Amasia NYU

Amasia-MLLM's activity

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

jihanyang 

authored 2 papers about 2 months ago

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published Nov 6, 2025 • 37

Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts

Paper • 2511.04655 • Published Nov 6, 2025 • 7

EdwinHuang 

authored a paper about 2 months ago

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published Nov 6, 2025 • 37

conan1024hao 

authored a paper 3 months ago

VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

Paper • 2509.19002 • Published Sep 23, 2025 • 2

conan1024hao 

updated a dataset 5 months ago

Amasia-MLLM/AmasiaIns-1M

Preview • Updated Aug 5, 2025 • 92

conan1024hao 

authored a paper 7 months ago

Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs

Paper • 2505.15075 • Published May 21, 2025 • 1

conan1024hao 

updated a model 10 months ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-he-5step-20250303

4B • Updated Mar 3, 2025 • 9

conan1024hao 

published a model 10 months ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-he-5step-20250303

4B • Updated Mar 3, 2025 • 9

conan1024hao 

updated a model 10 months ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-zh-5step-20250228

4B • Updated Feb 28, 2025 • 5

conan1024hao 

published a model 10 months ago

Amasia-MLLM/Qwen2.5-VL-3B-GRPO-zh-5step-20250228

4B • Updated Feb 28, 2025 • 5

jihanyang 

authored a paper 10 months ago

UniTok: A Unified Tokenizer for Visual Generation and Understanding

Paper • 2502.20321 • Published Feb 27, 2025 • 30

conan1024hao 

updated a dataset 10 months ago

Amasia-MLLM/A-OKVQA

Viewer • Updated Feb 27, 2025 • 2.08k • 21

conan1024hao 

published a dataset 10 months ago

Amasia-MLLM/A-OKVQA

Viewer • Updated Feb 27, 2025 • 2.08k • 21

jihanyang 

authored a paper 11 months ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28, 2025 • 123

conan1024hao 

published a dataset 11 months ago

Amasia-MLLM/GLDv2-images

Updated Jan 19, 2025 • 1

jihanyang 

authored a paper about 1 year ago

Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces

Paper • 2412.14171 • Published Dec 18, 2024 • 24

jihanyang 

authored a paper over 1 year ago

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Paper • 2406.16860 • Published Jun 24, 2024 • 63

jihanyang 

authored 2 papers almost 2 years ago

V-IRL: Grounding Virtual Intelligence in Real Life

Paper • 2402.03310 • Published Feb 5, 2024 • 16

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding

Paper • 2211.16312 • Published Nov 29, 2022