Juanxi Tian

Juanxi's activity

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

upvoted 2 papers 4 days ago

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 6 days ago • 172

MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory

Paper • 2511.22609 • Published 10 days ago • 47

upvoted a paper 6 days ago

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

Paper • 2512.01816 • Published 6 days ago • 87

upvoted a paper 8 days ago

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

Paper • 2511.20561 • Published 12 days ago • 31

upvoted 2 papers about 1 month ago

Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs

Paper • 2510.23127 • Published Oct 27 • 5

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Paper • 2510.23479 • Published Oct 27 • 14

upvoted a collection 2 months ago

Efficient AI (Optimization)

Collection

4 items • Updated Oct 18 • 1

upvoted 2 papers 2 months ago

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4 • 263

DINOv3

Paper • 2508.10104 • Published Aug 13 • 285

upvoted a paper 4 months ago

ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents

Paper • 2507.22827 • Published Jul 30 • 99

upvoted 2 papers 6 months ago

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Paper • 2506.03147 • Published Jun 3 • 58

Taming LLMs by Scaling Learning Rates with Gradient Grouping

Paper • 2506.01049 • Published Jun 1 • 38

upvoted a paper 8 months ago

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Paper • 2504.00999 • Published Apr 1 • 95

upvoted a paper 9 months ago

WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes

Paper • 2503.13435 • Published Mar 17 • 18

upvoted 2 papers about 1 year ago

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Paper • 2402.09240 • Published Feb 14, 2024 • 5

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Paper • 2410.06373 • Published Oct 8, 2024 • 36