Copertina

Prioritized Replay for RL Post-training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Fatemi, Mehdi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
di: Butt, Natasha, et al.
Pubblicazione: (2024)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
di: Zhou, Jin Peng, et al.
Pubblicazione: (2025)

Automatic Pair Construction for Contrastive Post-training
di: Xu, Canwen, et al.
Pubblicazione: (2023)

Post-training for Efficient Communication via Convention Formation
di: Hua, Yilun, et al.
Pubblicazione: (2025)

Efficient Post-training Quantization with FP8 Formats
di: Shen, Haihao, et al.
Pubblicazione: (2023)

RePO: Replay-Enhanced Policy Optimization
di: Li, Siheng, et al.
Pubblicazione: (2025)

Post-training an LLM for RAG? Train on Self-Generated Demonstrations
di: Finlayson, Matthew, et al.
Pubblicazione: (2025)

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
di: Yang, Zhuolin, et al.
Pubblicazione: (2026)

Post-training makes large language models less human-like
di: Binz, Marcel, et al.
Pubblicazione: (2026)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
di: Li, Melody Zixuan, et al.
Pubblicazione: (2025)

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
di: Kang, Feiyang, et al.
Pubblicazione: (2025)

FutureSim: Replaying World Events to Evaluate Adaptive Agents
di: Goel, Shashwat, et al.
Pubblicazione: (2026)

Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
di: Shi, Zhenning, et al.
Pubblicazione: (2026)

Self-generated Replay Memories for Continual Neural Machine Translation
di: Resta, Michele, et al.
Pubblicazione: (2024)

Investigating the Interplay of Prioritized Replay and Generalization
di: Panahi, Parham Mohammad, et al.
Pubblicazione: (2024)

StateX: Enhancing RNN Recall via Post-training State Expansion
di: Shen, Xingyu, et al.
Pubblicazione: (2025)

PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
di: Wang, Xinyu, et al.
Pubblicazione: (2025)

MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
di: Lu, Yiyang, et al.
Pubblicazione: (2026)

Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
di: Zhang, Kongcheng, et al.
Pubblicazione: (2025)

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
di: Hazard, Hugo, et al.
Pubblicazione: (2025)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
di: Song, Xiangchen, et al.
Pubblicazione: (2025)

Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
di: Kong, Injin, et al.
Pubblicazione: (2026)

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
di: Jing, Yi, et al.
Pubblicazione: (2026)

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
di: Tao, Yongding, et al.
Pubblicazione: (2025)

FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
di: Feng, Yujie, et al.
Pubblicazione: (2026)

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
di: Abbes, Istabrak, et al.
Pubblicazione: (2025)

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
di: Li, Jinze, et al.
Pubblicazione: (2025)

GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
di: Kharyal, Chaitanya, et al.
Pubblicazione: (2024)

Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena
di: Luo, Haipeng, et al.
Pubblicazione: (2024)

Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
di: Liu, Jinyi, et al.
Pubblicazione: (2023)

OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
di: Roush, Allen, et al.
Pubblicazione: (2024)

ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
di: Lu, Xingyu, et al.
Pubblicazione: (2026)

Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy
di: Tang, Xiangru, et al.
Pubblicazione: (2024)

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
di: Guan, Xinyan, et al.
Pubblicazione: (2024)

GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
di: Zhang, Yunan, et al.
Pubblicazione: (2025)

LIMR: Less is More for RL Scaling
di: Li, Xuefeng, et al.
Pubblicazione: (2025)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
di: Sun, Yifan, et al.
Pubblicazione: (2025)

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
di: Tang, Pingzhi, et al.
Pubblicazione: (2026)

On the Optimal Reasoning Length for RL-Trained Language Models
di: Nohara, Daisuke, et al.
Pubblicazione: (2026)

FlowRL: Matching Reward Distributions for LLM Reasoning
di: Zhu, Xuekai, et al.
Pubblicazione: (2025)