Cover Image

Post-Training as Reweighting: A Stochastic View of Reasoning Trajectories in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bu, Dake, Huang, Wei, Han, Andi, Nitanda, Atsushi, Xue, Bo, Zhang, Qingfu, Wong, Hau-San, Suzuki, Taiji
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
by: Bu, Dake, et al.
Published: (2025)

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models
by: Bu, Dake, et al.
Published: (2026)

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
by: Bu, Dake, et al.
Published: (2024)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
by: Bu, Dake, et al.
Published: (2025)

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
by: Bu, Dake, et al.
Published: (2024)

Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
by: Nitanda, Atsushi, et al.
Published: (2026)

Direct Distributional Optimization for Provable Alignment of Diffusion Models
by: Kawata, Ryotaro, et al.
Published: (2025)

Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization
by: Chen, Zonghao, et al.
Published: (2025)

Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
by: Fu, Guoji, et al.
Published: (2026)

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
by: Chen, Yilan, et al.
Published: (2025)

Koopman-based generalization bound: New aspect for full-rank weights
by: Hashimoto, Yuka, et al.
Published: (2023)

Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
by: Nitanda, Atsushi, et al.
Published: (2025)

Improved Particle Approximation Error for Mean Field Neural Networks
by: Nitanda, Atsushi
Published: (2024)

On the Comparison between Multi-modal and Single-modal Contrastive Learning
by: Huang, Wei, et al.
Published: (2024)

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
by: Huang, Wei, et al.
Published: (2026)

Uniform convergence of the smooth calibration error and its relationship with functional gradient
by: Futami, Futoshi, et al.
Published: (2025)

Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
by: Takagi, Hirohane, et al.
Published: (2026)

How Does Preconditioning Guide Feature Learning in Deep Neural Networks?
by: Yoshida, Kotaro, et al.
Published: (2025)

Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
by: Higuchi, Rei, et al.
Published: (2025)

Enhancing Adversarial Training via Reweighting Optimization Trajectory
by: Huang, Tianjin, et al.
Published: (2023)

Mirror Descent Policy Optimisation for Robust Constrained Markov Decision Processes
by: Bossens, David M., et al.
Published: (2025)

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
by: Huang, Wei, et al.
Published: (2025)

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
by: Li, Bingrui, et al.
Published: (2024)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
by: Zhang, Tongcheng, et al.
Published: (2026)

Statistical Analysis of the Sinkhorn Iterations for Two-Sample Schrödinger Bridge Estimation
by: Maeda, Ibuki, et al.
Published: (2025)

Uniform-in-$N$ log-Sobolev inequality for the mean-field Langevin dynamics with convex energy
by: Chewi, Sinho, et al.
Published: (2024)

Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning
by: Oh, Junsoo, et al.
Published: (2025)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
by: Jiang, Jiarui, et al.
Published: (2025)

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
by: Jiang, Jiarui, et al.
Published: (2024)

On the Role of Label Noise in the Feature Learning Process
by: Han, Andi, et al.
Published: (2025)

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
by: Nishikawa, Naoki, et al.
Published: (2024)

Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification
by: Wu, Yang, et al.
Published: (2026)

A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning
by: Wachi, Akifumi, et al.
Published: (2026)

Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
by: Li, Yize, et al.
Published: (2024)

QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized Model
by: Yang, Zongxian, et al.
Published: (2025)

An energy landscape-based theoretical framework for understanding the emergence of functions in a living system under the dynamical component interaction
by: Suzuki, Ryunosuke, et al.
Published: (2025)

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
by: Kim, Juno, et al.
Published: (2024)

Deep Two-Way Matrix Reordering for Relational Data Analysis
by: Watanabe, Chihiro, et al.
Published: (2021)

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
by: Awano, Ryoya, et al.
Published: (2026)

Transformers Provably Solve Parity Efficiently with Chain of Thought
by: Kim, Juno, et al.
Published: (2024)