Image de couverture de livre

Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Chao, Yang, Tao, Tian, Hongtao, Shi, Yunsheng, Ma, Qiyao, Liu, Xiaotao, Yao, Ting, Ding, Wenbo
Format:	Preprint
Publié:	2025
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

From Faithfulness to Correctness: Generative Reward Models that Think Critically
par: Ma, Qiyao, et autres
Publié: (2025)

Discriminative Policy Optimization for Token-Level Reward Models
par: Chen, Hongzhan, et autres
Publié: (2025)

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment
par: Xie, Guofu, et autres
Publié: (2025)

Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
par: Shrivastava, Vaishnavi, et autres
Publié: (2025)

WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library
par: Wu, Junyu, et autres
Publié: (2025)

G-Core: A Simple, Scalable and Balanced RLHF Trainer
par: Wu, Junyu, et autres
Publié: (2025)

Learning More With Less: Sample Efficient Model-Based RL for Loco-Manipulation
par: Hoffman, Benjamin, et autres
Publié: (2025)

Less is More: Resource-Efficient Low-Rank Adaptation
par: Tian, Chunlin, et autres
Publié: (2025)

More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
par: Gao, Pengfei, et autres
Publié: (2025)

Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning
par: Zhang, Zhi, et autres
Publié: (2026)

Less is More: Efficient Brain-Inspired Learning for Autonomous Driving Trajectory Prediction
par: Liao, Haicheng, et autres
Publié: (2024)

Constrained Dynamics Simulation: More With Less
par: Sathya, Ajay Suresha
Publié: (2024)

Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers
par: Lou, Chao, et autres
Publié: (2024)

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
par: Tian, Xinyu, et autres
Publié: (2025)

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
par: Zhang, Yixian, et autres
Publié: (2025)

Less is More: Efficient Weight Farcasting with 1-Layer Neural Network
par: Shou, Xiao, et autres
Publié: (2025)

Less is More: Towards Simple Graph Contrastive Learning
par: Zhao, Yanan, et autres
Publié: (2025)

Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation
par: Xie, Guofu, et autres
Publié: (2025)

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
par: Wu, Shaojin, et autres
Publié: (2025)

Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning
par: Schulte, David, et autres
Publié: (2024)

Learning More from Less: Unlocking Internal Representations for Benchmark Compression
par: Zhang, Yueqi, et autres
Publié: (2026)

Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
par: Banayeeanzade, Amin, et autres
Publié: (2026)

Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR
par: Yi, Hao, et autres
Publié: (2026)

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
par: Liu, Zongkai, et autres
Publié: (2024)

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
par: Yang, Zhen, et autres
Publié: (2025)

Less is More, More or Less... Finding the Optimal Threshold for Lexicalization in Chunking
par: Balázs Indig
Publié: (2017)

Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
par: Fan, Junchao, et autres
Publié: (2024)

Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
par: Bao, Jianzhu, et autres
Publié: (2026)

Less is More: Decoder-Free Masked Modeling for Efficient Skeleton Representation Learning
par: Do, Jeonghyeok, et autres
Publié: (2026)

Human-assisted Robotic Policy Refinement via Action Preference Optimization
par: Xia, Wenke, et autres
Publié: (2025)

Less is More: Contextual Sampling for Nonlinear Data-Driven Predictive Control
par: Beerwerth, Julius, et autres
Publié: (2025)

When Less Is More.
par: Lettis, Lucy
Publié: (1998)

Doing More with Less.
par: Wagenveld, Linda M.
Publié: (1987)

Less is More: Multimodal Region Representation via Pairwise Inter-view Learning
par: Namgung, Min, et autres
Publié: (2025)

ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement
par: Wang, Haoxu, et autres
Publié: (2025)

Less is More: Adaptive Program Repair with Bug Localization and Preference Learning
par: Dai, Zhenlong, et autres
Publié: (2025)

Get More for Less in Decentralized Learning Systems
par: Dhasade, Akash, et autres
Publié: (2023)

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
par: Li, Yulin, et autres
Publié: (2025)

Doing More With Less: Towards More Data-Efficient Syndrome-Based Neural Decoders
par: Ismail, Ahmad, et autres
Publié: (2025)

When Less is More: The LLM Scaling Paradox in Context Compression
par: Guo, Ruishan, et autres
Publié: (2026)