:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Li, Muheng, Qian, Jian, Mou, Wenlong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2605.10716
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Predicting and improving test-time scaling laws via reward tail-guided search
by: Li, Muheng, et al.
Published: (2026)

To bootstrap or to rollout? An optimal and adaptive interpolation
by: Mou, Wenlong, et al.
Published: (2024)

Continuous-time reinforcement learning: ellipticity enables model-free value function approximation
by: Mou, Wenlong
Published: (2026)

Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs
by: Mou, Wenlong
Published: (2025)

Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
by: Zhang, Rui, et al.
Published: (2025)

Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
by: Mou, Wenlong
Published: (2025)

Reheated Gradient-based Discrete Sampling for Combinatorial Optimization
by: Li, Muheng, et al.
Published: (2025)

On Bellman equations for continuous-time policy evaluation I: discretization and approximation
by: Mou, Wenlong, et al.
Published: (2024)

Language model developers should report train-test overlap
by: Zhang, Andy K, et al.
Published: (2024)

Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations
by: Xia, Xiaofan, et al.
Published: (2026)

What should an AI assessor optimise for?
by: Romero-Alvarado, Daniel, et al.
Published: (2025)

Reinforcement Learning with Action-Triggered Observations
by: Ryabchenko, Alexander, et al.
Published: (2025)

Measuring training variability from stochastic optimization using robust nonparametric testing
by: Banerjee, Sinjini, et al.
Published: (2024)

s1: Simple test-time scaling
by: Muennighoff, Niklas, et al.
Published: (2025)

ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm
by: Li, Chris Junchi, et al.
Published: (2020)

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
by: Wichers, Nevan, et al.
Published: (2025)

Collective variables of neural networks: empirical time evolution and scaling laws
by: Tovey, Samuel, et al.
Published: (2024)

Thought calibration: Efficient and confident test-time scaling
by: Wu, Menghua, et al.
Published: (2025)

ROC-n-reroll: How verifier imperfection affects test-time scaling
by: Dorner, Florian E., et al.
Published: (2025)

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
by: Mou, Wenlong, et al.
Published: (2021)

Why should autoencoders work?
by: Kvalheim, Matthew D., et al.
Published: (2023)

A new perspective on low-rank optimization
by: Bertsimas, Dimitris, et al.
Published: (2021)

Broken neural scaling laws in materials science
by: Großmann, Max, et al.
Published: (2026)

Optimal scaling laws in learning hierarchical multi-index models
by: Defilippis, Leonardo, et al.
Published: (2026)

Emergence and scaling laws in SGD learning of shallow neural networks
by: Ren, Yunwei, et al.
Published: (2025)

An operator preconditioning perspective on training in physics-informed machine learning
by: De Ryck, Tim, et al.
Published: (2023)

torchtune: PyTorch native post-training library
by: Obozov, Mark, et al.
Published: (2026)

Want to train KANS at scale? Now UKAN!
by: Moradzadeh, Alireza, et al.
Published: (2024)

Spiking the training data to correct for test set contamination
by: Wei, Johnny Tian-Zheng, et al.
Published: (2026)

Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology
by: Jiao, Yuchen, et al.
Published: (2025)

Calibrating Transformers via Sparse Gaussian Processes
by: Chen, Wenlong, et al.
Published: (2023)

Efficient training for large-scale optical neural network using an evolutionary strategy and attention pruning
by: Yang, Zhiwei, et al.
Published: (2025)

Superposition unifies power-law training dynamics
by: Chen, Zixin Jessie, et al.
Published: (2026)

A geometric framework for momentum-based optimizers for low-rank training
by: Schotthöfer, Steffen, et al.
Published: (2025)

Probabilistic Learning and Generation in Deep Sequence Models
by: Chen, Wenlong
Published: (2026)

Data-efficient pre-training by scaling synthetic megadocs
by: Kim, Konwoo, et al.
Published: (2026)

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
by: Nguyen, Minh-Toan, et al.
Published: (2026)

Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
by: Arous, Gérard Ben, et al.
Published: (2025)

What should a neuron aim for? Designing local objective functions based on information theory
by: Schneider, Andreas C., et al.
Published: (2024)

Accelerating trajectory optimization with Sobolev-trained diffusion policies
by: Hellard, Théotime Le, et al.
Published: (2026)