Friedrich Marty

Smorty100

https://gitlab.com/users/Marty_Friedrich/projects

AI & ML interests

I'm most interested in content rerouting between LLM and VLLM agens for automation possibilities. Using templates for each agent which is then filled in by another agents inputs seems really useful.

Recent Activity

upvoted a paper about 6 hours ago

Nexus-Gen: A Unified Model for Image Understanding, Generation, and Editing

liked a Space 4 days ago

Qwen/Qwen-Image

reacted to chintankp's post with 😔 7 days ago

We’re excited to share that Llama Nemotron Super v1.5 -- our latest open reasoning model -- is leading the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, for models running on a single NVIDIA H100. Super v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. Besides leading accuracy, it also delivers high throughput. Key features: - Leading accuracy on multi-step reasoning, math, coding, and function-calling - Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples - Fully transparent training data on HF (Nemotron-Post-Training-Dataset-v1) Try Super v1.5 on build.nvidia.com or download from Hugging Face

View all activity

Organizations

None yet

upvoted a paper about 6 hours ago

Nexus-Gen: A Unified Model for Image Understanding, Generation, and Editing

Paper • 2504.21356 • Published Apr 30 • 1

upvoted 4 papers 10 days ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published 16 days ago • 274

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Paper • 2507.20984 • Published 11 days ago • 51

A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence

Paper • 2507.21046 • Published 11 days ago • 75

Agentic Reinforced Policy Optimization

Paper • 2507.19849 • Published 14 days ago • 133

upvoted 7 papers 21 days ago

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Paper • 2506.07491 • Published Jun 9 • 42

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published Jun 25 • 46

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

Paper • 2507.05240 • Published Jul 7 • 45

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models

Paper • 2507.07484 • Published 30 days ago • 17

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Paper • 2507.10524 • Published 25 days ago • 65

Replacing thinking with tool usage enables reasoning in small language models

Paper • 2507.05065 • Published Jul 7 • 15

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning

Paper • 2507.12508 • Published 23 days ago • 26

upvoted 3 papers 4 months ago

DreamO: A Unified Framework for Image Customization

Paper • 2504.16915 • Published Apr 23 • 25

Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation

Paper • 2504.17207 • Published Apr 24 • 29

Step1X-Edit: A Practical Framework for General Image Editing

Paper • 2504.17761 • Published Apr 24 • 93

upvoted a collection 6 months ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 11 items • Updated 18 days ago • 522

upvoted a collection 11 months ago

Llama 3.2

Collection

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 628

upvoted a paper 11 months ago

Scaling Granite Code Models to 128K Context

Paper • 2407.13739 • Published Jul 18, 2024 • 20

Friedrich Marty

AI & ML interests

Recent Activity

Organizations

Smorty100's activity