A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Liangchen Li, Jiajun He
Bidirectional consistency models extend consistency models to enable both forward and reverse sampling, improving image generation quality and flexibility.
Unknown
AudioLCM introduces a latent consistency model for efficient text-to-audio generation, enabling high-quality synthesis in few sampling steps.
Bo Liu, Qiang Liu
Maglev is a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention, trains with a memory consistency loss, and improves validation loss and downstream benchmarks.
Unknown
Cycle3D proposes a unified 3D generation framework that enhances diversity and texture consistency through a generation-reconstruction cycle during the denoising process.
Unknown
Latent Consistency Models enable few-step inference for high-resolution image synthesis by distilling consistency into pre-trained latent diffusion models.
Unknown
This paper proposes consistency models as a new policy class for reinforcement learning, offering efficient and expressive alternatives to diffusion-based policies.
Unknown
This paper simplifies consistency models by deriving a differential consistency condition in continuous time, linking them to diffusion models.
Unknown
SelfCheckGPT is a zero-resource, black-box hallucination detection method for generative LLMs that uses sampling-based consistency checking.
Siqi Kou, Lanxiang Hu, Zhe He, et al.
Consistency LLMs accelerate LLM inference by refining the model to consistently predict the fixed point from any state, achieving 2.4-3.4x speedup over autoregressive decoding.
Unknown
SCPO uses self-consistency to generate preference pairs for unsupervised LLM training, improving reasoning without human labels.
Luzhe Huang, Hanlong Chen, Tairan Liu, et al.
GedankenNet eliminates the need for labeled or experimental training data in hologram reconstruction by using a physics-consistency loss and synthetic random images.