Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention research paper by NVIDIA, 2026

NVIDIA · Foundation models · May 21, 2026 · 48 citations · 30 upvotes · unverified

Read on arXiv

What it shows

Gated DeltaNet-2 improves upon existing linear attention models by separating erase and write operations through distinct channel-wise gates, achieving superior performance in long-context language modeling and retrieval tasks.

By Ali Hatamizadeh, Yejin Choi, Jan Kautz · arXiv 2605.22791 · 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 foundation models papers

Topic
Foundation modelsOct 11, 2018BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google125k citations33 upvotesRead →Foundation modelsMay 28, 2020Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI66.4k citations21 upvotesRead →Foundation modelsMar 15, 2023GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI28.4k citations7 upvotesRead →Foundation modelsFeb 27, 2023LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta22.6k citations25 upvotesRead →Foundation modelsJul 31, 2024The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta20.8k citations119 upvotesRead →Foundation modelsUnverifiedMay 14, 2025Qwen3 Technical ReportQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen)10.1k citations339 upvotesRead →
About this paper
Venue
arXiv.org
Citations
48, 9 influential · Semantic Scholar
Upvotes
30 · Hugging Face
Lab
NVIDIA · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

CitationsNov 9, 2026Influential citations rose from 7 to 9.
CitationsNov 9, 2026Citations rose from 42 to 48.
CitationsNov 2, 2026Citations rose from 33 to 42.
CitationsOct 12, 2026Influential citations rose from 6 to 7.
CitationsOct 12, 2026Citations rose from 27 to 33.
CitationsOct 5, 2026Influential citations rose from 5 to 6.
CitationsOct 5, 2026Citations rose from 22 to 27.
CitationsSep 28, 2026Citations rose from 21 to 22.
CitationsSep 25, 2026A first count of 5 influential citations.
CitationsSep 25, 2026A first count of 21 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.