Dan Jacobellis PRO

danjacobellis's activity

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

upvoted 5 papers about 7 hours ago

Dynamic View Synthesis as an Inverse Problem

Paper • 2506.08004 • Published 1 day ago • 2

Vision Transformers Don't Need Trained Registers

Paper • 2506.08010 • Published 1 day ago • 9

Pre-trained Large Language Models Learn Hidden Markov Models In-context

Paper • 2506.07298 • Published 2 days ago • 16

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published 1 day ago • 24

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Paper • 2506.07491 • Published 2 days ago • 31

upvoted 2 papers 5 days ago

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Paper • 2506.03147 • Published 7 days ago • 57

Native-Resolution Image Synthesis

Paper • 2506.03131 • Published 7 days ago • 18

upvoted a paper 14 days ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published 21 days ago • 73

upvoted 6 papers 19 days ago

dKV-Cache: The Cache for Diffusion Language Models

Paper • 2505.15781 • Published 20 days ago • 16

Vid2World: Crafting Video Diffusion Models to Interactive World Models

Paper • 2505.14357 • Published 22 days ago • 26

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

Paper • 2505.15045 • Published 21 days ago • 54

MMaDA: Multimodal Large Diffusion Language Models

Paper • 2505.15809 • Published 20 days ago • 87

Scaling Law for Quantization-Aware Training

Paper • 2505.14302 • Published 22 days ago • 73

Text Generation Beyond Discrete Token Sampling

Paper • 2505.14827 • Published 21 days ago • 10

upvoted 6 papers 20 days ago

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition

Paper • 2505.13380 • Published 22 days ago • 5

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning

Paper • 2505.13866 • Published 22 days ago • 16

Training-Free Watermarking for Autoregressive Image Generation

Paper • 2505.14673 • Published 21 days ago • 12

Latent Flow Transformer

Paper • 2505.14513 • Published 21 days ago • 27

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published 25 days ago • 72

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published 21 days ago • 130