37 citations · 169 across the 28 of their papers we have counts for
34 papers
On the spectral properties of generative denoiser Jacobians
Alexandros Graikos, Nebojsa Jojic, Dimitris Samaras
Generative denoising models, such as diffusion and flow-matching, learn to sample from complex distributions by training a deep neural network denoiser to recover clean data from n…
Fast constrained sampling in pre-trained diffusion models
Alexandros Graikos, Nebojsa Jojic, Dimitris Samaras
Large denoising diffusion models, such as Stable Diffusion, have been trained on billions of image-caption pairs to perform text-conditioned image generation. As a byproduct of thi…
Investigating Agency of LLMs in Human-AI Collaboration Tasks
Ashish Sharma, Sudha Rao, Chris Brockett +3
Agency, the capacity to proactively shape events, is central to how humans interact and collaborate. While LLMs are being developed to simulate human behavior and serve as human-li…
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
Weijia Xu, Andrzej Banburski-Fahey, Nebojsa Jojic
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sa…
GPT is becoming a Turing machine: Here are some ways to program it
Ana Jojic, Zhen Wang, Nebojsa Jojic
We demonstrate that, through appropriate prompting, GPT-3 family of models can be triggered to perform iterative behaviours necessary to execute (rather than just write or recall)…
ThinkSum: Probabilistic reasoning over sets using large language models
Batu Ozturkler, Nikolay Malkin, Zhen Wang +1
Large language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evalu…