Xi's picture

Xi

xi0v

·

AI & ML interests

Reinforcement learning, Diffusion Model Merging, LLM Merging, Model Editing and Vision/Multimodal Model Fine-tuning.

Recent Activity

liked a model 5 minutes ago

Super-shuhe/InstantID-FaceID-6M

liked a model 5 minutes ago

stabilityai/stable-diffusion-xl-base-1.0

liked a Space 5 minutes ago

multimodalart/InstantID-FaceID-6M

View all activity

Organizations

xi0v's activity

upvoted a paper about 20 hours ago

Modifying Large Language Model Post-Training for Diverse Creative Writing

Paper • 2503.17126 • Published 4 days ago • 23

upvoted a paper 3 days ago

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

Paper • 2503.16257 • Published 5 days ago • 22

upvoted an article 6 days ago

Article

Run ComfyUI workflows for free on Spaces

Jan 14, 2024

• 65

upvoted 2 papers 7 days ago

BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

Paper • 2503.13434 • Published 8 days ago • 24

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

Paper • 2503.12885 • Published 8 days ago • 41

upvoted 2 collections 8 days ago

DPO

Various useful datasets with preference optimization • 16 items • Updated Jan 23 • 5

abliteration loras

Extracted adapters for removing censorship in models • 3 items • Updated Jan 21 • 2

upvoted a paper 9 days ago

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation

Paper • 2503.10618 • Published 12 days ago • 17

upvoted 2 papers 11 days ago

Transformers without Normalization

Paper • 2503.10622 • Published 12 days ago • 134

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Paper • 2503.09516 • Published 13 days ago • 24

upvoted an article 12 days ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

14 days ago

• 343

upvoted a paper 12 days ago

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

Paper • 2502.20172 • Published 26 days ago • 28

upvoted 4 papers 14 days ago

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

Paper • 2503.07027 • Published 15 days ago • 26

MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning

Paper • 2503.07365 • Published 15 days ago • 54

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 213

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Paper • 2503.07067 • Published 15 days ago • 29

upvoted 2 papers 16 days ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published 19 days ago • 84

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

Paper • 2503.04724 • Published 19 days ago • 66

upvoted a collection 19 days ago

cool datasets

158 items • Updated 6 days ago • 15