Image de couverture de livre

Value-Based Pre-Training with Downstream Feedback

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ke, Shuqi, Fanti, Giulia
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
par: Ke, Shuqi, et autres
Publié: (2024)

Improving the Training of Rectified Flows
par: Lee, Sangyun, et autres
Publié: (2024)

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
par: Lee, Sangyun, et autres
Publié: (2025)

MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
par: Patel, Sara, et autres
Publié: (2025)

Pre-Trained Model Recommendation for Downstream Fine-tuning
par: Bai, Jiameng, et autres
Publié: (2024)

Mixture-of-Linear-Experts for Long-term Time Series Forecasting
par: Ni, Ronghao, et autres
Publié: (2023)

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
par: Yin, Lu, et autres
Publié: (2023)

How Can LLM Guide RL? A Value-Based Approach
par: Zhang, Shenao, et autres
Publié: (2024)

Fast and Accurate Probing of In-Training LLMs' Downstream Performances
par: Liu, Zhichen, et autres
Publié: (2026)

Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chains
par: Zhao, Jiale, et autres
Publié: (2024)

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
par: Xu, Chengyin, et autres
Publié: (2025)

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
par: Hou, Charlie, et autres
Publié: (2023)

Downstream Task-Oriented Generative Model Selections on Synthetic Data Training for Fraud Detection Models
par: Cheng, Yinan, et autres
Publié: (2024)

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
par: Feng, Wenfeng, et autres
Publié: (2025)

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training
par: Krajewski, Jakub, et autres
Publié: (2025)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
par: Chen, Hao, et autres
Publié: (2023)

Finetune-Informed Pretraining Boosts Downstream Performance
par: Faysal, Atik, et autres
Publié: (2026)

Reconciling Model Multiplicity for Downstream Decision Making
par: Du, Ally Yalei, et autres
Publié: (2024)

PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning
par: Wu, Yuanlong, et autres
Publié: (2025)

Provably Robust Pre-Trained Ensembles for Biomarker-Based Cancer Classification
par: Lee, Chongmin, et autres
Publié: (2024)

Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization
par: Pannacci, Matteo, et autres
Publié: (2026)

Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning
par: Li, Yanjie, et autres
Publié: (2024)

Vision-Language Model Selection and Reuse for Downstream Adaptation
par: Tan, Hao-Zhe, et autres
Publié: (2025)

REG: A Regularization Optimizer for Robust Training Dynamics
par: Liu, Zehua, et autres
Publié: (2025)

Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
par: He, Kun, et autres
Publié: (2025)

Analyzing Generalization in Pre-Trained Symbolic Regression
par: Voigt, Henrik, et autres
Publié: (2025)

floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
par: Agrawalla, Bhavya, et autres
Publié: (2025)

ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
par: Quinlan, Paul, et autres
Publié: (2026)

Feed-Forward Optimization With Delayed Feedback for Neural Network Training
par: Flügel, Katharina, et autres
Publié: (2023)

Fast Training of Recurrent Neural Networks with Stationary State Feedbacks
par: Caillon, Paul, et autres
Publié: (2025)

Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages
par: Cui, Brandon, et autres
Publié: (2026)

Self-Supervised Pre-Training for Precipitation Post-Processor
par: An, Sojung, et autres
Publié: (2023)

A Survey on Time-Series Pre-Trained Models
par: Ma, Qianli, et autres
Publié: (2023)

Practical Insights into Knowledge Distillation for Pre-Trained Models
par: Alballa, Norah, et autres
Publié: (2024)

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
par: Nepal, Aadim, et autres
Publié: (2025)

Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks
par: Patel, Niket, et autres
Publié: (2025)

WxC-Bench: A Novel Dataset for Weather and Climate Downstream Tasks
par: Shinde, Rajat, et autres
Publié: (2024)

Modular Deep Learning for Multivariate Time-Series: Decoupling Imputation and Downstream Tasks
par: Raj, Joseph Arul, et autres
Publié: (2024)

Efficient Deep Learning Board: Training Feedback Is Not All You Need
par: Gong, Lina, et autres
Publié: (2024)

Efficient Pre-Training of LLMs through Truncated SVD Layers
par: Kamali, Kaivan, et autres
Publié: (2026)