Alan

hiyata's activity

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

upvoted 6 papers about 24 hours ago

Coevolving Representations in Joint Image-Feature Diffusion

Paper • 2604.17492 • Published 8 days ago • 3

Hybrid Policy Distillation for LLMs

Paper • 2604.20244 • Published 5 days ago • 10

EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model

Paper • 2604.10268 • Published 16 days ago • 9

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

Paper • 2604.21689 • Published 4 days ago • 20

WorldMark: A Unified Benchmark Suite for Interactive Video World Models

Paper • 2604.21686 • Published 4 days ago • 34

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

Paper • 2604.17295 • Published 8 days ago • 81

upvoted 3 papers 3 days ago

Exploring Spatial Intelligence from a Generative Perspective

Paper • 2604.20570 • Published 5 days ago • 21

A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

Paper • 2604.19572 • Published 6 days ago • 18

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published 5 days ago • 229

upvoted a paper 6 days ago

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

Paper • 2604.16044 • Published 10 days ago • 73

upvoted 2 papers 9 days ago

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Paper • 2604.15284 • Published 11 days ago • 24

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 12 days ago • 111

upvoted a paper 11 days ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 13 days ago • 86

upvoted a paper 12 days ago

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

Paper • 2604.09132 • Published 17 days ago • 53

upvoted 6 papers 13 days ago

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published about 1 month ago • 360

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published 25 days ago • 489

EXAONE 4.5 Technical Report

Paper • 2604.08644 • Published 18 days ago • 66

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Paper • 2604.06870 • Published 19 days ago • 41

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Paper • 2604.08995 • Published 17 days ago • 48

FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios

Paper • 2604.07413 • Published 19 days ago • 94