Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Fast-dLLM v2: Efficient Block-Diffusion LLM research paper by NVIDIA, 2025

NVIDIA · Inference and efficiency · Sep 30, 2025 · 158 citations · 59 upvotes · unverified

Read on arXiv

What it shows

Fast-dLLM v2, a block diffusion language model, efficiently converts pretrained autoregressive models for parallel text generation, achieving significant speedup without compromising accuracy.

By Chengyue Wu, Hao Zhang, Shuchen Xue and 7 more · arXiv 2509.26328 · 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 inference and efficiency papers

Topic
Inference and efficiencySep 12, 2023Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.UC Berkeley9,965 citations72 upvotesRead →Inference and efficiencyMay 27, 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.Stanford University5,830 citations16 upvotesRead →Inference and efficiencyUnverifiedJul 24, 2025Group Sequence Policy OptimizationGroup Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm that improves training efficiency and performance of large language models by using sequence-level importance ratios and operations.Alibaba (Qwen)814 citations323 upvotesRead →Inference and efficiencyUnverifiedFeb 16, 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionNSA, a trainable sparse attention mechanism, enhances long-context modeling efficiency without sacrificing performance, achieving improvements in speed and accuracy over full attention models.DeepSeek596 citations157 upvotesRead →Inference and efficiencyUnverifiedApr 7, 2025SmolVLM: Redefining small and efficient multimodal modelsSmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.Hugging Face330 citations212 upvotesRead →Inference and efficiencyUnverifiedOct 17, 2025Chronos-2: From Univariate to Universal ForecastingChronos-2, a pretrained model with a group attention mechanism, achieves state-of-the-art performance in zero-shot univariate, multivariate, and covariate-informed forecasting tasks.Amazon276 citations28 upvotesRead →
About this paper
Venue
arXiv.org
Citations
158, 25 influential · Semantic Scholar
Upvotes
59 · Hugging Face
Lab
NVIDIA · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

CitationsNov 9, 2026Citations rose from 155 to 158.
CitationsNov 2, 2026Influential citations rose from 23 to 25.
CitationsNov 2, 2026Citations rose from 140 to 155.
CitationsOct 12, 2026Influential citations rose from 20 to 23.
CitationsOct 12, 2026Citations rose from 133 to 140.
CitationsOct 5, 2026Influential citations rose from 18 to 20.
CitationsOct 5, 2026Citations rose from 126 to 133.
CitationsSep 28, 2026Citations rose from 125 to 126.
CitationsSep 25, 2026A first count of 18 influential citations.
CitationsSep 25, 2026A first count of 125 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.