Xin Li

lixin67's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 2 papers 22 days ago

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Paper • 2412.18319 • Published 28 days ago • 37

YuLan-Mini: An Open Data-efficient Language Model

Paper • 2412.17743 • Published 29 days ago • 64

upvoted a collection 27 days ago

Open Image Preferences

Collection

Containing all artifacts for the Stable Diffusion 3.5L vs Flux Dev image preference community sprint. • 14 items • Updated Dec 19, 2024 • 6

upvoted a paper 28 days ago

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Paper • 2408.03314 • Published Aug 6, 2024 • 54

upvoted 5 papers about 1 month ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 139

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

Paper • 2412.09604 • Published Dec 12, 2024 • 35

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Paper • 2412.09596 • Published Dec 12, 2024 • 93

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 104

Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions

Paper • 2412.08737 • Published Dec 11, 2024 • 53

upvoted 3 articles 5 months ago

view article

Article

A failed experiment: Infini-Attention, and why we should keep trying?

Aug 14, 2024

• 57

view article

Article

Key Insights into the Law of Vision Representations in MLLMs

By •

Sep 2, 2024

• 17

view article

Article

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

By •

Aug 19, 2024

• 76

upvoted an article 7 months ago

view article

Article

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

By •

Jun 11, 2024

• 50

upvoted 3 collections about 1 year ago

Model Merging

Collection

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12, 2024 • 225

Awesome feedback datasets

Collection

A curated list of datasets with human or AI feedback. Useful for training reward models or applying techniques like DPO. • 19 items • Updated Apr 12, 2024 • 67

Awesome SFT datasets

Collection

A curated list of interesting datasets to fine-tune language models with. • 43 items • Updated Apr 12, 2024 • 127

upvoted a paper over 1 year ago

AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model

Paper • 2309.16058 • Published Sep 27, 2023 • 55