Cihang Xie

cihangxie's activity

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

upvoted a paper 5 days ago

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

Paper • 2601.15369 • Published 6 days ago • 16

updated a collection 5 days ago

OpenVision 3

Collection

A Family of Unified Visual Encoder with Unified Visual Representation. • 4 items • Updated about 12 hours ago • 1

submitted a paper to Daily Papers 5 days ago

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

Paper • 2601.15369 • Published 6 days ago • 16

upvoted a paper 20 days ago

SimpleMem: Efficient Lifelong Memory for LLM Agents

Paper • 2601.02553 • Published 22 days ago • 37

upvoted a paper 2 months ago

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards

Paper • 2511.07403 • Published Nov 10, 2025 • 15

upvoted a collection 2 months ago

SpatialThinker

Collection

This collection consists of SpatialThinker 3B and 7B model checkpoints, and STVQA-7K, a Spatial VQA dataset used for training the models. • 4 items • Updated Nov 12, 2025 • 1

upvoted a paper 3 months ago

When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought

Paper • 2511.02779 • Published Nov 4, 2025 • 59

liked a model 3 months ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated Nov 4, 2025 • 3.12M • 3.12k

upvoted a paper 3 months ago

LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

Paper • 2510.22946 • Published Oct 27, 2025 • 18

updated a collection 5 months ago

OpenVision 2

Collection

9 items • Updated Sep 3, 2025 • 10

authored 2 papers 5 months ago

AHELM: A Holistic Evaluation of Audio-Language Models

Paper • 2508.21376 • Published Aug 29, 2025 • 9

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

Paper • 2509.01644 • Published Sep 1, 2025 • 34

updated a collection 5 months ago

OpenVision 2

Collection

9 items • Updated Sep 3, 2025 • 10

upvoted a paper 5 months ago

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

Paper • 2509.01644 • Published Sep 1, 2025 • 34

liked a model 5 months ago

UCSC-VLAA/gpt-image-edit-training

Image-to-Image • Updated Jul 30, 2025 • 25

updated a collection 6 months ago

HQ-Edit

Collection

7 items • Updated Aug 15, 2025

liked a dataset 6 months ago

UCSC-VLAA/gpt-edit-simpler

Viewer • Updated Aug 1, 2025 • 1.55M • 512 • 7

updated a collection 6 months ago

GPT-Image-Edit-1.5M

Collection

6 items • Updated Aug 15, 2025 • 2

New activity in UCSC-VLAA/GPT-Image-Edit-1.5M 6 months ago

Simpler version of the dataset

❤️ 2

9

#3 opened 6 months ago by

sayakpaul