A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Wenrui Bao, Zhiben Chen, Dan Xu, et al.
Learn2PD trains a lightweight filter to adaptively unmask tokens in diffusion LLMs, achieving up to 22.58x speedup without performance loss.
Yan Deng, Fei Xu
DreamFly introduces causal memory and receding-horizon diffusion planning to improve aerial vision-language navigation, achieving state-of-the-art results on the OpenFly benchmark.
Haodong Li, Shaoteng Liu, Tianyu Wang, et al.
Introduces Latent Dynamics Reasoning (LDR), a video world model that explicitly models latent dynamics via kinematic integration, achieving far better out-of-distribution extrapolation than video diffusion baselines.
He-Yen Hsieh, H. T. Kung
ReRound is a post-training quantization method that uses a conditional diffusion model to resolve midpoint ambiguity in round-to-nearest, improving low-bit LLM quantization without calibration data.
Unknown
Diffusion-DPO aligns diffusion models to human preferences by directly optimizing the model on user preference data using Direct Preference Optimization.
Unknown
This paper proposes an efficient policy class for offline reinforcement learning that outperforms most existing methods on simulated robotic tasks.
Unknown
This paper introduces DiffGS, a method that represents Gaussian Splatting as functions and trains a latent diffusion model to generate these functions, enabling 3D generation.
Unknown
This survey provides a comprehensive overview of diffusion models for 3D generation, covering methods, datasets, and future directions.
Unknown
A comprehensive survey of 3D generation methods, covering a decade of advances and categorizing approaches from GANs to diffusion models.
Unknown
Direct3D introduces a scalable 3D latent diffusion transformer for image-to-3D generation, achieving strong generalization and high-quality 3D outputs.
Yichun Shi, Peng Wang, Jianglong Ye, et al.
MVDream introduces a multi-view diffusion model that generates consistent multi-view images from text prompts, enabling robust 3D generation.
Unknown
Imagen Video introduces a text-conditional video generation system that adapts image diffusion models to produce high-definition videos from text prompts.