Dan Jacobellis PRO

danjacobellis's activity

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

upvoted 2 papers 2 days ago

Communication-Inspired Tokenization for Structured Image Representations

Paper • 2602.20731 • Published 4 days ago • 4

stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

Paper • 2602.08968 • Published 18 days ago • 1

upvoted 9 papers 3 days ago

Is Hierarchical Quantization Essential for Optimal Reconstruction?

Paper • 2601.22244 • Published 29 days ago • 1

Adaptive 1D Video Diffusion Autoencoder

Paper • 2602.04220 • Published 24 days ago • 5

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Paper • 2601.17124 • Published Jan 23 • 33

Learning a distance measure from the information-estimation geometry of data

Paper • 2510.02514 • Published Oct 2, 2025 • 1

Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding

Paper • 2602.19626 • Published 5 days ago • 3

Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

Paper • 2602.19320 • Published 5 days ago • 5

DODO: Discrete OCR Diffusion Models

Paper • 2602.16872 • Published 9 days ago • 9

A Generative-First Neural Audio Autoencoder

Paper • 2602.15749 • Published 10 days ago • 1

VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation

Paper • 2602.17133 • Published 9 days ago • 1

upvoted 2 papers 4 days ago

VidEoMT: Your ViT is Secretly Also a Video Segmentation Model

Paper • 2602.17807 • Published 8 days ago • 6

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers

Paper • 2602.18292 • Published 7 days ago • 10

upvoted a paper 8 days ago

MAEB: Massive Audio Embedding Benchmark

Paper • 2602.16008 • Published 10 days ago • 19

upvoted 3 papers 9 days ago

VLTSeg: Simple Transfer of CLIP-Based Vision-Language Representations for Domain Generalized Semantic Segmentation

Paper • 2312.02021 • Published Dec 4, 2023 • 1

Image Generation with a Sphere Encoder

Paper • 2602.15030 • Published 11 days ago • 12

Wavelet-based Positional Representation for Long Context

Paper • 2502.02004 • Published Feb 4, 2025 • 1

upvoted 3 papers 11 days ago

Don't Look Twice: Faster Video Transformers with Run-Length Tokenization

Paper • 2411.05222 • Published Nov 7, 2024 • 3

One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation

Paper • 2512.07829 • Published Dec 8, 2025 • 23

Supervised Learning as Lossy Compression: Characterizing Generalization and Sample Complexity via Finite Blocklength Analysis

Paper • 2602.04107 • Published 24 days ago • 1