arXiv:2510.20861v1 Announce Type: new Abstract: Fuzzy numbers are commonly represented with fuzzy sets. Their objective is to better represent imprecise data. However, operations on fuzzy numbers are not as straightforward as maths on crisp numbers. Commonly, the Zadeh’s extension rule is applied to elaborate a result. This can produce two problems: (1) high computational complexity […]
Bridging Language Gaps with Adaptive RAG: Improving Indonesian Language Question Answering
arXiv:2510.21068v1 Announce Type: cross Abstract: Question Answering (QA) has seen significant improvements with the advancement of machine learning models, further studies enhanced this question answering system by retrieving external information, called Retrieval-Augmented Generation (RAG) to produce more accurate and informative answers. However, these state-of-the-art-performance is predominantly in English language. To address this gap we made […]
BASIN: Bayesian mAtrix variate normal model with Spatial and sparsIty priors in Non-negative deconvolution
arXiv:2510.16130v2 Announce Type: replace Abstract: Spatial transcriptomics allows researchers to visualize and analyze gene expression within the precise location of tissues or cells. It provides spatially resolved gene expression data but often lacks cellular resolution, necessitating cell type deconvolution to infer cellular composition at each spatial location. In this paper we propose BASIN for cell […]
Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
arXiv:2510.21090v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approach similar to behavior cloning, often struggles with overfitting and poor out-of-domain generalization, especially in limited-data scenarios. To address these limitations, we propose Self-Rewarding PPO, a novel […]
Ultra-wideband radar to measure in vivo musculoskeletal forces
arXiv:2510.20866v1 Announce Type: new Abstract: Accurate measures of musculoskeletal forces are critical for clinicians, biomechanists, and engineers, yet direct measurement is highly invasive and current estimation methods remain limited in accuracy. Here, we demonstrate the application of ultra-wideband radar to non-invasively estimate musculoskeletal forces by measuring changes in the electromagnetic properties of contracting muscles, in […]
Generalizable Hierarchical Skill Learning via Object-Centric Representation
arXiv:2510.21121v1 Announce Type: cross Abstract: We present Generalizable Hierarchical Skill Learning (GSL), a novel framework for hierarchical policy learning that significantly improves policy generalization and sample efficiency in robot manipulation. One core idea of GSL is to use object-centric skills as an interface that bridges the high-level vision-language model and the low-level visual-motor policy. Specifically, […]
On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
arXiv:2410.04108v3 Announce Type: replace-cross Abstract: Reinforcement learning with general utilities (RLGU) offers a unifying framework to capture several problems beyond standard expected returns, including imitation learning, pure exploration, and safe RL. Despite recent fundamental advances in the theoretical analysis of policy gradient (PG) methods for standard RL and recent efforts in RLGU, the understanding of […]
Spatially inhomogeneous two-cycles in an integrodifference equation
arXiv:2510.21134v1 Announce Type: cross Abstract: In this work, we prove the existence of a 2-cycle in an integrodifference equation with a Laplace kernel and logistic growth function, connecting two non-trivial fixed points of the second iterate of the logistic map in the non-chaotic regime. This model was first studied by Kot (1992), and the 2-cycle […]
Scalable inference of functional neural connectivity at submillisecond timescales
arXiv:2510.20966v1 Announce Type: new Abstract: The Poisson Generalized Linear Model (GLM) is a foundational tool for analyzing neural spike train data. However, standard implementations rely on discretizing spike times into binned count data, limiting temporal resolution and scalability. Here, we develop Monte Carlo (MC) methods and polynomial approximations (PA) to the continuous-time analog of these […]
Interpretable Next-token Prediction via the Generalized Induction Head
arXiv:2411.00066v2 Announce Type: replace-cross Abstract: While large transformer models excel in predictive performance, their lack of interpretability restricts their usefulness in high-stakes domains. To remedy this, we propose the Generalized Induction-Head Model (GIM), an interpretable model for next-token prediction inspired by the observation of “induction heads” in LLMs. GIM is a retrieval-based module that identifies […]