As AI tools become increasingly common for research ideation, robust evaluation is critical to ensure the validity and usefulness of generated ideas. We introduce ScholarEval, a retrieval augmented evaluation framework that assesses research ideas based on two fundamental criteria: soundness - the empirical validity of proposed methods based on existing literature, and contribution - the degree of advancement made by the idea across different dimensions relative to prior research. To evaluate ScholarEval, we introduce ScholarIdeas, the first expert-annotated dataset of multi-domain research ideas and reviews, comprised of 117 ideas across four disciplines: artificial intelligence, neuroscience, biochemistry, and ecology. Our evaluation shows that ScholarEval achieves significantly higher coverage of points mentioned in the human expert annotated rubrics in ScholarIdeas compared to all baselines. Furthermore, ScholarEval is consistently preferred over our strongest baseline o4-mini-deep-research, a reasoning and search-enabled agentic system by OpenAI, in terms of evaluation actionability, depth, and evidence support. Our large-scale user study also shows that ScholarEval significantly outperforms deep research in literature engagement, idea refinement, and usefulness. We openly release our code, dataset, and ScholarEval tool for the community to use and build on.

Climate change demands effective legislative action to mitigate its impacts. This study explores the application of machine learning (ML) to understand the progression of climate policy from announcement to adoption, focusing on policies within the European Green Deal. We present a dataset of 165 policies, incorporating text and metadata. We aim to predict a policy's progression status, and compare text representation methods, including TF-IDF, BERT, and ClimateBERT. Metadata features are included to evaluate the impact on predictive performance. On text features alone, ClimateBERT outperforms other approaches (RMSE = 0.17, R^2 = 0.29), while BERT achieves superior performance with the addition of metadata features (RMSE = 0.16, R^2 = 0.38). Using methods from explainable AI highlights the influence of factors such as policy wording and metadata including political party and country representation. These findings underscore the potential of ML tools in supporting climate policy analysis and decision-making.

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI) signals. This involves two stages: transforming fMRI signals into a latent space and then using a pretrained generative model to reconstruct images. The reconstruction quality depends on how similar the latent space is to the structure of neural activity and how well the generative model produces images from that space. Yet, it remains unclear which type of latent space best supports this transformation and how it should be organized to represent visual stimuli effectively. We present two key findings. First, fMRI signals are more similar to the text space of a language model than to either a vision based space or a joint text image space. Second, text representations and the generative model should be adapted to capture the compositional nature of visual stimuli, including objects, their detailed attributes, and relationships. Building on these insights, we propose PRISM, a model that Projects fMRI sIgnals into a Structured text space as an interMediate representation for visual stimuli reconstruction. It includes an object centric diffusion module that generates images by composing individual objects to reduce object detection errors, and an attribute relationship search module that automatically identifies key attributes and relationships that best align with the neural activity. Extensive experiments on real world datasets demonstrate that our framework outperforms existing methods, achieving up to an 8% reduction in perceptual loss. These results highlight the importance of using structured text as the intermediate space to bridge fMRI signals and image reconstruction.

Scientific literature is increasingly siloed by complex language, static disciplinary structures, and potentially sparse keyword systems, making it cumbersome to capture the dynamic nature of modern science. This study addresses these challenges by introducing an adaptable large language model (LLM)-driven framework to quantify thematic trends and map the evolving landscape of scientific knowledge. The approach is demonstrated over a 20-year collection of more than 1,500 engineering articles published by the Proceedings of the National Academy of Sciences (PNAS), marked for their breadth and depth of research focus. A two-stage classification pipeline first establishes a primary thematic category for each article based on its abstract. The subsequent phase performs a full-text analysis to assign secondary classifications, revealing latent, cross-topic connections across the corpus. Traditional natural language processing (NLP) methods, such as Bag-of-Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF), confirm the resulting topical structure and also suggest that standalone word-frequency analyses may be insufficient for mapping fields with high diversity. Finally, a disjoint graph representation between the primary and secondary classifications reveals implicit connections between themes that may be less apparent when analyzing abstracts or keywords alone. The findings show that the approach independently recovers much of the journal's editorially embedded structure without prior knowledge of its existing dual-classification schema (e.g., biological studies also classified as engineering). This framework offers a powerful tool for detecting potential thematic trends and providing a high-level overview of scientific progress.

Cancer exhibits diverse and complex phenotypes driven by multifaceted molecular interactions. Recent biomedical research has emphasized the comprehensive study of such diseases by integrating multi-omics datasets (genome, proteome, transcriptome, epigenome). This approach provides an efficient method for identifying genetic variants associated with cancer and offers a deeper understanding of how the disease develops and spreads. However, it is challenging to comprehend complex interactions among the features of multi-omics datasets compared to single omics. In this paper, we analyze lung cancer multi-omics datasets from The Cancer Genome Atlas (TCGA). Using four statistical methods, LIMMA, the T test, Canonical Correlation Analysis (CCA), and the Wilcoxon test, we identified differentially expressed genes across gene expression, DNA methylation, and miRNA expression data. We then integrated these multi-omics data using the Kernel Machine Regression (KMR) approach. Our findings reveal significant interactions among the three omics: gene expression, miRNA expression, and DNA methylation in lung cancer. From our data analysis, we identified 38 genes significantly associated with lung cancer. From our data analysis, we identified 38 genes significantly associated with lung cancer. Among these, eight genes of highest ranking (PDGFRB, PDGFRA, SNAI1, ID1, FGF11, TNXB, ITGB1, ZIC1) were highlighted by rigorous statistical analysis. Furthermore, in silico studies identified three top-ranked potential candidate drugs (Selinexor, Orapred, and Capmatinib) that could play a crucial role in the treatment of lung cancer. These proposed drugs are also supported by the findings of other independent studies, which underscore their potential efficacy in the fight against lung cancer.

While clustering methods such as spectral clustering and K-means effectively group genes by expression similarity, downstream interpretation is typically performed using enrichment-based statistics. These approaches provide high-level functional summaries but often fail to yield cluster-specific mechanistic insight or explicit links to supporting literature. As a result, biological interpretation frequently relies on manual curation, limiting reproducibility and scalability. Large language models (LLMs) have recently emerged as powerful tools for biomedical text mining and knowledge synthesis. Although LLMs can generate fluent biological narratives, they are optimized for linguistic coherence rather than evidential accountability. When applied directly to transcriptomic interpretation, they may produce plausible but unverifiable statements, omit explicit citations, or hallucinate unsupported claims. While retrieval-augmented and agentic systems partially address this issue, systematic verification and critic-based validation remain underexplored. This limitation is particularly consequential for antimicrobial resistance research in Salmonella enterica, a major foodborne pathogen responsible for substantial global morbidity.

Abstract--Domain Incremental Learning (DIL) is a continual learning sub-branch that aims to address never-ending arrivals of new domains without catastrophic forgetting problems. Despite the advent of parameter-efficient fine-tuning (PEFT) approaches, existing works create task-specific LoRAs overlooking shared knowledge across tasks. Inaccurate selection of task-specific LORAs during inference results in significant drops in accuracy, while existing works rely on linear or prototype-based classifiers, which have suboptimal generalization powers. Our paper proposes continual knowledge consolidation low rank adaptation (CONEC-LoRA) addressing the DIL problems. CONEC-LoRA is developed from consolidations between task-shared LORA to extract common knowledge and task-specific LORA to embrace domain-specific knowledge. Unlike existing approaches, CONEC-LoRA integrates the concept of a stochastic classifier whose parameters are sampled from a distribution, thus enhancing the likelihood of correct classifications. Last but not least, an auxiliary network is deployed to optimally predict the task-specific LoRAs for inferences and implements the concept of a different-depth network structure in which every layer is connected with a local classifier to take advantage of intermediate representations. This module integrates the ball-generator loss and transformation module to address the synthetic sample bias problem. Our rigorous experiments demonstrate the advantage of CONEC-LoRA over prior arts in 4 popular benchmark problems with over 5% margins. ONTINUAL learning (CL) constitutes a research area of growing interests where the main goal is to develop a learning agent that can accumulate knowledge overtime [1], [2], [3], [4].

Billions of dollars are lost every year in DeFi platforms by transactions exploiting business logic or accounting vulnerabilities. Existing defenses focus on static code analysis, public mempool screening, attacker contract detection, or trusted off-chain monitors, none of which prevents exploits submitted through private relays or malicious contracts that execute within the same block. We present the first decentralized, fully on-chain learning framework that: (i) performs gas-prohibitive computation on Layer-2 to reduce cost, (ii) propagates verified model updates to Layer-1, and (iii) enables gas-bounded, low-latency inference inside smart contracts. A novel Proof-of-Improvement (PoIm) protocol governs the training process and verifies each decentralized micro update as a self-verifying training transaction. Updates are accepted by \textit{PoIm} only if they demonstrably improve at least one core metric (e.g., accuracy, F1-score, precision, or recall) on a public benchmark without degrading any of the other core metrics, while adversarial proposals get financially penalized through an adaptable test set for evolving threats. We develop quantization and loop-unrolling techniques that enable inference for logistic regression, SVM, MLPs, CNNs, and gated RNNs (with support for formally verified decision tree inference) within the Ethereum block gas limit, while remaining bit-exact to their off-chain counterparts, formally proven in Z3. We curate 298 unique real-world exploits (2020 - 2025) with 402 exploit transactions across eight EVM chains, collectively responsible for \$3.74 B in losses.

Symmetries are known to improve the empirical performance of machine learning models, yet theoretical guarantees explaining these gains remain limited. Prior work has focused mainly on compact group symmetries and often assumes that the data distribution itself is invariant, an assumption rarely satisfied in real-world applications. In this work, we extend generalization guarantees to the broader setting of non-compact symmetries, such as translations and to non-invariant data distributions. Building on the PAC-Bayes framework, we adapt and tighten existing bounds, demonstrating the approach on McAllester's PAC-Bayes bound while showing that it applies to a wide range of PAC-Bayes bounds. We validate our theory with experiments on a rotated MNIST dataset with a non-uniform rotation group, where the derived guarantees not only hold but also improve upon prior results. These findings provide theoretical evidence that, for symmetric data, symmetric models are preferable beyond the narrow setting of compact groups and invariant distributions, opening the way to a more general understanding of symmetries in machine learning.

Inferring causal relationships between variable pairs in the observational study is crucial but challenging, due to the presence of unmeasured confounding. While previous methods employed the negative controls to adjust for the confounding bias, they were either restricted to the discrete setting (i.e., all variables are discrete) or relied on strong assumptions for identification. To address these problems, we develop a general nonparametric approach that accommodates both discrete and continuous settings for testing causal hypothesis under unmeasured confounders. By using only a single negative control outcome (NCO), we establish a new identification result based on a newly proposed integral equation that links the outcome and NCO, requiring only the completeness and mild regularity conditions. We then propose a kernel-based testing procedure that is more efficient than existing moment-restriction methods. We derive the asymptotic level and power properties for our tests. Furthermore, we examine cases where our procedure using only NCO fails to achieve identification, and introduce a new procedure that incorporates a negative control exposure (NCE) to restore identifiability. We demonstrate the effectiveness of our approach through extensive simulations and real-world data from the Intensive Care Data and World Values Survey.