7 papers
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
Yu Wu, Minsik Jeon, Jen-Hao Rick Chang +2
We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-inv…
Velox: Learning Representations of 4D Geometry and Appearance
Anagh Malik, Dorian Chan, Xiaoming Zhao +3
We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downst…
LiTo: Surface Light Field Tokenization
Jen-Hao Rick Chang, Xiaoming Zhao, Dorian Chan +1
We propose a 3D latent representation that jointly models object geometry and view-dependent appearance. Most prior works focus on either reconstructing 3D geometry or predicting v…
3D Shape Tokenization via Latent Flow Matching
Jen-Hao Rick Chang, Yuyang Wang, Miguel Angel Bautista Martin +4
We introduce a latent 3D representation that models 3D surfaces as probability density functions in 3D, i.e., p(x,y,z), with flow-matching. Our representation is specifically desig…
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula +8
In this work, we propose Mutual Reinforcing Data Synthesis (MRDS) within LLMs to improve few-shot dialogue summarization task. Unlike prior methods that require external knowledge,…
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Hadi Pouransari, Chun-Liang Li, Jen-Hao Rick Chang +4
Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various…