Haiwen Diao

Paranioar's activity

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

authored a paper 13 days ago

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published 15 days ago • 46

authored a paper about 1 month ago

Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

Paper • 2606.15236 • Published Jun 16 • 22

authored a paper about 2 months ago

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76

submitted a paper to Daily Papers about 2 months ago

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76

authored 3 papers 2 months ago

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation

Paper • 2601.22153 • Published Jan 29 • 75

VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?

Paper • 2602.04802 • Published Feb 4 • 2

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 194

submitted a paper to Daily Papers 2 months ago

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 194

authored a paper 7 months ago

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

Paper • 2512.19693 • Published Dec 22, 2025 • 68

authored 2 papers 9 months ago

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

Paper • 2510.14979 • Published Oct 16, 2025 • 70

GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning

Paper • 2410.15266 • Published Oct 20, 2024

authored a paper 10 months ago

Visual Jigsaw Post-Training Improves MLLMs

Paper • 2509.25190 • Published Sep 29, 2025 • 37

authored 2 papers about 1 year ago

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

Paper • 2502.06788 • Published Feb 10, 2025 • 14

End-to-End Vision Tokenizer Tuning

Paper • 2505.10562 • Published May 15, 2025 • 22

authored a paper over 1 year ago

Autoregressive Video Generation without Vector Quantization

Paper • 2412.14169 • Published Dec 18, 2024 • 15

authored 4 papers about 2 years ago

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Paper • 2407.08303 • Published Jul 11, 2024 • 19

SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning

Paper • 2407.07523 • Published Jul 10, 2024 • 6

Unveiling Encoder-Free Vision-Language Models

Paper • 2406.11832 • Published Jun 17, 2024 • 55

Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching

Paper • 2404.18114 • Published Apr 28, 2024

authored a paper over 2 years ago

UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory

Paper • 2308.14316 • Published Aug 28, 2023