Ting Pan

PhyscalX's activity

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

upvoted a paper 19 days ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published 19 days ago • 62

upvoted 3 papers 2 months ago

Defeating the Training-Inference Mismatch via FP16

Paper • 2510.26788 • Published Oct 30, 2025 • 29

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 108

Uniform Discrete Diffusion with Metric Path for Video Generation

Paper • 2510.24717 • Published Oct 28, 2025 • 40

upvoted a collection 2 months ago

🐻 URSA

Collection

URSA: Uniform Discrete Diffusion with Metric Path for Video Generation • 6 items • Updated Nov 2, 2025 • 6

upvoted a paper 3 months ago

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Paper • 2510.14979 • Published Oct 16, 2025 • 66

upvoted a paper 9 months ago

GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation

Paper • 2504.02782 • Published Apr 3, 2025 • 57

upvoted 2 papers 10 months ago

Video-T1: Test-Time Scaling for Video Generation

Paper • 2503.18942 • Published Mar 24, 2025 • 90

Position: Interactive Generative Video as Next-Generation Game Engine

Paper • 2503.17359 • Published Mar 21, 2025 • 61

upvoted a paper 11 months ago

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

Paper • 2502.06788 • Published Feb 10, 2025 • 13

upvoted a paper about 1 year ago

Autoregressive Video Generation without Vector Quantization

Paper • 2412.14169 • Published Dec 18, 2024 • 14

upvoted a paper over 1 year ago

Unveiling Encoder-Free Vision-Language Models

Paper • 2406.11832 • Published Jun 17, 2024 • 54