Karsten Kuhnke PRO

mindchain's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 2 hours ago

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Paper • 2504.19413 • Published Apr 28 • 36

upvoted 3 papers about 3 hours ago

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published Nov 20 • 122

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14 • 122

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 12 days ago • 84

upvoted an article about 3 hours ago

view article

Article

Diffusers welcomes FLUX-2

• 
• 
• +6

Nov 25

•

166

upvoted a paper about 3 hours ago

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Paper • 2512.20605 • Published 6 days ago • 54

upvoted a collection about 3 hours ago

— Awesome RL datasets 📈 —

Collection

3 items • Updated Sep 23 • 1

upvoted 2 collections about 4 hours ago

— Long-context post-training 🧶 —

Collection

Resources for post-training LLMs with long-context samples • 5 items • Updated Sep 14 • 6

smol2operator Release

Collection

4 items • Updated Sep 23 • 24

upvoted a paper about 4 hours ago

VL-JEPA: Joint Embedding Predictive Architecture for Vision-language

Paper • 2512.10942 • Published 18 days ago • 11

upvoted a collection about 4 hours ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13 • 177

upvoted 5 articles 1 day ago

view article

Article

Codex is Open Sourcing AI models

• 
• 

19 days ago

•

51

view article

Article

New in llama.cpp: Model Management

• 

18 days ago

•

100

view article

Article

AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems

• 

6 days ago

•

31

view article

Article

The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator

• 

12 days ago

•

34

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

26 days ago

•

544

upvoted 4 collections 1 day ago

Google Gemma Scope 2 - Neuronpedia

Collection

Google Gemma Scope 2: JumpReLU SAEs for Gemma 2 interpretability. 270M PT/IT, 1B PT variants. Neuronpedia integration. Mechanistic analysis. • 11 items • Updated 1 day ago • 1

SigLIP2

Collection

36 items • Updated Jul 10 • 101

Gemma 3n

Collection

4 items • Updated Jul 10 • 253

EmbeddingGemma

Collection

3 items • Updated Sep 11 • 105