Text Generation

YOUDREAM generates anatomically consistent, high-quality 3D animal models from text and 2D pose priors, pushing creative boundaries in text-to-3D generation.

ToMe: a novel training-free method dramatically improves semantic binding in text-to-image synthesis by intelligently merging related tokens, ensuring accurate alignment between generated images and t…

Generate multiple text drafts from a single language model pass with Superposed Decoding, significantly boosting efficiency!

SpeechAlign: Iteratively aligning speech generation models to human preferences via preference optimization, bridging distribution gaps for improved speech quality.

Simplified and generalized masked diffusion models achieve state-of-the-art results in discrete data generation, surpassing previous methods in text and image modeling.

ChatGPT amplifies gender bias in job applications, revealing AI’s potential to worsen labor market inequality.

Meta-DiffuB enhances sequence-to-sequence text diffusion models by using meta-exploration to learn a contextualized noise schedule, resulting in state-of-the-art performance.

Transformers’ learning dynamics depend heavily on initialization and Markovian data properties, leading to either global or local minima; this paper proves this, offers initialization guidelines, and …

Linear transformers efficiently learn sparse contextual bigrams by leveraging both in-context and global information, achieving polynomial sample complexity.

Active learning for video captioning is enhanced by a novel algorithm that prioritizes ’learnability’, diversity, and uncertainty to address annotation inconsistency.

LCGen: A novel method for view-consistent text-to-3D generation, resolving the ‘Janus Problem’ by strategically using low-certainty priors to align viewpoints and optimize the generation process.

Cost-robust contracts, inspired by statistical hypothesis tests, incentivize quality in LLM text generation, overcoming the moral hazard of pay-per-token models.

IF-Font: Revolutionary font generation using Ideographic Description Sequences (IDS) to surpass state-of-the-art methods in style transfer, especially for unique styles.

Accelerated discrete diffusion model sampling is achieved via novel discrete non-Markov diffusion models (DNDM) with predetermined transition times, enabling a training-free algorithm that significant…

Bridging the gap between continuous diffusion models and discrete data, this work introduces a novel boundary-conditional approach achieving superior performance in language modeling and image generat…

CONTEXTCITE pinpoints which parts of a given context led a language model to generate a specific statement, improving model verification and response quality.

AP-Adapter boosts text-to-image diffusion model generalization by using a two-stage prompt optimization method that leverages large language models and inter-model differences.

AdaNovo tackles data biases in de novo peptide sequencing by using Conditional Mutual Information, significantly improving PTM identification and overall accuracy.