Xinyu Ma

MaxyLee's activity

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

liked a model 11 days ago

openbmb/MiniCPM-SALA

Text Generation • 9B • Updated about 18 hours ago • 1.08k • 494

upvoted a paper 19 days ago

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Paper • 2603.12793 • Published 21 days ago • 38

upvoted 2 papers about 1 month ago

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Paper • 2602.22766 • Published Feb 26 • 42

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 120

upvoted a paper 2 months ago

MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios?

Paper • 2512.23219 • Published Dec 29, 2025 • 4

liked a dataset 2 months ago

daisq/MM-UAVBench

Viewer • Updated Jan 18 • 6.5k • 5.08k • 5

liked 2 models 6 months ago

PerceptronAI/Isaac-0.1

Image-Text-to-Text • 3B • Updated 14 days ago • 55.2k • 114

openbmb/VoxCPM-0.5B

Text-to-Speech • Updated Sep 19, 2025 • 505 • 768

upvoted 2 papers 10 months ago

MiniCPM4: Ultra-Efficient LLMs on End Devices

Paper • 2506.07900 • Published Jun 9, 2025 • 96

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 190

upvoted a paper 12 months ago

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

Paper • 2504.10479 • Published Apr 14, 2025 • 308

upvoted a collection about 1 year ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 10 items • Updated Mar 2 • 560

New activity in MaxyLee/KVG about 1 year ago

Update dataset card: add link to paper, change task category

#1 opened about 1 year ago by

nielsr

New activity in MaxyLee/DeepPerception-FGVR about 1 year ago

Add image-text-to-text pipeline tag, transformers library, and link to paper and project page

#1 opened about 1 year ago by

nielsr

New activity in MaxyLee/KVG-Bench about 1 year ago

Change Github link to specific folder, change task category to `image-text-to-text`

#2 opened about 1 year ago by

nielsr

New activity in MaxyLee/DeepPerception about 1 year ago

Add library_name to metadata

#1 opened about 1 year ago by

nielsr

authored a paper about 1 year ago

DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding

Paper • 2503.12797 • Published Mar 17, 2025 • 32

updated a dataset about 1 year ago

MaxyLee/KVG-Bench

Viewer • Updated Mar 20, 2025 • 1.34k • 22

updated a model about 1 year ago

MaxyLee/DeepPerception

Image-Text-to-Text • 8B • Updated Mar 19, 2025 • 26 • 2

upvoted a collection about 1 year ago

DeepPerception

Collection

5 items • Updated Mar 19, 2025 • 1