-
RWTH Aachen University
- Aachen, Germany
- nekrasov.dev
- @kumuji
Starred repositories
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
A ESP32 based MQTT bridge for Treadmills for Home Assistant
Control a PitPat/Superun WalkingPad treadmill in Home Assistant over Bluetooth (incl. ESP32 Bluetooth proxy) — no MQTT, no extra hardware.
Arbitrary Reconstruction and Tracking of 4D Observation in the Wild
Browse media content with your own rules on Android TV
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, P…
A multi-thread crawler framework with many builtin image crawlers provided.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
[CVPR 2026 Workshop] Official code and models for Plain Mask Transformer (PMT).
Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation
[CVPR 2024] Probing the 3D Awareness of Visual Foundation Models
NEO Series: Native Vision-Language Models from First Principles
Official Repository for the paper "Getting to the Point: Why Pointing Improves LVLMs"
All of TÜV and DEKRA German driving theory exam questions and answers in English
[CVPR 2026] Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation
[ECCV 2026 Long Oral] Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding
Open source, cross-platform, user-mode tablet driver
[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.
PyTorch building blocks for the OLMo ecosystem
[CVPR 2026 Oral] "INSID3: Training-Free In-Context Segmentation with DINOv3"
MapAnything: Universal Feed-Forward Metric 3D Reconstruction