Image de couverture de livre

RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Lianghuan, Anupam, Sagnik, Lee, Insup, Li, Shuo, Bastani, Osbert
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Effective Reinforcement Learning for Reasoning in Language Models
par: Huang, Lianghuan, et autres
Publié: (2025)

LLM Program Optimization via Retrieval Augmented Search
par: Anupam, Sagnik, et autres
Publié: (2025)

Conformal Constrained Policy Optimization for Cost-Effective LLM Agents
par: Si, Wenwen, et autres
Publié: (2025)

BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
par: Anupam, Sagnik, et autres
Publié: (2025)

Uncertainty in Language Models: Assessment through Rank-Calibration
par: Huang, Xinmeng, et autres
Publié: (2024)

Rethinking Algorithmic Fairness for Human-AI Collaboration
par: Ge, Haosen, et autres
Publié: (2023)

Asymptotic Normality of Generalized Low-Rank Matrix Sensing via Riemannian Geometry
par: Bastani, Osbert
Publié: (2024)

WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning
par: Ge, Haosen, et autres
Publié: (2025)

Improving Human Sequential Decision-Making with Reinforcement Learning
par: Bastani, Hamsa, et autres
Publié: (2021)

Conformal Structured Prediction
par: Zhang, Botong, et autres
Publié: (2024)

SeekerGym: A Benchmark for Reliable Information Seeking
par: Kim, Remy, et autres
Publié: (2026)

Stochastic Online Conformal Prediction with Semi-Bandit Feedback
par: Ge, Haosen, et autres
Publié: (2024)

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
par: Si, Wenwen, et autres
Publié: (2026)

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
par: Xu, Kan, et autres
Publié: (2021)

TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction
par: Li, Shuo, et autres
Publié: (2023)

Beating the Winner's Curse via Inference-Aware Policy Optimization
par: Bastani, Hamsa, et autres
Publié: (2025)

Winner's Curse Drives False Promises in Data-Driven Decisions: A Case Study in Refugee Matching
par: Bastani, Hamsa, et autres
Publié: (2026)

One-Shot Safety Alignment for Large Language Models via Optimal Dualization
par: Huang, Xinmeng, et autres
Publié: (2024)

SPARLING: Learning Latent Representations with Extremely Sparse Activations
par: Gupta, Kavi, et autres
Publié: (2023)

Stochastic Bandits with ReLU Neural Networks
par: Xu, Kan, et autres
Publié: (2024)

Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
par: Yao, Michael S., et autres
Publié: (2025)

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
par: Mukherjee, Sagnik, et autres
Publié: (2025)

Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction
par: Ramalingam, Ramya, et autres
Publié: (2024)

Prior-Agnostic Incentive-Compatible Exploration
par: Ramalingam, Ramya, et autres
Publié: (2026)

Generative Adversarial Model-Based Optimization via Source Critic Regularization
par: Yao, Michael S., et autres
Publié: (2024)

Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
par: Yao, Michael S., et autres
Publié: (2025)

Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
par: Huang, Lianghuan, et autres
Publié: (2025)

Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting
par: Young, Halley, et autres
Publié: (2024)

Alignment of large language models with constrained learning
par: Zhang, Botong, et autres
Publié: (2025)

Monitor and Recover: A Paradigm for Future Research on Distribution Shift in Learning-Enabled Cyber-Physical Systems
par: Lin, Vivian, et autres
Publié: (2025)

Eurekaverse: Environment Curriculum Generation via Large Language Models
par: Liang, William, et autres
Publié: (2024)

A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions
par: Mell, Stephen, et autres
Publié: (2025)

Quantifying and Improving Adaptivity in Conformal Prediction through Input Transformations
par: Jang, Sooyong, et autres
Publié: (2025)

Eureka: Human-Level Reward Design via Coding Large Language Models
par: Ma, Yecheng Jason, et autres
Publié: (2023)

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement
par: Zhang, Xuechen, et autres
Publié: (2025)

DrEureka: Language Model Guided Sim-To-Real Transfer
par: Ma, Yecheng Jason, et autres
Publié: (2024)

MathDSL: A Domain-Specific Language for Concise Mathematical Solutions Via Program Synthesis
par: Anupam, Sagnik, et autres
Publié: (2024)

IBCL: Zero-shot Model Generation under Stability-Plasticity Trade-offs
par: Lu, Pengyuan, et autres
Publié: (2023)

Pattern-Guided Diffusion Models
par: Lin, Vivian, et autres
Publié: (2025)

Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria
par: Yao, Michael S., et autres
Publié: (2024)