Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization research paper by NVIDIA, 2026

NVIDIA · Alignment and safety · Jan 8, 2026 · 234 citations · 235 upvotes · unverified

Read on arXiv

What it shows

Multi-reward reinforcement learning suffers from reward normalization collapse in GRPO, which GDPO addresses by decoupling reward normalization for improved training stability and performance across reasoning tasks.

By Shih-Yang Liu, Xin Dong, Ximing Lu and 10 more · arXiv 2601.05242 · PDF · Code

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

More from NVIDIA

All 90
Multimodal and roboticsUnverifiedNov 5, 2026VFlash: Fast, Accurate Visual Planning via Flash Primitive DecodingA method called VFlash speeds up and improves visual motion planning for robots by predicting entire spatial shapes at once.NVIDIA109 upvotesRead →Foundation modelsUnverifiedOct 27, 2026Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy DistillationNLD-Uni is a unified discrete diffusion language model that combines visual understanding and generation via cross-paradigm on-policy distillation and progressive self-refining diffusion.NVIDIA12 upvotesRead →ReasoningUnverifiedOct 27, 2026ThinkWorld: World Imagination Reinforces Chain-of-Dynamics ReasoningThinkWorld improves robotic generalization by representing actions as dynamics chains and using world imagination to learn from unlabeled human videos.NVIDIA57 upvotesRead →Multimodal and roboticsUnverifiedOct 20, 2026Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary RigsThis model generates both video and 3D motion for any character rig, allowing the motion to be replayed accurately within a 3D scene.NVIDIA26 upvotesRead →Inference and efficiencyUnverifiedOct 13, 2026EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud DelegationThis paper introduces a framework that reduces inference costs by using a small local model for most tasks and delegating only critical steps to the cloud.NVIDIA30 upvotesRead →Training and scalingUnverifiedOct 8, 2026When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often BetterThis paper shows that distilling from offline student rollouts is often more efficient and accurate than standard on-policy distillation for many model pairs.NVIDIA28 upvotesRead →Multimodal and roboticsUnverifiedOct 7, 2026Long-WAM: Scaling the Context of World-Action ModelsLong-WAM improves robot control by using autoregressive pretraining to effectively leverage long visual histories for real-time action prediction.NVIDIA2 citations114 upvotesRead →Inference and efficiencyUnverifiedOct 6, 2026NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter ScaleNeMo-DCR enables efficient, bit-exact synchronization of trillion-parameter model checkpoints by transmitting only the sparse weight changes between clusters.NVIDIA1 citations29 upvotesRead →

Other alignment and safety papers

Topic
Alignment and safetyMar 4, 2022Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.OpenAI25.8k citations26 upvotesRead →Alignment and safetyMay 29, 2023Direct Preference Optimization: Your Language Model is Secretly a Reward ModelDPO aligns a model to human preferences with a simple classification loss, no reward model or RL loop.Stanford University11.6k citations73 upvotesRead →Alignment and safetyDec 15, 2022Constitutional AI: Harmlessness from AI FeedbackConstitutional AI trains a harmless assistant from AI feedback guided by a short list of written principles, not human harm labels.Anthropic3,987 citations4 upvotesRead →Alignment and safetyFeb 22, 2024Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsReinforcement Learning from Human Feedback (RLHF) benefits from simpler REINFORCE-style optimization methods over computationally expensive PPO or "RL-free" methods, enhancing performance and reducing cost in large language models.Cohere804 citations18 upvotesRead →Alignment and safetyJan 10, 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.Anthropic657 citations30 upvotesRead →Alignment and safetyDec 18, 2024Alignment faking in large language modelsClaude 3 Opus sometimes went along with a training goal it disagreed with, to avoid being changed, without being told to.Anthropic393 citations10 upvotesRead →
About this paper
Venue
arXiv.org
Citations
234, 49 influential · Semantic Scholar
Upvotes
235 · Hugging Face
Lab
NVIDIA · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

CitationsNov 9, 2026Influential citations rose from 47 to 49.
CitationsNov 9, 2026Citations rose from 227 to 234.
CitationsNov 2, 2026Influential citations rose from 39 to 47.
CitationsNov 2, 2026Citations rose from 194 to 227.
CitationsOct 12, 2026Influential citations rose from 35 to 39.
CitationsOct 12, 2026Citations rose from 183 to 194.
CitationsOct 5, 2026Influential citations rose from 30 to 35.
CitationsOct 5, 2026Citations rose from 161 to 183.
CitationsSep 28, 2026Influential citations rose from 28 to 30.
CitationsSep 28, 2026Citations rose from 158 to 161.
CitationsSep 25, 2026A first count of 28 influential citations.
CitationsSep 25, 2026A first count of 158 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.