Deng Cai

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

PersonalView: Multi-View Consistent Human Image Customization via In-Context Learning

AlignChat: Endowing LLMs with End-to-End Speech-to-Text Chat Capability through Token-Level Representation Alignment

LEMUR: Leveraging Vision-Language Models for Fine-Grained Multimodal Retrieval

Controlling Thinking Speed in Reasoning Models

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

UniHDA: A Unified and Versatile Framework for Generalized Hybrid Domain Adaptation

RaCNN: Region-aware Convolutional Neural Network with Global Receptive Field

Simple and Fast CNN for Vision

PersonalVideo: High ID-Fidelity Video Customization With Static Images

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models

Dynamic Alignment of Representations for Enhanced Chain-of-Thought Reasoning in Large Language Models