Perspective accurate splatting
Matthias Zwicker, Jussi Räsänen, Mario Botsch, et al.
A novel point rendering algorithm using homogeneous coordinates for perspective-correct splatting with EWA filtering and GPU implementation.
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Matthias Zwicker, Jussi Räsänen, Mario Botsch, et al.
A novel point rendering algorithm using homogeneous coordinates for perspective-correct splatting with EWA filtering and GPU implementation.
Unknown
This paper introduces two methods, 2IWIL and IC-GAIL, to improve imitation learning from imperfect demonstrations by weighting or filtering unreliable data.
Shifu Chen, Yanqing Zhou, Yaru Chen, et al.
fastp is an ultra-fast all-in-one FASTQ preprocessor that performs quality control, adapter trimming, and filtering in a single scan, achieving 2-5x speedup over existing tools.
B. Sheth
Proposes a learning-based framework for personalized information filtering agents, implemented as 'Newt', using relevance feedback and genetic algorithms to adapt to user interests.
Tapas Kanungo, David M. Mount, Nathan S. Netanyahu, et al.
Presents a simple and efficient kd-tree-based filtering algorithm for Lloyd's k-means clustering with data-sensitive runtime analysis and empirical validation.
Xiaoyuan Su, Taghi M. Khoshgoftaar
A comprehensive survey of collaborative filtering techniques, categorizing them into memory-based, model-based, and hybrid approaches while addressing key challenges like data sparsity and scalability.
Jing Chen, Zheng Liu, Xu Huang, et al.
This perspective paper reviews how large language models can transform personalization from passive filtering to active, interactive, and explainable user engagement.
Unknown
STaR bootstraps reasoning in language models by iteratively generating rationales, filtering correct ones, and fine-tuning, with rationalization to learn from failures.
Unknown
Leverages Gemini LLM to generate generalizable multilingual text and code embeddings via synthetic data and filtering.
Unknown
BLIP introduces a unified VLP framework with a multimodal encoder-decoder and a captioning-filtering method to learn from noisy web data.
Unknown
Explores many-shot in-context learning by filtering examples via answer correctness and studying learning dynamics.