Search Results for author:
Found 10 papers, 4 papers with code
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
In practice, particularly when learning from human feedback in an online sense, adversaries can observe and react to the learning process and inject poisoned samples that optimize adversarial objectives better than when they are restricted to poisoning a static dataset once, before the learning algorithm is applied.
LitLLMs, LLMs for Literature Review: Are we there yet?
This paper explores the zero-shot abilities of recent Large Language Models (LLMs) in assisting with the writing of literature reviews based on an abstract.
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
We use an efficient data curation process to ensure our data is high-quality and license-permissive.
Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation
Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established.
LitLLM: A Toolkit for Scientific Literature Review
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.
Rich Human Feedback for Text-to-Image Generation
We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions.
Faithful Knowledge Distillation
To address these questions, we introduce a faithful imitation framework to discuss the relative calibration of confidences and provide empirical and certified methods to evaluate the relative calibration of a student w. r. t.
Efficient Error Certification for Physics-Informed Neural Networks
Recent work provides promising evidence that Physics-Informed Neural Networks (PINN) can efficiently solve partial differential equations (PDE).
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play
Standard empirical risk minimization (ERM) training can produce deep neural network (DNN) models that are accurate on average but under-perform in under-represented population subgroups, especially when there are imbalanced group distributions in the long-tailed training data.
(Certified!!) Adversarial Robustness for Free!
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models.
