Isolater - Feed

Ax Junxiong Wang, Fengxiang Bie, Jisen Li, Zhongzhu Zhou, Zelei Shao, Yubo Wang, Yinghui Liu, Qingyang Wu, Avner May, Sri Yanamandra, Yineng Zhang, Ce Zhang, Tri Dao, Percy Liang, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu 29d ago

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

Unified training-serving system combining RL with adaptive speculative decoding for accelerated LLM inference.

Ax J Rosser, Robert Kirk, Edward Grefenstette, Jakob Foerster, Laura Ruis 29d ago

Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions

Infusion: Framework using influence functions to craft training data perturbations that induce targeted model behavior changes.

Ax Zhongyao Wang, Taoyong Cui, Jiawen Zou, Shufei Zhang, Bo Yan, Wanli Ouyang, Weimin Tan, Mao Su 29d ago

Equivariant Evidential Deep Learning for Interatomic Potentials

Uncertainty quantification for machine learning interatomic potentials using evidential deep learning.

Ax Yongzhong Xu 29d ago

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking

Geometric analysis of optimization dynamics in transformers trained on modular arithmetic revealing low-dimensional subspaces.

Ax Yongzhong Xu 29d ago

Early-Warning Signals of Grokking via Loss-Landscape Geometry

Study on early-warning signals of grokking via loss-landscape geometry on SCAN and Dyck-1 benchmarks.

Ax Hung-Hsuan Chen 29d ago

CeRA: Overcoming the Linear Ceiling of Low-Rank Adaptation via Capacity Expansion

CeRA: Parameter-efficient fine-tuning method extending LoRA with non-linear capacity expansion via gating and dropout.

Ax Vignesh Gopakumar, Ander Gray, Dan Giles, Lorenzo Zanisi, Matt J. Kusner, Timo Betcke, Stanislas Pamela, Marc Peter Deisenroth 29d ago

Learning Physical Operators using Neural Operators

Physics-informed neural operators for solving PDEs with improved generalization beyond training distributions.

Ax Xiangyang Zhu, Yuan Tian, Qi Jia, Kaiwei Zhang, Zicheng Zhang, Chunyi Li, Kaiyuan Ji, Dongrui Liu, Zijian Chen, Lu Sun, Renrui Zhang, Yan Teng, Jing Shao, Wei Sun, Xia Hu, Yu Qiao, Guangtao Zhai 29d ago

SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond

SafeSci: Framework for evaluating safety of large language models in scientific domains with comprehensive benchmarks.

Ax Hejian Sang, Yuanda Xu, Zhengze Zhou, Ran He, Zhipeng Wang, Jiachen Sun 29d ago

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

CRISP: Method for teaching LLMs to reason more concisely via self-distillation with 'be concise' conditioning.

Ax Mohammad Al Ridhawi, Mahtab Haj Ali, Hussein Al Osman 29d ago

Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis

Stock market prediction using Node Transformer and BERT sentiment analysis for financial forecasting.

Ax Janne Perini, Rafael Bischof, Moab Arar, Ay\c{c}a Duran, Michael A. Kraus, Siddhartha Mishra, Bernd Bickel 29d ago

Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows

WinDiNet uses pretrained video diffusion model as differentiable physics simulator for urban wind flow prediction, replacing expensive CFD simulations.

Ax Cristian P\'erez-Corral, Alberto Fern\'andez-Hern\'andez, Jose I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ort\'i 29d ago

$\lambda$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks

λ-GELU parameterized gating function enabling controlled ReLU conversion while maintaining smooth activation properties for deployment.

Ax Song Yu, Li Li, Wenwen Zhao, Zhisheng Yang 29d ago

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models

ERPO method for token-level credit assignment in LLM reasoning models, addressing entropy collapse in GRPO through information heterogeneity.

Ax Aur Shalev Merin 29d ago

Temporal Credit Is Free

Recurrent network training without Jacobian propagation using hidden state temporal credit. Studies gradient normalization and online adaptation.

Ax Yongzhong Xu 29d ago

The Spectral Edge Thesis: A Mathematical Framework for Intra-Signal Phase Transitions in Neural Network Training

Mathematical framework explaining phase transitions in neural network training via spectral gap of parameter update Gram matrices. Grokking and capability gains analysis.

Ax Rafael Sojo, Pedro Larra\~naga, Concha Bielza 29d ago

Transfer learning for nonparametric Bayesian networks

Transfer learning for nonparametric Bayesian networks under scarce data. Proposes PC-stable-transfer and hill climbing transfer learning methods.

Ax Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval, Zikai Xie, Zhenzhi Tan, Jiankang Wang, Zijing Li, Liangliang Xu, Qi Yang, Jun Jiang, Sanzhong Luo, Zhenxiao Guo, Haitham Bou-Ammar, Jun Wang 29d ago

Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial

Tutorial on Bayesian Optimization for automating scientific discovery using surrogate models and probability-driven frameworks.

Ax Ilan Gold, Felix Fischer, Lucas Arnoldt, F. Alexander Wolf, Fabian J. Theis 29d ago

annbatch unlocks terabyte-scale training of biological data in anndata

annbatch: mini-batch loader for terabyte-scale biological data in AnnData format, addressing memory bottlenecks in ML training on large datasets.

Ax Ziyang Wei, Jiaqi Li, Likai Chen, Wei Biao Wu 29d ago

Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators

arXiv paper developing asymptotic theory for quantile estimation via stochastic gradient descent with constant learning rate.

Ax Yingqi Gao, Wenlu Xu, Jin J. Zhou, Hua Zhou, Yong Chen, Xiaowu Dai 29d ago

Learn then Decide: A Learning Approach for Designing Data Marketplaces

arXiv paper introducing MAPP mechanism for efficient data marketplace pricing using learned value distributions.

Ax Om Khangaonkar, Hamed Pirsiavash 29d ago

gen2seg: Generative Models Enable Generalizable Instance Segmentation

arXiv paper on gen2seg: using generative models (Stable Diffusion, MAE) for category-agnostic instance segmentation.

Ax Tianyou Li, Haijun Zou, Jiayuan Wu, Zaiwen Wen 29d ago

LMask: Learn to Solve Constrained Routing Problems with Lazy Masking

arXiv paper proposing LMask, a learning framework using dynamic masking for constrained routing problems optimization.

Ax Skyler Wu, Shihao Yang, S. C. Kou 29d ago

Are Statistical Methods Obsolete in the Era of Deep Learning? A Study of ODE Inverse Problems

arXiv paper comparing deep learning neural networks against statistical methods for solving ODE inverse problems.

Ax Junliang Luo, Katrin Tinn, Samuel Ferreira Duran, Di Wu, Xue Liu 29d ago

Decoding RWA Tokenized U.S. Treasuries: Functional Dissection and Address Role Inference

arXiv paper analyzing tokenized U.S. Treasuries transactions on blockchain infrastructure.

Ax Michele Minervini, Madison Chin, Jacob Kupperman, Nana Liu, Ivy Luo, Meghan Ly, Soorya Rethinasamy, Kathie Wang, Mark M. Wilde 29d ago

Constrained free energy minimization for the design of thermal states and stabilizer thermodynamic systems

arXiv paper on constrained free energy minimization for quantum thermodynamic system design.

Ax Aida Kostikova, Ole P\"utz, Steffen Eger, Olga Sabelfeld, Benjamin Paassen 29d ago

LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade

arXiv paper analyzing 150+ years of German parliamentary migration debates using LLMs, revealing shift from post-war solidarity to anti-solidarity.

Ax Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita 29d ago

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation

arXiv paper on ROPA: synthetic robot pose generation for RGB-D bimanual data augmentation to improve imitation learning policies.

Ax Ethan N. Epperly 29d ago

Adaptive randomized pivoting and volume sampling

Algorithm for column subset selection using adaptive randomized pivoting with connections to volume sampling.

Ax Zhongkai Yu, Yue Guan, Zihao Yu, Chenyang Zhou, Zhengding Hu, Shuyi Pei, Yangwook Kang, Yufei Ding, Po-An Tsai 29d ago

Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference

Forecasting data movement patterns in MoE LLM inference to reduce bottlenecks in multi-unit serving systems.

Ax Samuel Girard, Aurelien Bibaut, Arthur Gretton, Nathan Kallus, Houssam Zenati 29d ago

Fast Best-in-Class Regret for Contextual Bandits

Fast regret bounds for contextual bandits without realizability assumptions using pessimistic policy updates.

Ax Ruoyu Qin, Weiran He, Weixiao Huang, Yangkun Zhang, Yikai Zhao, Bo Pang, Xinran Xu, Yingdi Shan, Yongwei Wu, Mingxing Zhang 29d ago

Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning

Seer: context learning RL system for fast synchronous LLM training, addressing rollout latency and resource utilization.

Ax Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel 29d ago

Investigating Test Overfitting on SWE-bench

Investigation of test overfitting in SWE-bench for code resolution, where models pass tests but miss important cases.

Ax Jingran Zhang, Ning Li, Yuanhao Ban, Andrew Bai, Justin Cui 29d ago

Reward-Forcing: Autoregressive Video Generation with Reward Feedback

Autoregressive video generation using reward feedback to improve performance without strong teacher models.

Ax Daniel Chen, Zaria Zinn, Marcus Lowe 29d ago

Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification

GoogleFontsBench: benchmark for font classification using parameter-efficient fine-tuning of DINOv2 vision model.

Ax Daniel Zantedeschi, Kumar Muthuraman 29d ago

Fisher-Geometric Diffusion in Stochastic Gradient Descent: Optimal Rates, Oracle Complexity, and Information-Theoretic Limits

Analysis of stochastic gradient descent convergence under exchangeable mini-batch sampling and Fisher information.

Ax Jaemin Kim, Jong Chul Ye 29d ago