Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

The Art of Scaling Reinforcement Learning Compute for LLMs research paper by Meta, 2025

Meta · Training and scaling · Oct 15, 2025 · 112 citations · 34 upvotes · unverified

Read on arXiv

What it shows

A systematic study defines a framework for analyzing and predicting reinforcement learning scaling in large language models, identifying key design choices that affect compute efficiency and proposing a best-practice recipe.

By Devvrit Khatri, Lovish Madaan, Rishabh Tiwari and 6 more · arXiv 2510.13786 · PDF

UnverifiedHugging Face's summary; not yet checked by hand.

More from Meta

All 40
Multimodal and roboticsUnverifiedOct 25, 2026InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM AssistantsInteractiveWorld provides a verifiable simulation environment and benchmark to evaluate whether multimodal language models can reliably guide humans through physical tasks.Meta46 upvotesRead →Multimodal and roboticsUnverifiedOct 2, 2026Native Action-Prior Learning from Videos for World Action ModelsNAVA-WAM learns robot action priors directly from observation-only videos, improving control performance without needing action-labeled data for pretraining.Meta88 upvotesRead →Alignment and safetyUnverifiedOct 1, 2026Sharpening Tax in Post-TrainingThis paper introduces a metric to quantify the loss in solution coverage after reinforcement learning and proposes a sampler to mitigate it.Meta1 citations111 upvotesRead →Multimodal and roboticsUnverifiedOct 1, 2026World Action Modeling with Progressive Visual PlanningProWAM improves robotic control by predicting sparse visual sub-goals to guide action generation, avoiding the need for dense video generation.Meta1 citations98 upvotesRead →ArchitecturesUnverifiedSep 29, 2026Context Language ModelsContext Language Models manage their own context by treating it as an editable file, improving performance and efficiency.Meta5 citations47 upvotesRead →Inference and efficiencyUnverifiedSep 26, 2026In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video DiffusionFlashForward accelerates video diffusion by reusing in-flight KV caches and using sparse clean anchors to maintain structural consistency.Meta1 citations34 upvotesRead →Agents and evaluationUnverifiedSep 4, 2026WearableQA: A Benchmark for Health Reasoning over Real-World Wearable DataWearableQA is a benchmark of multiple-choice questions derived from real longitudinal wearable data that evaluates large language model reasoning across data and health dimensions.Meta43 upvotesRead →Multimodal and roboticsAug 6, 2026Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and RecipesControlled experiments on when text, image understanding and image generation help or compete when trained together.Meta7 citations63 upvotesRead →

Other training and scaling papers

Topic
Training and scalingJun 17, 2021LoRA: Low-Rank Adaptation of Large Language ModelsLoRA fine-tunes a large model by training small low-rank matrices, cutting trainable parameters by 10,000 times.Microsoft25.6k citations66 upvotesRead →Training and scalingJan 23, 2020Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.OpenAI9,592 citations12 upvotesRead →Training and scalingMar 29, 2022Training Compute-Optimal Large Language ModelsChinchilla: for a fixed compute budget, train a smaller model on more data; parameters and tokens should grow together.Google DeepMind4,035 citations13 upvotesRead →Training and scalingSep 17, 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismMegatron-LM splits each Transformer layer across GPUs to train models with billions of parameters.NVIDIA3,387 citations5 upvotesRead →Training and scalingUnverifiedJan 5, 2024DeepSeek LLM: Scaling Open-Source Language Models with LongtermismDeepSeek LLM, an open-source language model project, develops a large dataset and employs SFT and DPO to achieve performance surpassing LLaMA-2 70B and GPT-3.5 in various benchmarks and open-ended evaluations.DeepSeek872 citations56 upvotesRead →Training and scalingMay 15, 2024LoRA Learns Less and Forgets LessLoRA learns less than full fine-tuning on code and math, but forgets less of what the model already knew.Databricks486 citations91 upvotesRead →
About this paper
Venue
arXiv.org
Citations
112, 13 influential · Semantic Scholar
Upvotes
34 · Hugging Face
Lab
Meta · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

CitationsNov 2, 2026Citations rose from 99 to 112.
CitationsOct 12, 2026Influential citations rose from 12 to 13.
CitationsOct 12, 2026Citations rose from 96 to 99.
CitationsOct 5, 2026Citations rose from 91 to 96.
CitationsSep 25, 2026A first count of 12 influential citations.
CitationsSep 25, 2026A first count of 91 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.