High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion
Paper
•
2502.12752
•
Published
•
2
hjkim
hojie11
·
AI & ML interests
Computer Vision, 3D Vision, Anomaly Detection
Recent Activity
upvoted
a
paper
1 day ago
High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion
Organizations
None yet
hojie11's activity
upvoted
8
papers
1 day ago
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
Paper
•
2502.13144
•
Published
•
33
LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models
Paper
•
2502.14834
•
Published
•
20
Dynamic Concepts Personalization from Single Videos
Paper
•
2502.14844
•
Published
•
12
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper
•
2502.14786
•
Published
•
85
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Paper
•
2502.14739
•
Published
•
85
TESS 2: A Large-Scale Generalist Diffusion Language Model
Paper
•
2502.13917
•
Published
•
4
Qwen2.5-VL Technical Report
Paper
•
2502.13923
•
Published
•
130
upvoted
a
paper
2 days ago
upvoted
5
papers
3 days ago
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Paper
•
2502.12464
•
Published
•
26
Continuous Diffusion Model for Language Modeling
Paper
•
2502.11564
•
Published
•
48
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
Paper
•
2502.10458
•
Published
•
27
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
Paper
•
2502.13143
•
Published
•
28
Phantom: Subject-consistent video generation via cross-modal alignment
Paper
•
2502.11079
•
Published
•
48
upvoted
6
papers
8 days ago
Detailed Human-Centric Text Description-Driven Large Scene Synthesis
Paper
•
2311.18654
•
Published
•
2
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
Paper
•
2502.08690
•
Published
•
39
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper
•
2502.08910
•
Published
•
139
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
Paper
•
2502.06608
•
Published
•
32
Humanity's Last Exam
Paper
•
2501.14249
•
Published
•
62
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
Paper
•
2502.03544
•
Published
•
42