final accuracy and demands several hours of training. We refine this framework by introducing domain-specific neural architectures based on Kolmogorov-Arnold networks, an automated adaptive training pipeline and a physics-based convergence criterion that eliminate the need for manual calibration. The proposed methodology delivers self-consistent axisymmetric magnetosphere solutions with mean squared errors of the PDE residuals at O(1e-6) in double precision - an improvement of two orders of magnitude over the baseline - while achieving convergence in under 20 minutes in single precision. Importantly, the method reliably resolves stellar radii reduced by up to 80% compared to the baseline, overcoming the severe spatial scale disparities that also challenge traditional solvers. Furthermore, by varying the flux that opens to infinity, we provide a correction to the equation that connects it to the equatorial T-point's position. The complete framework is released as the open-source library PulsarX.