Sheng Li

21

Papers

33

Total Citations

Papers (21)

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety

Watermarking One for All: A Robust Watermarking Scheme Against Partial Image Theft

Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal

The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers

Unified Dense Prediction of Video Diffusion

Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning

MoFRR: Mixture of Diffusion Models for Face Retouching Restoration

Embedding Robust Watermarking into Pattern to Protect the Copyright of Ceramic Artifacts

Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks

Frozen CLIP Transformer Is an Efficient Point Cloud Encoder

Open-Set Graph Domain Adaptation via Separate Domain Alignment

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

Purified and Unified Steganographic Network

Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs

Searching for Fast Model Families on Datacenter Accelerators

Frame Flexible Network

TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching

DRAW: Defending Camera-shooted RAW Against Image Manipulation

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

NeurIPS 2022arXiv