Isolater - Feed

Ax Viktor Martinek, Roland Herzog 3/31/2026

Symbolic Regression for Shared Expressions: Introducing Partial Parameter Sharing

Symbolic regression with partial parameter sharing for discovering expressions describing related phenomena with varying parameters.

Ax Huyen Vo, Isabel Valera 3/31/2026

Hellinger Multimodal Variational Autoencoders

Hellinger multimodal VAEs using probabilistic opinion pooling to aggregate unimodal inference distributions.

Ax Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, Jing Zhang 3/31/2026

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts

Sparse-RL addresses memory bottleneck in LLM reinforcement learning by reducing KV cache overhead during long-horizon rollouts.

Ax Haonan Yang, Jianchao Tang, Zhuo Li 3/31/2026

Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting

Dual-prototype disentanglement framework for context-aware time series forecasting using dynamic temporal pattern learning.

Ax Spyros Rigas, Thanasis Papaioannou, Panagiotis Trakadas, Georgios Alexandridis 3/31/2026

A Dynamic Framework for Grid Adaptation in Kolmogorov-Arnold Networks

Generalized framework for adaptive grid allocation in Kolmogorov-Arnold Networks accounting for target function complexity.

Ax Xinyu Zhou, Jiawei Zhang, Stephen J. Wright 3/31/2026

Smoothing the Score Function for Generalization in Diffusion Models: An Optimization-based Explanation Framework

Theoretical framework explaining memorization in diffusion models through weighted sum of empirical score functions.

Ax Zizheng Zhang, Yuyang Liao, Chen Chen, Jian He, Dun Wu, Qianjin Yu, Yanqin Gao, Jin Yang, Kailai Zhang, Eng Siong Chng, Xionghu Zhong 3/31/2026

TextBFGS: A Case-Based Reasoning Approach to Code Optimization via Error-Operator Retrieval

TextBFGS applies case-based reasoning to iterative code generation with LLMs, using past solutions to guide optimization.

Ax Alexander H\"au{\ss}er 3/31/2026

Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

Benchmarks Echo State Networks for univariate time series forecasting against traditional statistical methods on M4 dataset.

Ax Pengcheng Wang, Qinghang Liu, Haotian Lin, Yiheng Li, Guojian Zhan, Masayoshi Tomizuka, Yixiao Wang 3/31/2026

DADP: Domain Adaptive Diffusion Policy

Domain adaptive diffusion policy for control that generalizes to unseen transition dynamics through domain representation learning.

Ax Zhiqi Yu, Zhangquan Chen, Mengting Liu, Heye Zhang, Liangqiong Qu 3/31/2026

Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation

Analyzes GRPO limitations in exploration and difficulty adaptation for LLM reasoning, proposing improvements to advantage symmetry.

Ax Amin Oji, Paul Fieguth 3/31/2026

Joint Embedding Variational Bayes

VJE framework for self-supervised learning using reconstruction-free latent variables with symmetric conditional ELBO optimization.

Ax Mounir Lbath (X), Alexandre Paresy (X), Abdelkayoum Kaddouri (X), Abdelrahman Zighem (ENS-PSL), Alan Andr\'e (X), Alexandre Ittah (X), Jill-J\^enn Vie (SODA) 3/31/2026

Live Knowledge Tracing: Real-Time Adaptation using Tabular Foundation Models

Applies tabular foundation models to knowledge tracing for real-time student learning prediction without extensive offline training.

Ax Nghia Nguyen, Tianjiao Ding, Ren\'e Vidal 3/31/2026

Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification

Interpretable image classification using hierarchical concept embeddings recovered from vision-language models.

Ax Thanh-Dat Truong, Huu-Thien Tran, Jackson Cothren, Bhiksha Raj, Khoa Luu 3/31/2026

$\phi$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

φ-DPO addresses fairness in continual learning for multimodal models when training data is imbalanced across tasks.

Ax Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang 3/31/2026

Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection

Reduces transformer KV cache by using low-dimensional keys for attention selection while maintaining full-dimensional values.

Ax Jonas Landsgesell, Pascal Knoll 3/31/2026

Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predictions via Proper Scoring Rules

Proposes using proper scoring rules to evaluate probabilistic predictions from tabular foundation models instead of point-estimate metrics.

Ax Shubham Aggarwal, Lokendra Kumar 3/31/2026

Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers

Replaces dense attention projections with Walsh Hadamard Transforms to reduce transformer parameters by 25% while maintaining performance.

Ax Yongqiang Chen, Chenxi Liu, Zhenhao Chen, Tongliang Liu, Bo Han, Kun Zhang 3/31/2026

CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad

LLM agent framework with causal scratchpad for open-ended scientific discovery through iterative program evolution.

Ax Yuri Kinoshita, Naoki Nishikawa, Taro Toyoizumi 3/31/2026

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks

Theoretical analysis of dataset distillation for encoding low-dimensional task representations from gradient-based learning.

Ax Koichi Tanaka, Ren Kishimoto, Bushun Kawagishi, Yusuke Narita, Yasuo Yamamoto, Nobuyuki Shimizu, Yuta Saito 3/31/2026

Off-Policy Learning with Limited Supply

Off-policy learning framework for contextual bandits with constrained item supply in recommendation and advertising.

Ax Qi Luo, Minghui Xu, Dongxiao Yu, Xiuzhen Cheng 3/31/2026

Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs

Backdoor attack method on text-attributed graphs by injecting malicious cues into node text.

Ax Zakaria Mhammedi, James Cohan 3/31/2026

Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration

RL approach decoupling exploration and policy optimization using uncertainty-guided tree search for hard exploration problems.

Ax Yan Xie, Tiansheng Wen, Tangda Huang, Bo Chen, Chenyu You, Stefanie Jegelka, Yifei Wang 3/31/2026

Scaling Attention via Feature Sparsity

Sparse Feature Attention (SFA) method reducing transformer attention complexity via feature-level sparsity for ultra-long contexts.

Ax Eric Czech, Zhiwei Xu, Yael Elmatad, Yixin Wang, William Held 3/31/2026

Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits

Analysis of systematic biases in Chinchilla Approach 2 neural scaling law fits for compute-optimal LLM allocation.

Ax YanZhao Zheng, ZhenTao Zhang, Chao Ma, YuanQiang Yu, JiHuai Zhu, Yong Wu, Tianze Xu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu 3/31/2026

SkillRouter: Skill Routing for LLM Agents at Scale

Skill routing system for LLM agents managing and selecting from large skill ecosystems at inference time.

Ax Seungju Han, Konwoo Kim, Chanwoo Park, Benjamin Newman, Suhas Kotha, Jaehun Jung, James Zou, Yejin Choi 3/31/2026

Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG

Synthetic Mixed Training method combining synthetic QAs and documents to scale LLM knowledge acquisition beyond RAG limitations.

Ax Fabio Ferreira, Lucca Wobbe, Arjun Krishnakumar, Frank Hutter, Arber Zela 3/31/2026

Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch

Study comparing LLM agents against classical hyperparameter optimization algorithms using autoresearch framework for hyperparameter tuning.

Ax Bhavya Kohli, Biplab Sikdar 3/31/2026

PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing

Attack method (PEANUT) exploiting GNN vulnerabilities through graph topology perturbations in message passing.

Ax Fadoua Amri-Jouidel, Emmanuel Kemel, St\'ephane Mussard 3/31/2026

Shapley meets Rawls: an integrated framework for measuring and explaining unfairness

Framework using Shapley values to measure and explain unfairness in ML models under group fairness criteria.

Ax Mohamed elShehaby, Ashraf Matrawy 3/31/2026

Evasion Adversarial Attacks Remain Impractical Against ML-based Network Intrusion Detection Systems, Especially Dynamic Ones

Study on adversarial evasion attacks against ML-based network intrusion detection systems, showing attacks remain impractical against dynamic systems.

Ax Jeongmin Brian Park, Kun Wu, Vikram Sharma Mailthody, Zaid Quresh, Scott Mahlke, Wen-mei Hwu 3/31/2026

LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme

Multi-GPU GNN training system optimizing data transfer for large-scale graphs exceeding GPU memory capacity via storage-based approaches.

Ax Jinlin Lai, Antonio Linero, Yuling Yao 3/31/2026

Predictive variational inference: Learn the predictively optimal posterior distribution

Framework for variational inference that optimizes posterior distributions under model misspecification for better predictive accuracy.

Ax Boxin Zhao, Cong Ma, Mladen Kolar 3/31/2026

Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation

Transfer learning method for precision matrix estimation leveraging related source data with limited target samples.

Ax Yilie Huang, Yanwei Jia, Xun Yu Zhou 3/31/2026

Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study

RL approach for continuous-time portfolio selection using unknown diffusion processes, with data-driven strategy learning.

Ax Yiran Huang, Jian-Feng Yang, Haoda Fu 3/31/2026