Jie Ren

16

Papers

93

Total Citations

Papers (16)

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention

RRM: Robust Reward Model Training Mitigates Reward Hacking

Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models

Defining and Quantifying the Emergence of Sparse Concepts in DNNs

Explaining Neural Networks Semantically and Quantitatively

MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment

HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection

Monitoring Primitive Interactions During the Training of DNNs

Likelihood Ratios for Out-of-Distribution Detection

Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Exploring the Limits of Out-of-Distribution Detection

Pluralistic Image Completion with Gaussian Mixture Models

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning