Rauno Ryystö

raunoryys

·

AI & ML interests

None yet

Recent Activity

liked a dataset about 1 hour ago

LiquidAI/d1-decision-index

liked a Space about 2 hours ago

FineEnvs/multi-harness-rl-slides

liked a model about 2 hours ago

LiquidAI/d1-omni-600M

View all activity

Organizations

None yet

upvoted an article about 2 hours ago

Article

Multimodal open d1 decision models for the edge

LiquidAI

•

about 2 hours ago

• 12

upvoted a paper about 4 hours ago

Bolmo: Byteifying the Next Generation of Language Models

Paper • 2512.15586 • Published Dec 17, 2025 • 20

upvoted a collection about 6 hours ago

Nemotron Labs IMO 2026

Checkpoints, training data and benchmark from 'An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics' (IMO 2026). • 7 items • Updated 26 days ago • 10

upvoted an article about 6 hours ago

Article

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

nvidia

•

about 6 hours ago

• 7

upvoted a paper about 9 hours ago

Stop Comparing LLM Agents Without Disclosing the Harness

Paper • 2605.23950 • Published May 7 • 1

upvoted a paper about 10 hours ago

UNREAL: Unifying Retrieval and Long-Context with a Single Model

Paper • 2610.08463 • Published 2 days ago • 19

upvoted 5 papers about 11 hours ago

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

Paper • 2610.08430 • Published 2 days ago • 10

MiniCorp: The Last Mile of the AI Agent Firm

Paper • 2610.05912 • Published 3 days ago • 15

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published 2 days ago • 60

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

Paper • 2610.04109 • Published 6 days ago • 18

Capability-Driven Self-Evolution of Agent Memory

Paper • 2610.06361 • Published 3 days ago • 14

upvoted a collection 1 day ago

EmbeddingGemma 2

1 item • Updated 1 day ago • 14

upvoted 2 articles 1 day ago

Article

autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model

autotrust

•

10 days ago

• 218

Article

autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training

autotrust

•

8 days ago

• 165

upvoted a paper 1 day ago

OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

Paper • 2609.39490 • Published 8 days ago • 23

upvoted a collection 1 day ago

Clef

Clef is a family of open-weight decision models trained by Cloudflare, optimized for speed, quality and a new vision encoder. • 2 items • Updated 2 days ago • 3

upvoted a collection 2 days ago

Apertus v1.5 datasets

This collection contains datasets used for the continuous pre-training and post-training (SFT, RL and Alignment) of Apertus 1.5. • 6 items • Updated 3 days ago • 1

upvoted a paper 2 days ago

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

Paper • 2610.00972 • Published 7 days ago • 51

upvoted 2 collections 3 days ago

GLiNER2.5 Models

6 items • Updated 13 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 8 days ago • 3