08:27 CETWednesday · May 13, 2026

shipfeed

⌘K SEARCHJK NAVO OPEN
on the wire
arXiv — cs.AIMedHopQA benchmark tests LLM reasoning in biomedical Q&A◆arXiv — cs.CLRouters learn geometry of sparse mixture-of-experts◆arXiv — cs.AIStudy audits how LLMs generate political discourse during crises◆arXiv — cs.AIClassifier Context Rot: Monitor Performance Degrades with Context◆arXiv — cs.AIExecutable Agentic Memory for GUI Agent◆arXiv — cs.CLLongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced◆arXiv — cs.AISparse-to-dense rewards improve language model post-training◆arXiv — cs.AIAI-native mobility dataset advances 6G handover and beam management◆arXiv — cs.AIMedHopQA benchmark tests LLM reasoning in biomedical Q&A◆arXiv — cs.CLRouters learn geometry of sparse mixture-of-experts◆arXiv — cs.AIStudy audits how LLMs generate political discourse during crises◆arXiv — cs.AIClassifier Context Rot: Monitor Performance Degrades with Context◆arXiv — cs.AIExecutable Agentic Memory for GUI Agent◆arXiv — cs.CLLongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced◆arXiv — cs.AISparse-to-dense rewards improve language model post-training◆arXiv — cs.AIAI-native mobility dataset advances 6G handover and beam management◆
home/cluster
ad slot opena single understated line lives here — sponsor wordmark + a short line.advertise on shipfeed →
§ feed · cluster

Meta and Stanford propose transformer cutting inference memory by 50%

May 11 · · primary fetch1 sourcecluster fcb314e9updated May 11 ·

Meta, Stanford, and University of Washington researchers propose methods to accelerate Byte Latent Transformer (BLT) generation, reducing inference memory bandwidth by over 50% without tokenization using diffusion and verification techniques.

read full article on marktechpost.com ↗
§ sources1 publication · timeline below
  1. marktechpost.comMeta and Stanford Researchers Propose Fast Byte Latent Transformer That Reduces Inference Memory Bandwidth by Over 50% Without Tokenizationprimary