Di Liu

14

Papers

90

Total Citations

Papers (14)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

LUCAS: Layered Universal Codec Avatars

Instantaneous Perception of Moving Objects in 3D

Temporal Action Localization with Cross Layer Task Decoupling and Refinement

Improving Generalization With Domain Convex Game

DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image

Show and Segment: Universal Medical Image Segmentation via In-Context Learning

T2Bs: Text-to-Character Blendshapes via Video Generation

Layout-Agnostic Scene Text Image Synthesis with Diffusion Models

Causality Inspired Representation Learning for Domain Generalization

Pareto Domain Adaptation

Contrastive Graph Structure Learning via Information Bottleneck for Recommendation

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

Pairwise GUI Dataset Construction Between Android Phones and Tablets