Knut Jägersberg

KnutJaegersberg

·

jagersbergknut

AI & ML interests

NLP, opinion mining, narrative intelligence

Recent Activity

liked a model about 6 hours ago

google/embeddinggemma-2

upvoted a collection 3 days ago

liked a model 4 days ago

Aleph-Alpha/Kolibri-1-BF16

View all activity

Organizations

upvoted a collection 3 days ago

Kolibri-1

2 items • Updated 4 days ago • 12

upvoted a paper 4 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 20 days ago • 224

upvoted a collection 4 days ago

DeepSeek-V4

10 items • Updated 27 days ago • 920

upvoted a collection 7 days ago

Intern-Decision

4 items • Updated 11 days ago • 20

upvoted a collection 19 days ago

Bonsai-2

4 items • Updated 19 days ago • 164

upvoted a paper 22 days ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 26 days ago • 69

upvoted a paper about 1 month ago

Language Models Can Control Their Own Attention

Paper • 2609.02737 • Published Sep 2 • 79

upvoted an article about 1 month ago

Article

Technical writing in the agentic era

joelniklaus

•

Aug 31

• 17

upvoted 3 collections about 2 months ago

Ornith-1.5

13 items • Updated 17 days ago • 183

Qwen3.8

4 items • Updated Aug 13 • 552

Hybrid Diffusion

3 items • Updated Aug 15 • 7

upvoted 3 collections 2 months ago

J.O.S.I.E-2

The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 22 items • Updated Aug 7 • 11

Metis

Metis persistent-memory model family based on Qwen3.5, including 4B, 9B, and 27B parameter scales. • 4 items • Updated Jul 31 • 8

Instella-MoE ✨

Family of fully open 16B MoE LLM with 2.8B active params per token, trained on AMD Instinct™ MI300 & MI325 GPUs. https://arxiv.org/abs/2609.00791 • 6 items • Updated 18 days ago • 19

upvoted 3 collections 3 months ago

Bonsai 27B

10 items • Updated Jul 15 • 248

LingBot-World-V2

5 items • Updated Sep 4 • 17

LingBot-Vision

5 items • Updated Jul 7 • 11

upvoted 3 collections 4 months ago

Laguna M.1

Our first M-class coding agent model, designed for long-horizon work. Apache 2.0. • 4 items • Updated Jul 21 • 24

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated Aug 26 • 267

Zamba2-VL

A suite of vision-language models based on Zamba2. • 3 items • Updated Jun 9 • 5