Isolater - Feed

Ax Hao Chen, Tao Han, Jie Zhang, Song Guo, Lei Bai 3d ago

STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting

Spatial-temporal weather forecasting with adaptive boundary alignment for regional integration from global atmosphere predictions.

Ax Rongguang Ye, Ming Tang, Edith C. H. Ngai 3d ago

On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs

Configuration-aware LoRA adaptation for quantized LLMs enabling efficient edge device deployment with heterogeneous capabilities.

Ax ShengYun Peng, Eric Smith, Ivan Evtimov, Song Jiang, Pin-Yu Chen, Hongyuan Zhan, Haozhu Wang, Duen Horng Chau, Mahesh Pasupuleti, Jianfeng Chi 3d ago

Large Reasoning Models Learn Better Alignment from Flawed Thinking

RECAP: RL method for safety alignment in large reasoning models, teaching critical evaluation of flawed premises via counter-aligned prefilling.

Ax Justus Arweiler, Indra Jungjohann, Aparna Muraleedharan, Heike Leitte, Jakob Burger, Kerstin M\"unnemann, Fabian Jirasek, Hans Hasse 3d ago

Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods

Open dataset of batch distillation experiments for developing ML anomaly detection methods in chemical processes.

Ax Mary E. An, Paul M. Griffin, Jonathan G. Stine, Balakrishnan S. Ramakrishna, Soundar R. T. Kumara 3d ago

Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study

Machine learning models for metabolic liver disease prediction from EHR data, comparing LASSO, random forests, and neural networks.

Ax Thaweerath Phisannupawong, Joshua Julian Damanik, Han-Lim Choi 3d ago

LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation

LLM-based flight delay prediction integrating textual aeronautical data and aircraft trajectories for air traffic management.

Ax Xin He, Yili Wang, Yiwei Dai, Xin Wang 3d ago

Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling

Graph neural network architecture using selective state space modeling to address over-smoothing in deep GNNs via node-specific representation evolution.

Ax Zhangyu Ge, Xu He, Lingfei Mo, Xiaolin Meng, Wenxuan Yin, Youdong Zhang, Lansong Jiang, Fengyuan Liu 3d ago

Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics

Optimization of continuous attractor neural networks for brain-inspired path integration, reducing computational redundancy in navigation systems.

Ax Lei Xiao, Jifeng Li, Juntao Gao, Feiyang Ye, Yan Jin, Jingjing Qian, Jing Zhang, Yong Wu, Xiaoyuan Yu 3d ago

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

Vision-Language-Action model with active visual attention for robotic manipulation, extending from Markov to partially observable decision processes.

Ax Haoming Liu, Jinnuo Liu, Yanhao Li, Liuyang Bai, Yunkai Ji, Yuanhe Guo, Shenji Wan, Hongyi Wen 3d ago

From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity

Analysis of flow-based diffusion models revealing two-stage behavior through oracle velocity fields, focusing on memorization-generalization dynamics.

Ax Giray \"On\"ur, Azita Dabiri, Bart De Schutter 3d ago

Adaptive Tuning of Parameterized Traffic Controllers via Multi-Agent Reinforcement Learning

Multi-agent RL framework for adaptive traffic signal control, replacing static controllers with learning-based optimization for complex traffic dynamics.

Ax Wei Duan, Jie Lu, En Yu, Junyu Xuan 3d ago

Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning

Multi-agent RL for graph-based coordination with bandwidth constraints, addressing what information agents should transmit under communication limits.

Ax Zibo Zhao (Arizona State University), Yuanting Zha (ShanghaiTech University), Haipeng Zhang (ShanghaiTech University), Xingcheng Xu (Shanghai Artificial Intelligence Laboratory) 3d ago

The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs

Analysis of self-reflection emergence in LLMs through RL post-training, using gradient attribution to explain distinct solution generation and revision capabilities.

Ax Prakash Gawas, Antoine Legrain, Louis-Martin Rousseau 3d ago

Imitation Learning for Combinatorial Optimisation under Uncertainty

Imitation learning framework for combinatorial optimization problems, examining how expert demonstrations affect policy learning in sequential decision problems.

Ax Zhaopeng Qiu, Shuang Yu, Jingqi Zhang, Shuai Zhang, Xue Huang, Jingyi Yang, Junjie Lai 3d ago

FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning

FP8 low-precision quantization for LLM reinforcement learning, addressing memory and compute bottlenecks in rollout generation with engineering and algorithmic solutions.

Ax Safal Shrestha, Anubhav Shrestha, Aadim Nepal, Minwu Kim, Keith Ross 3d ago

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models

Demonstrates layer pruning limitations for LLM reasoning tasks, showing pruned models lose algorithmic capabilities despite compression on classification tasks.

Ax Arnav Shah, Junzhe Li, Parsa Idehpour, Adibvafa Fallahpour, Brandon Wang, Sukjun Hwang, Bo Wang, Patrick D. Hsu, Hani Goodarzi, Albert Gu 3d ago

dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning

dnaHNet foundation model for genomic sequence learning with tokenizer-free design preserving biological motifs while handling long contexts efficiently.

Ax Adolfo Gonz\'alez, V\'ictor Parada 3d ago

An Adaptive Model Selection Framework for Demand Forecasting under Horizon-Induced Degradation to Support Business Strategy and Operations

Adaptive model selection framework for demand forecasting addressing horizon-induced degradation across heterogeneous inventory portfolios.

Ax Ammar Kheder, Helmi Toropainen, Wenqing Peng, Samuel Ant\~ao, Jia Chen, Michael Boy, Zhi-Song Liu 3d ago

TopoFlow: Topography-aware Pollutant Flow Learning for High-Resolution Air Quality Prediction

Physics-guided neural network for high-resolution air quality prediction incorporating topography and wind direction as critical factors.

Ax Rong Fu, Zijian Zhang, Kun Liu, Jiekai Wu, Xianda Li, Simon Fong 3d ago

SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework

SubQuad pipeline for adaptive immune repertoire analysis combining subquadratic retrieval with learned multimodal fusion for clinical clonotype detection.

Ax Zhaoyang Zhang, Shuli Jiang, Yantao Shen, Yuting Zhang, Dhananjay Ram, Shuo Yang, Zhuowen Tu, Wei Xia, Stefano Soatto 3d ago

Reinforcement-aware Knowledge Distillation for LLM Reasoning

Reinforcement-aware knowledge distillation method for distilling RL-trained reasoning LLMs into smaller models while preserving chain-of-thought capability.

Ax Hiroki Matsutani, Naoki Matsuda, Naoto Sugiura 3d ago

Accelerating Local LLMs on Resource-Constrained Edge Devices via Distributed Prompt Caching

Distributed prompt caching technique for accelerating local LLM inference on resource-constrained edge devices via inter-device state sharing.

Ax Jiawen Li 3d ago

Implicit Bias in Deep Linear Discriminant Analysis

Analyzes implicit regularization of Deep LDA objective for scale-invariant discriminative metric learning.

Ax Ruinan Jin, Yingbin Liang, Shaofeng Zou 3d ago

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

Theoretical analysis explaining Adam's empirical advantage over SGD through second-moment normalization using stopping-time/martingale analysis.

Ax Lukas K\"onig, Manuel Kuhn, David Kappel, Anand Subramoney 3d ago

Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAX

Enables exact gradient computation for spiking neural networks via differentiable ODE solving in JAX, supporting arbitrary neuron models.

Ax Minh-Duong Nguyen, Thien-Thanh Dao, Le-Tuan Nguyen, Dung D. Le, Kok-Seng Wong 3d ago

Memory-efficient Continual Learning with Prototypical Exemplar Condensation

Proposes prototypical exemplar condensation for memory-efficient continual learning, reducing stored samples per class from 20+ to single digits.

Ax Foo Hui-Mean, Yuan-chin I Chang 3d ago

ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization

ALMAB-DC framework combines active learning, multi-armed bandits, and distributed computing for expensive black-box optimization.

Ax Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey 3d ago

Mechanisms of Introspective Awareness

Investigates mechanisms of introspective awareness in LLMs, where models detect injected steering vectors with minimal false positives.

Ax M Jawad, HV Gupta, YH Wang, MA Farmani, A Behrangi, GY Niu 3d ago

Improving Model Performance by Adapting the KGE Metric to Account for System Non-Stationarity

Adapts KGE metric for non-stationary geoscientific systems in water management applications.

Ax Zequn Chen, Wesley J. Marrero 3d ago

Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications

Analyzes distributional reinforcement learning with applications to healthcare, moving beyond expectation-based objectives for uncertain domains.

Ax Ximing Xing, Ziteng Xue, Zhenxi Li, Weicong Liang, Linqing Wang, Zhantao Yang, Tiankai Hang, Zijin Yin, Qinglin Lu, Chunyu Wang, Qian Yu 3d ago

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

Proposes hierarchical SVG tokenization approach for improved scalable vector graphics modeling with LLMs via geometric-aware token design.

Ax Jingwei Zuo, Xinze Feng, Zien Liu, Kaijian Wang, Fanjiang Ye, Ye Cao, Zhuang Wang, Yuke Wang 3d ago

ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads

ALTO system for adaptive hyperparameter tuning and orchestration of LoRA fine-tuning jobs across heterogeneous multi-tenant environments.

Ax Dipan Maity, Suman Mondal, Arindam Roy 3d ago

Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating

Introduces Gated-SwinRMT, a vision transformer combining Swin attention with Manhattan-distance decay for improved spatial modeling.

Ax Yuanjie Shi, Peihong Li, Zijian Zhang, Janardhan Rao Doppa, Yan Yan 3d ago

Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise

Proposes CMRM, a framework for improving classification under label noise without privileged knowledge, using quantile-calibrated regularization.

Ax Rui Dong, Zitong Wang, Jiaxing Li, Weihuang Zheng, Youyong Kong 3d ago

BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis

Combines LLMs with Graph Neural Networks to enhance fMRI brain network analysis by leveraging LLM representations.

Ax Constantin Le Cle\"i, Nils Thuerey, Xiaoxiang Zhu 3d ago

Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training

Bias-constrained diffusion schedules for PDE emulation with improved reconstruction error and efficient unrolled training.

Ax Jung-Hoon Cho, Sirui Li, Jeongyun Kim, Cathy Wu 3d ago

Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy

Temporal transfer learning approach for traffic optimization using real-time driving advisories for connected vehicles.

Ax Andrea Nini, Oren Halvani, Lukas Graner, Sophie Titze, Valerio Gherardi, Shunichi Ishihara 3d ago

Grammar as a Behavioral Biometric: Using Cognitively Motivated Grammar Models for Authorship Verification

Uses cognitively motivated grammar models as behavioral biometrics for authorship verification in digital forensics.

Ax Xin He, Wenqi Fan, Ruobing Wang, Yili Wang, Ying Wang, Shirui Pan, Xin Wang 3d ago

Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias

Social recommendation model using condition-guided approach to mitigate popularity bias in recommendation systems.

Ax Lorenzo Mannocci, Michele Mazza, Anna Monreale, Maurizio Tesconi, Stefano Cresci 3d ago