3 24 1

Bozhou Li

zooblastlbz

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

MMSkills: Towards Multimodal Skills for General Visual Agents

upvoted a paper 5 days ago

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

upvoted a paper 6 days ago

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling

View all activity

Organizations

Collections 3

View 3 collections

Papers 11

models 5

datasets 2

zooblastlbz/OpenNewsArchieve

Viewer • Updated May 24, 2025 • 5.85M • 345

zooblastlbz/conceptual-12M-224

Viewer • Updated May 15, 2024 • 563k • 115 • 1

Bozhou Li

AI & ML interests

Recent Activity

Organizations

Collections 3

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

SmolVLM: Redefining small and efficient multimodal models

Kimi-VL Technical Report

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

SmolVLM: Redefining small and efficient multimodal models

Kimi-VL Technical Report

Papers 11

models 5

zooblastlbz/id-align

zooblastlbz/mmpe

zooblastlbz/scaling

zooblastlbz/lbz

zooblastlbz/dj

datasets 2

zooblastlbz/OpenNewsArchieve

zooblastlbz/conceptual-12M-224

Bozhou Li

AI & ML interests

Recent Activity

Organizations

Collections 3

Papers 11

models 5 Sort: Recently updated

datasets 2 Sort: Recently updated

models 5

datasets 2