Kyle Tuft's picture

Kyle Tuft

Chilangosta

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 hour ago

ComfyUI-R1: Exploring Reasoning Models for Workflow Generation

upvoted a paper about 2 hours ago

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

liked a model about 16 hours ago

mistralai/Magistral-Small-2506

View all activity

Organizations

None yet

Chilangosta's activity

upvoted a paper about 1 hour ago

ComfyUI-R1: Exploring Reasoning Models for Workflow Generation

Paper • 2506.09790 • Published about 21 hours ago • 16

upvoted a paper about 2 hours ago

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Paper • 2506.09350 • Published 1 day ago • 23

upvoted a paper 3 days ago

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Paper • 2506.06276 • Published 6 days ago • 18

upvoted 2 papers 5 days ago

ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development

Paper • 2506.05010 • Published 7 days ago • 62

Aligning Latent Spaces with Flow Priors

Paper • 2506.05240 • Published 7 days ago • 25

upvoted 2 papers 7 days ago

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

Paper • 2506.02096 • Published 10 days ago • 51

MiMo-VL Technical Report

Paper • 2506.03569 • Published 8 days ago • 70

upvoted a paper 11 days ago

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Paper • 2505.23380 • Published 14 days ago • 23

upvoted a collection 12 days ago

Alchemist

📊 Dataset and 🏆 checkpoints for paper 📝 "Alchemist: Turning Public Text-to-Image Data into Generative Gold" • 7 items • Updated 16 days ago • 14

upvoted 6 papers 12 days ago

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Paper • 2505.19297 • Published 18 days ago • 74

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers

Paper • 2505.23758 • Published 14 days ago • 23

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

Paper • 2505.21784 • Published 16 days ago • 18

VidText: Towards Comprehensive Evaluation for Video Text Understanding

Paper • 2505.22810 • Published 15 days ago • 20

ZeroGUI: Automating Online GUI Learning at Zero Human Cost

Paper • 2505.23762 • Published 14 days ago • 45

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Paper • 2505.23716 • Published 14 days ago • 31

upvoted 2 collections 13 days ago

Uncensored Gemma 3 MLX

13 items • Updated Apr 24 • 2

Jack of all Trades Models

Home of the Personality Engine series, models that can be molded to fit any task or purpose. • 2 items • Updated 20 days ago • 5

upvoted a paper 14 days ago

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

Paper • 2505.21333 • Published 16 days ago • 39

upvoted an article 24 days ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13, 2024

• 610

upvoted a collection 24 days ago

OpenThinkIMG

OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images. • 5 items • Updated 17 days ago • 3