Knut Jägersberg's picture

Knut Jägersberg

KnutJaegersberg

·

jagersbergknut

AI & ML interests

NLP, opinion mining, narrative intelligence

Recent Activity

liked a model about 9 hours ago

XiaomiMiMo/MiMo-VL-7B-RL-2508

upvoted a paper 1 day ago

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

upvoted a collection 1 day ago

gpt-oss-abliterated

View all activity

Organizations

upvoted a paper 1 day ago

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Paper • 2508.01191 • Published 7 days ago • 173

upvoted a collection 1 day ago

gpt-oss-abliterated

1 item • Updated 2 days ago • 6

upvoted a paper 8 days ago

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

Paper • 2507.22448 • Published 10 days ago • 60

upvoted a collection 8 days ago

Cogito v2 Preview

6 items • Updated 9 days ago • 22

upvoted an article 8 days ago

Article

Introducing Command A Vision: Multimodal AI built for Business

By

and 3 others •

8 days ago

• 61

upvoted a collection 16 days ago

GLiCLass-V3

Models for zero-shot text classification that are up to 50 times faster than Cross-Encoders and show the same or higher accuracy. • 7 items • Updated 18 days ago • 13

upvoted an article 19 days ago

Article

OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models

By

and 3 others •

21 days ago

• 47

upvoted a collection 25 days ago

EXAONE-4.0

EXAONE unified model series of 1.2B and 32B, integrating non-reasoning and reasoning modes. • 20 items • Updated 10 days ago • 44

upvoted a collection 26 days ago

MetaStone-S1

The open-source model of MetaStone-S1. • 4 items • Updated 9 days ago • 9

upvoted a collection 27 days ago

MLM vs CLM

65 items • Updated Jul 3 • 1

upvoted a collection 29 days ago

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 15 items • Updated 11 days ago • 83

upvoted a collection 30 days ago

ThinkPRM

Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 • 8 items • Updated 10 days ago • 3

upvoted a collection about 1 month ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 12 items • Updated 4 days ago • 69

upvoted an article about 1 month ago

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

Jul 8

• 614

upvoted a collection about 1 month ago

POLAR

5 items • Updated about 1 month ago • 12

upvoted 2 papers about 1 month ago

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published Jul 2 • 59

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

Paper • 2507.01352 • Published Jul 2 • 52

upvoted 2 collections about 1 month ago

Reward Models

Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge • 8 items • Updated 18 days ago • 19

Weaver

The models and datasets for Weaver: Shrinking the Generation-Verification Gap with Weak Verifiers • 21 items • Updated Jun 24 • 2

upvoted a paper about 2 months ago

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

Paper • 2503.05139 • Published Mar 7 • 4