Rauno Ryystö

raunoryys

·

AI & ML interests

None yet

Recent Activity

liked a model about 9 hours ago

BreezeBlue/Breeze-TTS-2

liked a Space about 9 hours ago

BreezeBlue/breeze-tts-2-demo

reacted to DedeProGames's post with 🤯 about 13 hours ago

how is this possible

View all activity

Organizations

None yet

upvoted 2 collections about 14 hours ago

GLiNER2.5 Models

6 items • Updated 10 days ago • 40

Typed decision models (System One)

Open models that answer yes/no, choice and score questions with probabilities, plus typed-decisions, a public benchmark to compare them. • 17 items • Updated 5 days ago • 3

upvoted 2 collections about 18 hours ago

K2 Horizon GGUF

5 items • Updated 1 day ago • 1

Kolibri-1

2 items • Updated 1 day ago • 5

upvoted a paper 1 day ago

Rubric Rewards from Item Response Theory

Paper • 2609.35646 • Published 7 days ago • 13

upvoted an article 2 days ago

Article

New in llama.cpp: Decision Models

ggml-org

•

2 days ago

• 71

upvoted a paper 2 days ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 222

upvoted 5 collections 2 days ago

Voxtral

Mistral AI Audio models. • 4 items • Updated Apr 14 • 18

Devstral 2

A couple of agentic LLMs for software engineering tasks, excelling at using tools to explore codebases, edit multiple files, and power SWE Agents. • 2 items • Updated Mar 2 • 61

Mistral Large 3

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated Dec 2, 2025 • 104

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 82

Mistral Medium 3.5

Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated Apr 29 • 24

upvoted a collection 3 days ago

Decision models

GGUF decision models for the /v1/systemone API in llama.cpp • 6 items • Updated 2 days ago • 15

upvoted 2 papers 3 days ago

LOCI: Spatial Linear Memory for Streaming World Models

Paper • 2609.40222 • Published 4 days ago • 11

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization

Paper • 2610.00906 • Published 4 days ago • 64

upvoted 4 papers 4 days ago

Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

Paper • 2609.40358 • Published 5 days ago • 13

AIM: Agentic Idea Management for Automated Research

Paper • 2609.38445 • Published 6 days ago • 50

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 5 days ago • 112

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

Paper • 2609.40285 • Published 5 days ago • 21

upvoted a paper 5 days ago

Disaggregated Quantization: Specializing LLM Prefill and Decode

Paper • 2609.26333 • Published 13 days ago • 91