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 15 minutes ago

IntervitensInc/internlm2_5-20b-llamafied

liked a model 15 minutes ago

ArliAI/InternLM2_5-20B-ArliAI-RPMax-v1.1

upvoted a paper 1 day ago

An Empirical Study of Qwen3 Quantization

View all activity

Organizations

xi0v's activity

upvoted a paper 1 day ago

An Empirical Study of Qwen3 Quantization

Paper • 2505.02214 • Published 4 days ago • 19

upvoted a paper 2 days ago

LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Paper • 2505.02625 • Published 3 days ago • 16

upvoted a paper 3 days ago

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Paper • 2503.09641 • Published Mar 12 • 38

upvoted a paper 10 days ago

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published 13 days ago • 41

upvoted a paper 15 days ago

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Paper • 2504.16078 • Published 16 days ago • 20

upvoted a paper 21 days ago

YourBench: Easy Custom Evaluation Sets for Everyone

Paper • 2504.01833 • Published Apr 2 • 20

upvoted an article 21 days ago

Article

Introducing HELMET

23 days ago

• 24

upvoted a paper 21 days ago

D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation

Paper • 2504.09454 • Published 25 days ago • 12

upvoted a paper 23 days ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published 24 days ago • 255

upvoted 2 collections 24 days ago

Shisa V2

A family of bilingual JA/EN LLMs • 27 items • Updated 22 days ago • 7

GLM-4-0414

GLM-4-0414 series model • 8 items • Updated 23 days ago • 123

upvoted a paper 27 days ago

DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning

Paper • 2504.07128 • Published Apr 2 • 83

upvoted 2 papers 28 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published about 1 month ago • 73

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published 29 days ago • 73

upvoted 5 papers about 1 month ago

FreSca: Unveiling the Scaling Space in Diffusion Models

Paper • 2504.02154 • Published Apr 2 • 19

ZClip: Adaptive Spike Mitigation for LLM Pre-Training

Paper • 2504.02507 • Published Apr 3 • 78

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Paper • 2504.00595 • Published Apr 1 • 36

AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation

Paper • 2503.19693 • Published Mar 25 • 75

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Paper • 2503.21144 • Published Mar 27 • 25