taesiri PRO

taesiri's activity

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

submitted a paper to Daily Papers about 10 hours ago

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

Paper • 2512.14067 • Published 1 day ago • 4

submitted 4 papers to Daily Papers about 11 hours ago

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives

Paper • 2512.14699 • Published about 19 hours ago • 13

MMGR: Multi-Modal Generative Reasoning

Paper • 2512.14691 • Published about 19 hours ago • 54

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Paper • 2512.14614 • Published about 20 hours ago • 43

Olmo 3

Paper • 2512.13961 • Published 1 day ago • 5

submitted 5 papers to Daily Papers 1 day ago

Towards Interactive Intelligence for Digital Humans

Paper • 2512.13674 • Published 2 days ago • 9

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

Paper • 2512.12967 • Published 2 days ago • 80

Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?

Paper • 2512.13281 • Published 2 days ago • 38

KlingAvatar 2.0 Technical Report

Paper • 2512.13313 • Published 2 days ago • 32

Memory in the Age of AI Agents

Paper • 2512.13564 • Published 2 days ago • 82

submitted 5 papers to Daily Papers 2 days ago

Exploring MLLM-Diffusion Information Transfer with MetaCanvas

Paper • 2512.11464 • Published 5 days ago • 11

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder

Paper • 2512.11749 • Published 5 days ago • 34

PersonaLive! Expressive Portrait Image Animation for Live Streaming

Paper • 2512.11253 • Published 5 days ago • 24

The N-Body Problem: Parallel Execution from Single-Person Egocentric Video

Paper • 2512.11393 • Published 5 days ago • 2

V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties

Paper • 2512.11799 • Published 5 days ago • 29

submitted 5 papers to Daily Papers 5 days ago

MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos

Paper • 2512.10881 • Published 6 days ago • 27

Stronger Normalization-Free Transformers

Paper • 2512.10938 • Published 6 days ago • 17

Confucius Code Agent: An Open-sourced AI Software Engineer at Industrial Scale

Paper • 2512.10398 • Published 6 days ago • 5

Evaluating Gemini Robotics Policies in a Veo World Simulator

Paper • 2512.10675 • Published 6 days ago • 15

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

Paper • 2512.10791 • Published 6 days ago • 5