Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference research paper by Cerebras, 2026

Cerebras · Inference and efficiency · Sep 4, 2026 · 0 citations · 25 upvotes · unverified

Read on arXiv

What it shows

Layer dropout improves large language model training efficiency and enables faster inference via early exit and speculative decoding without sacrificing accuracy.

By Mostafa Elhoushi, Alex Pretko, Nolan Dey and 6 more · arXiv 2609.05275 · PDF

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

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
Citations
0, 0 influential · Semantic Scholar
Upvotes
25 · Hugging Face
Lab
Cerebras · on Companies · on calendar · on datacenters · on Quarterly · on emerging · on Mainstage · on labs · on lawsuits · on Leaders · on newsletters · on Allied · on Paydays · on Metered · on Releases · on socials · on standards · on sunsets · on TechConf · on terms · on Titlewave · on Hotlist

Changes

CitationsSep 25, 2026A first count of 0 influential citations.
CitationsSep 25, 2026A first count of 0 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.