Xu Yang

20

Papers

174

Total Citations

Papers (20)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient

Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On

How to Configure Good In-Context Sequence for Visual Question Answering

KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models

MemoNav: Working Memory Model for Visual Navigation

Mimic In-Context Learning for Multimodal Tasks

Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation

Building Variable-Sized Models via Learngene Pool

Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks

Transformer as Linear Expansion of Learngene

Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark

A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability

Democratizing High-Fidelity Co-Speech Gesture Video Generation

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation

Number it: Temporal Grounding Videos like Flipping Manga

Long-Tail Class Incremental Learning via Independent Sub-prototype Construction

VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception

Vision Transformers as Probabilistic Expansion from Learngene

One Meta-tuned Transformer is What You Need for Few-shot Learning