Search Results for author:
Found 14 papers, 7 papers with code
On the Coexistence and Ensembling of Watermarks
We perform the first study of coexistence of deep image watermarking methods and, contrary to intuition, we find that various open-source watermarks can coexist with only minor impacts on image quality and decoding robustness.
Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models
Fine-tuning large language models on small, high-quality datasets can enhance their performance on specific downstream tasks.
Universal In-Context Approximation By Prompting Fully Recurrent Models
We demonstrate that RNNs, LSTMs, GRUs, Linear RNNs, and linear gated architectures such as Mamba and Hawk/Griffin can also serve as universal in-context approximators.
Risks and Opportunities of Open-Source Generative AI
Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education.
Near to Mid-term Risks and Opportunities of Open-Source Generative AI
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education.
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs).
Prompting a Pretrained Transformer Can Be a Universal Approximator
Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of transformer models, our theoretical understanding of these fine-tuning methods remains limited.
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning with a fraction of the parameters.
Language Models as a Service: Overview of a New Paradigm and its Challenges
This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, replicability, reliability, and trustworthiness of LMaaS.
Language Model Tokenizers Introduce Unfairness Between Languages
Recent language models have shown impressive multilingual performance, even when not explicitly trained for it.
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
Improving and guaranteeing the robustness of deep learning models has been a topic of intense research.
Robustness of Unsupervised Representation Learning without Labels
When used in adversarial training, they improve most unsupervised robustness measures, including certified robustness.
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
As robotics matures and increases in complexity, it is more necessary than ever that robot autonomy research be reproducible.
Learning Camera Miscalibration Detection
Self-diagnosis and self-repair are some of the key challenges in deploying robotic platforms for long-term real-world applications.
