Dan Jacobellis PRO

danjacobellis's activity

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

upvoted a paper about 6 hours ago

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

Paper • 2603.26425 • Published Mar 30 • 1

upvoted 7 papers 1 day ago

The Last Human-Written Paper: Agent-Native Research Artifacts

Paper • 2604.24658 • Published 8 days ago • 18

Representation Fréchet Loss for Visual Generation

Paper • 2604.28190 • Published 7 days ago • 27

Soft Anisotropic Diagrams for Differentiable Image Representation

Paper • 2604.21984 • Published 10 days ago • 5

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

Paper • 2605.00503 • Published 6 days ago • 8

Let ViT Speak: Generative Language-Image Pre-training

Paper • 2605.00809 • Published 6 days ago • 25

Hallucinations Undermine Trust; Metacognition is a Way Forward

Paper • 2605.01428 • Published 5 days ago • 17

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

Paper • 2605.00877 • Published 12 days ago • 13

upvoted 5 papers 4 days ago

Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolution

Paper • 2404.11273 • Published Apr 17, 2024 • 1

ViT-5: Vision Transformers for The Mid-2020s

Paper • 2602.08071 • Published Feb 8 • 2

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

Paper • 2307.06304 • Published Jul 12, 2023 • 36

FlexiViT: One Model for All Patch Sizes

Paper • 2212.08013 • Published Dec 15, 2022 • 2

High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator

Paper • 2510.10693 • Published Oct 12, 2025 • 1

updated a model 10 days ago

danjacobellis/FRAPPE

Updated 10 days ago

published a model 10 days ago

danjacobellis/FRAPPE

Updated 10 days ago

upvoted a paper 14 days ago

Neural Garbage Collection: Learning to Forget while Learning to Reason

Paper • 2604.18002 • Published 17 days ago • 2

upvoted a paper 15 days ago

Recurrent Video Masked Autoencoders

Paper • 2512.13684 • Published 16 days ago • 1

upvoted 2 papers 17 days ago

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

Paper • 2604.14228 • Published 23 days ago • 25

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips

Paper • 2502.07408 • Published 21 days ago • 59

upvoted a paper 18 days ago

CoD-Lite: Real-Time Diffusion-Based Generative Image Compression

Paper • 2604.12525 • Published 23 days ago • 1