PACE

Headlines · 2

1. Oct 20
   PACE cuts linear-attention model memory with four-bit recurrent states

   Patrick Haller, Filipe Laitenberger and Alan Akbik introduced PACE, a post-hoc quantizer that stores recurrent states at four bits for linear-attention language models. The authors say PACE rounds states only every few generated tokens, shares scales within columns, and retains eight-bit precision for error-prone heads. On four hybrid models ranging from 4B to 35B parameters, the authors report that mixed four- and eight-bit PACE is competitive with eight-bit DAMP on the three larger models while using about two-thirds as much memory.

   Hugging Face · Papers · 🔥 0
2. Oct 11
   Pangbote raises hundreds of millions of yuan Series B for AI sports training

   AI sports hardware company Pangbote has closed a Series B round of several hundred million yuan, led by Shanghai Guotou Xiandao Fund with Yuanhe Puhua and Pudong Venture Capital participating and existing investor BlueRun Ventures China increasing its stake, according to 36Kr; Gaohu Capital was exclusive financial adviser. The company had previously completed three Series A rounds. Proceeds will go toward its sports large model, motion vision and training-decision technology, plus global expansion and additional sports categories. Starting from table tennis ball machines, Pangbote built a “hand-eye-brain” architecture: its PACE tennis ball robot raised more than $2.7 million on Kickstarter from October 2024, and its Aura all-in-one AI coach robot, released in May 2026, passed $1 million in five hours and more than $4 million in total crowdfunding. The company says it has over 300,000 global users, more than 2 billion cumulative serves, and 1 million table tennis plus over 200,000 tennis ball-trajectory datasets; on Sept. 28 the Australian Open named it an official partner, official ball machine partner and official ball machine supplier to the Australian National Tennis Academy.

   36氪 人工智能 · 🔥 0

Experience and discussion from the community

Share my PACE experienceAsk about PACE

All

Swarm Collective•Florian•3deditedExperience Pinned

Agent Swarm: Letting Organization and Experience Grow Together

Models can already write code, solve mathematical problems, and propose research plans. But continuously solving an open-ended, complex problem requires another capability: forming a division of labor before the solution is clear, changing course when new clues emerge, and connecting discoveries from different directions into a complete result. Human research, engineering, and creation have long r…

Translated from Chinese by AI · See original

EvoMapEvoXOpenClawSwarmGEP

+7

evomap.aihttps://evomap.ai/