Isolater - Feed

Ax Mehran Taghian, Yunke Peng, Xing Huang, Yao Wang, Yaoyuan Wang, Wei Guo, Yuanyong Luo, Tianchi Hu, Junsong Wang, Xin Wang, Hu Liu, Yu Cheng, Ziwei Yu, Hongliang Li, Mehdi Rahimifar, Lei Yan, Xuefei Wang, Zhuang Ma, Lei Liu, Hui Yu, Anandharaju Durai Raju, Hoang Le, Hei Yi Mak, Tanzila Rahman, Shadan Golestan 4/13/2026

HiFloat4 Format for Language Model Pre-training on Ascend NPUs

4-bit floating-point format (HiFloat4) for efficient language model pre-training on Ascend NPU hardware.

Ax Chia-Hong Hsu, Randall Balestriero 4/13/2026

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning

Guidance method for consistency models using joint flow distribution learning to enable classifier-free guidance without separate teacher model.

Ax Chia-Hong Hsu, Frank Wood 4/13/2026

Discrete Meanflow Training Curriculum

Training curriculum method for discrete flow-based image generation models to improve one-step sampling stability and quality.

Ax Roi Paul 4/13/2026

Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance

Analysis of LoRA adapter spectral geometry to identify fine-tuning objectives and predict harmful model behavior in language models.

Ax Jinqi Luo, Jinyu Yang, Tal Neiman, Lei Fan, Bing Yin, Son Tran, Mubarak Shah, Ren\'e Vidal 4/13/2026

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

Safety steering mechanism for multimodal LLMs using dictionary-aligned concept control to prevent unsafe outputs without retraining.

Ax Yuwen Jiang 4/13/2026

Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds

Theoretical analysis of finite-sample properties and identifiability bounds for nonlinear Independent Component Analysis algorithms.

Ax Amrut Nadgir, Vijay Balasubramanian, Pratik Chaudhari 4/13/2026

How does Chain of Thought decompose complex tasks?

Demonstrates power-law scaling of classification error with number of classes and how chain-of-thought decomposition reduces error through task splitting.

Ax Tokio Kajitsuka, Ukyo Honda, Sho Takase 4/13/2026

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective

Practical analysis of chain-of-thought distillation from students to teachers, revisiting capacity gap assumptions and baseline comparisons.

Ax Abhiram Vellore, Niraj K. Jha 4/13/2026

Uncertainty-Aware Transformers: Conformal Prediction for Language Models

Conformal prediction framework for transformers providing uncertainty quantification and calibration for trustworthy LLM deployment.

Ax Hang Gao, Kunyu Li, Huang Hong, Baoquan Cui, Fengge Wu 4/13/2026

A Closer Look at the Application of Causal Inference in Graph Representation Learning

Analysis of causal inference applications in graph representation learning and risks of aggregating graph elements.

Ax Donney Fan, Geoff Pleiss 4/13/2026

Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization

Adaptive Thompson sampling for high-dimensional Bayesian optimization addressing sparse candidate point grids.

Ax Taojie Zhu, Dongyang Xu, Ding Zou, Sen Zhao, Qiaobo Hao, Zhiguo Yang, Yonghong He 4/13/2026

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning

Dynamic policy optimization bridging SFT and RL for LLMs, addressing bias-variance tradeoff in post-training through adaptive loss weighting.

Ax Zhipeng Zhou, Linxiao Cao, Pengcheng Wu, Peilin Zhao, Chunyan Miao 4/13/2026

Delve into the Applicability of Advanced Optimizers for Multi-Task Learning

Empirical study on effectiveness of advanced optimizers for multi-task learning, identifying overlooked factors in optimization approaches.

Ax Binesh Sadanandan, Vahid Behzadan 4/13/2026

Predictive Entropy Links Calibration and Paraphrase Sensitivity in Medical Vision-Language Models

Analyzes calibration and paraphrase sensitivity in medical vision-language models using predictive entropy and uncertainty quantification.

Ax Benjamin Amoh, Geoffrey Parker, Wesley Marrero 4/13/2026

Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication

SeqComm-DFL: Multi-agent coordination via sequential communication and decision-focused learning for value-aware message generation.

Ax Mintae Kim, Koushil Sreenath 4/13/2026

WOMBET: World Model-based Experience Transfer for Robust and Sample-efficient Reinforcement Learning

WOMBET: World model-based framework for experience transfer in robotics RL, generating and utilizing prior data for sample efficiency.

Ax Zhiqiang Dong, Teng Pang, Rongjian Xu, Guoqiang Wu 4/13/2026

Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning

Hierarchical implicit flow Q-learning for offline goal-conditioned reinforcement learning with improved policy expressiveness.

Ax Yueyuan Sui, Payal Mohapatra, Do\u{g}a\c{c} Eldenk, Haodong Yang, Yiting Zhang, Haoyan Zhang, Qi Zhu, Stephen Xia 4/13/2026

Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference

SentryFuse: Framework for efficient multimodal model compression on edge devices with sensor dropout robustness via zero-shot pruning.

Ax Yi Luo, Xu Sun, Guangchun Luo, Aiguo Chen 4/13/2026

Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning

Graph neural network architecture addressing heterophilic graphs using switchable attention mechanism for monophily-aware learning.

Ax Gyuwon Park, DongIl Shin, SolGil Oh, SangGi Ryu, Byung-Hak Kim 4/13/2026

The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge

Solution to NeurIPS 2023 LLM Efficiency Challenge: Fine-tuning LLaMA 70B on single A100 GPU within 24-hour constraint.

Ax Salva R\"uhling Cachay, Duncan Watson-Parris, Rose Yu 4/13/2026

U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

U-Cast: Efficient probabilistic weather forecasting model using standard U-Net architecture, simplifying state-of-art approaches.

Ax Min Young Baeg, Yoon-Yeong Kim 4/13/2026

PDE-regularized Dynamics-informed Diffusion with Uncertainty-aware Filtering for Long-Horizon Dynamics

PDYffusion: Diffusion model for long-horizon spatiotemporal prediction incorporating physics-based constraints and uncertainty quantification.

Ax Yu Chen, Weijun Lv, Yue Huang, Xiaozhao Fang, Jie Wen, Yong Xu, Guanbin Li 4/13/2026

Feature-Label Modal Alignment for Robust Partial Multi-Label Learning

Proposes PML-MA method for partial multi-label learning using feature-label modal alignment to handle noisy labels.

Ax Jafar Bakhshaliyev, Johannes Burchert, Niels Landwehr, Lars Schmidt-Thieme 4/13/2026

Temporal Patch Shuffle (TPS): Leveraging Patch-Level Shuffling to Boost Generalization and Robustness in Time Series Forecasting

arXiv paper proposing Temporal Patch Shuffle data augmentation for time series forecasting preserving temporal coherence and improving generalization.

Ax Harry Proshian, Nikita Severin, Sergey Nikolenko, Kireev Ivan, Andrey Savchenko, Ivan Sergeev, Maria Postnova, Ilya Makarov 4/13/2026

Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Models

arXiv paper integrating graph-based embeddings into event sequence models for user-item interactions in fraud and recommendation systems.

Ax Jiabao Brad Wang, Xiang Shi, Yiliang Yuan, Mustafa Misir 4/13/2026

GeoPAS: Geometric Probing for Algorithm Selection in Continuous Black-Box Optimisation

arXiv paper on GeoPAS geometric probing approach for automated algorithm selection in continuous black-box optimization.

Ax Yi-Lun Liao, Alexander J. Hoffman, Sabrina C. Shen, Alexandre Duval, Sam Walton Norwood, Tess Smidt 4/13/2026

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

arXiv paper on EquiformerV3, advancing SE(3)-equivariant graph attention Transformers for efficiency, expressivity, and 3D atomistic modeling.

Ax Yushi Feng, Junye Du, Qifan Wang, Zizhan Ma, Qian Niu, Yutaka Matsuo, Long Feng, Lequan Yu 4/13/2026

CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation

arXiv paper on CORA, conformal risk-controlled GUI agents using vision language models with formal safety guarantees for mobile automation.

Ax Xubin Zhou, Yipeng Yang, Zhan Li 4/13/2026

Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling

arXiv paper proposing truncated rectified flow policy for maximum entropy RL enabling one-step multimodal action distribution sampling.

Ax Jennifer Werner, Justus Arweiler, Indra Jungjohann, Jochen Schmid, Fabian Jirasek, Hans Hasse, Michael Bortz 4/13/2026

Automated Batch Distillation Process Simulation for a Large Hybrid Dataset for Deep Anomaly Detection

arXiv paper augmenting distillation process dataset with simulations for deep learning-based anomaly detection in chemical batch processes.

Ax Mansour Zoubeirou a Mayaki 4/13/2026

Generalization and Scaling Laws for Mixture-of-Experts Transformers

arXiv paper developing generalization and scaling theory for Mixture-of-Experts Transformers with covering-number bounds and routing overhead analysis.

Ax Anas Hattay, Fred Ngole Mboula, Eric Gascard, Zakaria Yahoun 4/13/2026

On the Role of DAG topology in Energy-Aware Cloud Scheduling : A GNN-Based Deep Reinforcement Learning Approach

arXiv paper on GNN-based deep reinforcement learning scheduler for cloud workflow DAGs optimizing completion time and energy consumption.

Ax Zedong Peng, Zeju Li, Qiang Xu, Jieru Zhao 4/13/2026

DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings

arXiv paper proposing DiffHLS framework using GNNs and LLM code embeddings for high-level synthesis quality prediction via differential learning.

Ax Huanran Chen, Huaqing Zhang, Xiao Li, Yinpeng Dong, Ke Shen, Jun Zhu 4/13/2026

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima

arXiv paper investigating LLM pretraining geometry and common minima to improve downstream generalization without changing loss function.

Ax Sifan Yang, Dan-Yue Li, Lijun Zhang 4/13/2026

Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications

arXiv paper on distributed online convex optimization with compressed communication, establishing optimal regret bounds for large-scale applications.

Ax Carl R. Richardson, Jichen Zhang, Ethan King, J\'an Drgo\v{n}a 4/13/2026

Stability Enhanced Gaussian Process Variational Autoencoders

Novel stability-enhanced Gaussian process VAE for training low-dimensional LTI systems from high-dimensional video data using probabilistic and physical models.

Ax G\"otz-Henrik Wiegand, Lorena Raichle, Rico St\"adeli, Tomas Hrycej, Bernhard Bermeitinger, Siegfried Handschuh 4/13/2026

Is More Data Worth the Cost? Dataset Scaling Laws in a Tiny Attention-Only Decoder

Controlled study of dataset scaling laws in attention-only decoder architecture across power-of-two subset sizes.

Ax Khoa Tran, Simon S. Woo 4/13/2026

Efficient Unlearning through Maximizing Relearning Convergence Delay

Machine unlearning approach using relearning convergence delay metric to remove contaminated data from pretrained models.

Ax Sakshi Choudhary, Utkarsh Saxena, Kaushik Roy 4/13/2026

OASIS: Online Activation Subspace Learning for Memory-Efficient Training

Online activation subspace learning (OASIS) to reduce memory requirements during LLM training through low-rank projections.

Ax Aishwarya Sarkar, Sayan Ghosh, Nathan R. Tallent, Ali Jannesari 4/13/2026

NOMAD: Generating Embeddings for Massive Distributed Graphs

Scalable method for generating node embeddings on massive distributed graphs with millions to billions of nodes.

Ax Ioannis Tsingalis, Constantine Kotropoulos, Corentin Briat 4/13/2026

AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning

AdaCubic optimizer using adaptive cubic regularization with Hutchinson's method for approximating Hessian in deep learning.

Ax Lifeng Chen, Tianqi You, Hao Liu, Zhimin Bao, Jile Jiao, Xiao Han, Zhicai Ou, Tao Sun, Xiaofeng Mou, Xiaojie Jin, Yi Xu 4/13/2026

ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion

One-step diffusion model for efficient chest X-ray report generation reducing inference latency compared to autoregressive models.

Ax Maksim Anisimov (Imperial College London), Francesco Belardinelli (Imperial College London), Matthew Wicker (Imperial College London) 4/13/2026

SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning

Method for safely updating deep reinforcement learning policies while preserving safety guarantees on previously encountered tasks.

Ax Luis Mickeler, Kai Lion, Alfonso Nardi, Jost Kellner, Pierre Didier, Bhavin J. Shastri, Niao He, Rachel Grange 4/13/2026

Integrated electro-optic attention nonlinearities for transformers

Hardware optimization using electro-optic nonlinearities to replace softmax bottleneck in transformer attention mechanisms.

Ax Igor Jankowski 4/13/2026

Event-Driven Temporal Graph Networks for Asynchronous Multi-Agent Cyber Defense in NetForge_RL

High-fidelity cyber operations simulator (NetForge_RL) using temporal graph networks for multi-agent reinforcement learning in cybersecurity.

Ax Jiawei Chen, Ruoxi Xu, Boxi Cao, Ruotong Pan, Yunfei Zhang, Yifei Hu, Yong Du, Tingting Gao, Yaojie Lu, Yingfei Sun, Xianpei Han, Le Sun, Xiangyu Wu, Hongyu Lin 4/13/2026

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

OmniBehavior benchmark for evaluating LLMs as user simulators on long-horizon, cross-scenario behavior traces from real-world data.

Ax Wenjie Qu, Xuandong Zhao, Jiaheng Zhang, Dawn Song 4/13/2026