UniWorld-Design: From Pixel Generation to Layer-Native Design
Paper • 2608.03971 • Published • 15
taesiri PRO
taesiri
AI & ML interests
AGI ... one linear layer at a time
Recent Activity
submitted a paper about 1 hour ago
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents upvoted a paper about 2 hours ago
UniWorld-Design: From Pixel Generation to Layer-Native Design upvoted a paper about 2 hours ago
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space BridgingOrganizations
upvoted 5
papers about 2 hours ago
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Paper • 2608.03316 • Published • 12
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Paper • 2608.03974 • Published • 51
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Paper • 2608.02711 • Published • 24
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
Paper • 2608.03509 • Published • 9
upvoted 2
papers about 14 hours ago
upvoted a paper about 22 hours ago
upvoted 5
papers 1 day ago
Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis
Paper • 2608.01973 • Published • 16
WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning
Paper • 2607.29613 • Published • 22
SWE-Touch: Benchmarking Coding Agents When Users Touch the Code
Paper • 2608.02499 • Published • 22
WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
Paper • 2608.02603 • Published • 30
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
Paper • 2608.02023 • Published • 142
upvoted 5
papers 2 days ago
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction
Paper • 2607.29677 • Published • 17
Meshy T2: Fast Native Mesh Generation with Flow Matching
Paper • 2607.28675 • Published • 48
N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens
Paper • 2607.23782 • Published • 56
QQWorld: Quantile-Quantile Matching for World Model Regularization
Paper • 2607.28415 • Published • 28
Scaling Properties of Text Conditioning in Visual Generation
Paper • 2607.29679 • Published • 32
upvoted a paper 4 days ago
upvoted a paper 5 days ago