Latest

Every published item, in order · 7652 items
Oct 20
PapersBuildersSelected11:47
Addressed-Memory Writes Fail at Reasoning in Qwen3 and DeepSeek Beds

Memory write-injection looks like a cheap way to add knowledge to a deployed model, but these results show the added facts cannot be chained into multi-hop reasoning by the model itself — orchestration must live in the application layer. Builders wiring RAG-style memory into agents should chain written atoms explicitly in prompts or system logic, and benchmark vendors should adopt coverage, synergy and distortion reporting. The tested beds include Chinese frontier models Qwen3 and DeepSeek, making the findings broadly relevant across model families.

arXiv: DeepSeek@Wei Gao et al. (4)Source
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
PapersBuildersSelected09:50
Statistical Framework Unifies Adam, Shampoo and Muon Optimizers

The practical value lies in the unification: one statistical principle explains Adam, Shampoo and Muon, so practitioners can tune or combine these optimizers with a clearer theoretical map instead of treating them as folklore. Engineers training GPT-scale models get concrete alternatives, since MND beats Distributed Shampoo and KL-Shampoo on stability and runtime, and MND-Muon wins 21 of 24 paired runs against Muon. Researchers in optimizer design can extend the covariance-approximation framework to new preconditioners.

arXiv cs.LG@Tetiana Parshakova et al. (3)Source
PapersBuildersMulti-source09:50
Chinese content研究显示小模型的多语言效率常被英文基准掩盖:印度语系分词器覆盖不足

这篇论文用数据戳破一个常见假设:小模型“多语言省内存”的说法对印度语系根本不成立。卡纳达语用户只有英文用户 6% 的上下文,数字很扎心,做本地化的开发者应该看看。

Event
arXiv cs.LG@Anna PramodSource

Only the latest 2000 items are listed; for older ones see the daily archive