Jen-Hao Rick Chang

Computer Science · Physical Sciences

10h-index338citations37works10.12yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(11), Natural Language Processing Techniques(10), Music and Audio Processing(10), Advanced Vision and Imaging(8), Generative Adversarial Networks and Image Synthesis(8)

Publications37 total

RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
arXiv (Cornell University)·2026Open Access
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
ArXiv.org·2026Open Access
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
arXiv (Cornell University)·2025Open Access
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
2025Open Access
3D Shape Tokenization via Latent Flow Matching
arXiv (Cornell University)·2024Open Access
Novel-view Acoustic Synthesis From 3D Reconstructed Rooms
2024· 3 cited
HUGS: Human Gaussian Splats
2024· 82 cited
Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications
2024· 13 cited
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
arXiv (Cornell University)·2024· 1 citedOpen Access
Corpus Synthesis for Zero-Shot ASR Domain Adaptation Using Large Language Models
2024· 2 cited
Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications
arXiv (Cornell University)·2023· 1 citedOpen Access
HUGS: Human Gaussian Splats
arXiv (Cornell University)·2023· 1 citedOpen Access
Novel-View Acoustic Synthesis from 3D Reconstructed Rooms
arXiv (Cornell University)·2023Open Access
Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
arXiv (Cornell University)·2023· 2 citedOpen Access
Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models
arXiv (Cornell University)·2023Open Access
Pointersect: Neural Rendering with Cloud-Ray Intersection
2023· 16 cited
FaceLit: Neural 3D Relightable Faces
2023· 18 cited
Text is all You Need: Personalizing ASR Models Using Controllable Speech Synthesis
2023· 7 cited
Pointersect: Neural Rendering with Cloud-Ray Intersection
arXiv (Cornell University)·2023· 2 citedOpen Access
FaceLit: Neural 3D Relightable Faces
arXiv (Cornell University)·2023Open Access
page 1 of 2Next →

Frequent Co-authors

Oncel Tuzel(28), Anurag Ranjan(12), Hema Swetha Koppula(12), Ting-Yao Hu(9), Karren Yang(8), Ashish Shrivastava(6), Raviteja Vemulapalli(6), Kwang Moo Yi(4), Aswin C. Sankaranarayanan(4), B. V. K. Vijaya Kumar(3), Hadi Pouransari(3), Muhammed Kocabas(2), James Gabriel(2), Dmitrii Marin(2), Anish Prabhu(2), Mohammad Rastegari(2), Mohammadreza Armandpour(2), Stefan Braun(2), Kyuyeon Hwang(2), Ozlem Kalinli(2)