arXiv:2605.01109v1 Announce Type: new Abstract: Phylogenetic trees are the primary framework for conveying evolutionary relationships. While many tools exist for visualizing phylogenetic trees, most are limited to static graphics, require coding expertise, or are developed for a specific website and not easily reusable or extensible. To address these limitations, we developed heat-tree, a collection of […]
Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI
arXiv:2605.01240v1 Announce Type: cross Abstract: Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored. In this work, we introduce Rhamba, a region-aware pretraining framework that integrates anatomically guided masking with hybrid Attention-Mamba architectures for resting state functional magnetic resonance imaging (fMRI) analysis. Models were pretrained […]
Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
arXiv:2504.10063v4 Announce Type: replace-cross Abstract: Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting, which leverages a topological divergence metric to quantify the structural properties of graphs induced by attention matrices. Examining the topological divergence between prompt and […]
New Bounds for Zarankiewicz Numbers via Reinforced LLM Evolutionary Search
arXiv:2605.01120v1 Announce Type: new Abstract: The Zarankiewicz number $textbfZ(m, n, s, t)$ is the maximum number of edges in a bipartite graph $G_m, n$ such that there is no complete $K_s, t$ bipartite subgraph. We determine for the first time the exact values of three Zarankiewicz numbers: $textbfZ(11, 21, 3, 3)=116$, $textbfZ(11, 22, 3, 3)=121$, […]
AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification
arXiv:2605.01355v1 Announce Type: cross Abstract: Automated leaf disease classification is critical for early disease detection in resource-constrained field environments. Vision Transformers (ViTs) provide strong representation capability by modeling long-range dependencies and inter-class relationships; however, their high computational cost makes them impractical for deployment on edge devices. As a result, existing approaches struggle to effectively transfer […]
Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
arXiv:2509.10468v2 Announce Type: replace-cross Abstract: Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized for different objectives: semantic reconstruction during tokenizer pretraining […]
Investigating the Effects of Different Levels of User Control in an Interactive Educational Recommender System
arXiv:2605.01400v1 Announce Type: cross Abstract: Educational recommender systems (ERSs) are becoming increasingly important in enhancing educational outcomes and personalizing learning experiences by providing recommendations of personalized resources and activities to learners, tailored to their individual learning needs. While user control is widely assumed to improve user experience, the effects of different levels of control in […]
PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs
arXiv:2605.01123v1 Announce Type: new Abstract: Large language models (LLMs) can provide automated feedback in educational settings, but aligning an LLMs style with a specific instructors tone while maintaining diagnostic correctness remains challenging. We ask how can we update an LLM for automated feedback generation to align with a target instructors style without sacrificing core knowledge? […]
Decision Boundary-aware Generation for Long-tailed Learning
arXiv:2605.01468v1 Announce Type: cross Abstract: Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the generator bias inherit from long-tailed dataset. However, we show that while head-to-tail transfer helps balance the decision space of the classifier, […]
Exact inference via quasi-conjugacy in two-parameter Poisson-Dirichlet hidden Markov models
arXiv:2512.22098v3 Announce Type: replace-cross Abstract: We introduce a nonparametric model for time-evolving, unobserved probability distributions from discrete-time data consisting of unlabelled partitions. The latent process is a two-parameter Poisson-Dirichlet diffusion, and observations arise via exchangeable sampling. Applications include social and genetic data where only aggregate clustering summaries are observed. To address the intractable likelihood, we […]
Mesh Based Simulations with Spatial and Temporal awareness
arXiv:2605.01542v1 Announce Type: cross Abstract: Machine Learning surrogates for Computational Fluid Dynamics (CFD), particularly Graph Neural Networks (GNNs) and Transformers, have become a new important approach for accelerating physics simulations. However, we identify a critical bottleneck in the field: while architectures have advanced significantly, the common underlying training paradigms remain bound to naive assumptions, such […]
Iterative Finetuning is Mostly Idempotent
arXiv:2605.01130v1 Announce Type: new Abstract: If a model has some behavioral tendency, such as sycophancy or misalignment, and it is trained on its own outputs, will the tendency be amplified in the next generation of models? We study this question by training a series of models where each model is finetuned on data generated by […]