Latest

Every published item, in order · 8120 items
Nov 4
PapersBuildersSelected12:00
MobileSpec Trains LLM Specialists on iPhones Using Forward Passes Only

Skipping backpropagation means on-device fine-tuning no longer needs training-grade memory, letting a shared 8B model be personalized overnight on consumer hardware like an iPhone 16 Pro. The 89-100% success-rate jump for a phone-use agent suggests practical deployment paths for on-device agents handling private data. Practitioners working on edge AI, quantization or RLVR-style training should examine FuRA-S as an alternative to LoRA-based ES methods.

arXiv cs.LG@Liyan Tan et al. (6)Source
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
PapersBuildersSelected11:52
LeanSparse Cuts GPU Memory for Sparse-Attention LLM Serving

The key insight is that prefill memory spikes, not just KV cache size, throttle concurrency — streaming layer histories through reusable buffers removes that admission bottleneck. Engineers running long-context inference on SGLang can adopt the design to serve more users per GPU without changing model weights. Compared with HiSparse and ECHO, the gains come from better indexing rather than more hardware.

arXiv: DeepSeek@Zaifeng Pan et al. (6)Source

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