Sheng Li

Affiliations

University of Georgia

papers

225

total citations

papers (23)

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

NEURIPS 2022arXiv

citations

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

ICML 2024arXiv

citations

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

ICML 2025arXiv

citations

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

AAAI 2024arXiv

citations

DRAW: Defending Camera-shooted RAW Against Image Manipulation

ICCV 2023arXiv

citations

Purified and Unified Steganographic Network

CVPR 2024arXiv

citations

Unified Dense Prediction of Video Diffusion

CVPR 2025arXiv

citations

Frame Flexible Network

CVPR 2023arXiv

citations

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

CVPR 2025

citations

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

ICML 2025arXiv

citations

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

CVPR 2025

citations

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

AAAI 2025arXiv

citations

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

CVPR 2025

citations

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

ICLR 2025

citations

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

AAAI 2025

citations

MoFRR: Mixture of Diffusion Models for Face Retouching Restoration

ICCV 2025arXiv

citations

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

ICCV 2023

citations

Open-Set Graph Domain Adaptation via Separate Domain Alignment

AAAI 2024

citations

Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning

CVPR 2025

citations

Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks

AAAI 2025

citations

Sheng Li

Affiliations

papers (23)

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

Searching for Fast Model Families on Datacenter Accelerators

Frozen CLIP Transformer Is an Efficient Point Cloud Encoder

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

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

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

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

DRAW: Defending Camera-shooted RAW Against Image Manipulation

Purified and Unified Steganographic Network

Unified Dense Prediction of Video Diffusion

Frame Flexible Network

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

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

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

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

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

MoFRR: Mixture of Diffusion Models for Face Retouching Restoration

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

Open-Set Graph Domain Adaptation via Separate Domain Alignment

Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning

Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks

papers (23)

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

Searching for Fast Model Families on Datacenter Accelerators

Frozen CLIP Transformer Is an Efficient Point Cloud Encoder

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

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

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

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

DRAW: Defending Camera-shooted RAW Against Image Manipulation

Purified and Unified Steganographic Network

Unified Dense Prediction of Video Diffusion

Frame Flexible Network

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

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

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

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

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

MoFRR: Mixture of Diffusion Models for Face Retouching Restoration

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

Open-Set Graph Domain Adaptation via Separate Domain Alignment

Subspace Constraint and Contribution Estimation for Heterogeneous Federated Learning

Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks