Dan Jacobellis PRO

danjacobellis's activity

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

upvoted a paper about 15 hours ago

Learning to Drive from a World Model

Paper • 2504.19077 • Published 16 days ago • 1

upvoted a paper 5 days ago

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Paper • 2505.02567 • Published 8 days ago • 66

upvoted 2 papers 15 days ago

Kimi-Audio Technical Report

Paper • 2504.18425 • Published 18 days ago • 16

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published 18 days ago • 41

upvoted 14 papers 22 days ago

DDT: Decoupled Diffusion Transformer

Paper • 2504.05741 • Published Apr 8 • 73

Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging

Paper • 2504.08635 • Published Apr 11 • 5

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published Apr 10 • 19

ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration

Paper • 2504.08591 • Published Apr 11 • 18

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Paper • 2504.08736 • Published Apr 11 • 47

MIEB: Massive Image Embedding Benchmark

Paper • 2504.10471 • Published 29 days ago • 16

Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability

Paper • 2504.08003 • Published Apr 9 • 49

Efficient Generative Model Training via Embedded Representation Warmup

Paper • 2504.10188 • Published 29 days ago • 12

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Paper • 2504.11455 • Published 28 days ago • 14

DataDecide: How to Predict Best Pretraining Data with Small Experiments

Paper • 2504.11393 • Published 28 days ago • 17

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

Paper • 2504.10483 • Published 29 days ago • 21

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Paper • 2504.13180 • Published 26 days ago • 17

Perception Encoder: The best visual embeddings are not at the output of the network

Paper • 2504.13181 • Published 26 days ago • 34

Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images

Paper • 2504.09621 • Published 30 days ago • 12

upvoted 2 papers about 1 month ago

Challenges and Paths Towards AI for Software Engineering

Paper • 2503.22625 • Published Mar 28 • 4

Your ViT is Secretly an Image Segmentation Model

Paper • 2503.19108 • Published Mar 24 • 21