Related papers: Language Generation in the Limit: Noise, Loss, and…

Generative Artificial Intelligence (AI) has rapidly become a powerful tool, capable of generating various types of data, such as images and text. However, despite the significant advancement of generative AI, time series generative AI…

Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research problem. Achieving controllable generation requires semantically…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where…

We present a constructive approach to bounded $\ell_2$-gain adaptive control with noisy measurements for linear time-invariant scalar systems with uncertain parameters belonging to a finite set. The gain bound refers to the closed-loop…

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation. This capability is desirable in a variety of applications, including conversational…

This paper presents InfiniteAudio, a simple yet effective strategy for generating infinite-length audio using diffusion-based text-to-audio methods. Current approaches face memory constraints because the output size increases with input…

Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models. However, such feedback is known to introduce systematic biases into the training process and it obscures a…

Generalization is a central problem in machine learning, especially when data is limited. Using prior information to enforce constraints is the principled way of encouraging generalization. In this work, we propose to leverage the prior…

This paper considers the problem of variable-length lossy source coding. The performance criteria are the excess distortion probability and the cumulant generating function of codeword lengths. We derive a non-asymptotic fundamental limit…

Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, a comparison of various generation strategies for low-resource language settings is lacking. While…

This paper introduces the Luca-Noise Reflex Protocol (LN-RP), a computational framework for analyzing noise-driven persona emergence in large language models. By injecting stochastic noise seeds into the initial generation state, we observe…

We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues…

We address the non-redundant random generation of k words of length n from a context-free language. Additionally, we want to avoid a predefined set of words. We study the limits of a rejection-based approach, whose time complexity is shown…

Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of…

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…

We address the problem of human-in-the-loop control for generating prosody in the context of text-to-speech synthesis. Controlling prosody is challenging because existing generative models lack an efficient interface through which users can…

Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These works typically operate under a strong realizability assumption: that the input data is drawn from…

Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space. Recent advancements in Large Language Models…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…