Level Loop

"Level Loop" encompasses iterative processes within various computational frameworks, aiming to improve efficiency, accuracy, or robustness. Current research focuses on applying iterative loops to enhance novel view synthesis (using methods like progressive Gaussian initialization), improve large language model generation (by mitigating issues like hallucinations and repetitive text), and optimize deep learning performance (through joint graph and operator-level optimizations). These advancements have significant implications for computer graphics, natural language processing, and high-performance computing, leading to more efficient algorithms and improved model outputs across diverse applications.

Papers

August 1, 2024

LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting
Zhenyu Bao, Guibiao Liao, Kaichen Zhou, Kanglin Liu, Qing Li, Guoping Qiu
Gaussian Splatting Novel View Synthesis View Synthesis Sparse Input View Level Loop

July 8, 2024

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
Maor Ivgi, Ori Yoran, Jonathan Berant, Mor Geva
Large Language Model Language Model High Uncertainty Anticipation Human Answer Mistake Exercise Repetition Level Loop

March 18, 2024

Loops On Retrieval Augmented Generation (LoRAG)
Ayush Thakur, Rashmi Vashisth
Retrieval Augmented Generation Text Generation Iterative Algorithm Level Loop Retrieval Augmented Text Generation

January 21, 2024

Discussion of Loop Expansion and Introduction of Series Cutting Functions to Local Potential Approximation: Complexity Analysis Using Green's Functions, Cutting Of Nth-Order Social Interactions For Progressive Safety
Yasuko Kawahata
Information Flow Complexity Analysis Level Loop Local Approximation Bradley Terry Filter Bubble

July 15, 2023

On Loop Formulas with Variables
Joohyung Lee, Yunsong Meng
First Order Logic Program Variable Model First Order Logic Stable Model Semantics Level Loop

April 25, 2023

Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures
Evangelos Georganas, Dhiraj Kalamkar, Kirill Voronin, Abhisek Kundu, Antonio Noack, Hans Pabst, Alexander Breuer, Alexander Heinecke
Deep Learning High Performance Computing Tensor Data Computational System Level Loop

March 29, 2023

Preventing Object-centric Discovery of Unsound Process Models for Object Interactions with Loops in Collaborative Systems: Extended Version
Janik-Vasily Benzin, Gyunam Park, Stefanie Rinderle-Ma
Process Mining Object Centric Object Discovery Process Model Object Interaction Collaborative Environment Process Discovery Level Loop Object Centric Process Mining

March 7, 2023

Root Cause Identification for Collective Anomalies in Time Series given an Acyclic Summary Causal Graph with Loops
Charles K. Assaad, Imad Ez-zejjari, Lei Zan
Time Series Causal Graph Causal Relation Root Cause Level Loop Summary Causal Graph Collective Anomaly

October 22, 2022

ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations
Zhiying Xu, Jiafan Xu, Hongding Peng, Wei Wang, Xiaoliang Wang, Haoran Wan, Haipeng Dai, Yixu Xu, Hao Cheng, Kun Wang, Guihai Chen
Deep Learning Graph Drawing Graph Optimization Brick Wall Deep Learning Compiler Level Loop Alt Text Operator Level Optimization

May 27, 2022

Will Bilevel Optimizers Benefit from Loops
Kaiyi Ji, Mingrui Liu, Yingbin Liang, Lei Ying
Bilevel Optimization Convergence Analysis Hessian Vector Product Gradient Complexity Level Loop

November 29, 2021

Comparing Machine Learning and Interpolation Methods for Loop-Level Calculations
Ibrahim Chahrour, James D. Wells
Machine Learning High Energy Physic Radial Basis Function First Integral Interpolation Method Level Loop Self Loop

Level Loop

Papers

LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty

Loops On Retrieval Augmented Generation (LoRAG)

Discussion of Loop Expansion and Introduction of Series Cutting Functions to Local Potential Approximation: Complexity Analysis Using Green's Functions, Cutting Of Nth-Order Social Interactions For Progressive Safety

On Loop Formulas with Variables

Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures

Preventing Object-centric Discovery of Unsound Process Models for Object Interactions with Loops in Collaborative Systems: Extended Version

Root Cause Identification for Collective Anomalies in Time Series given an Acyclic Summary Causal Graph with Loops

ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations

Will Bilevel Optimizers Benefit from Loops

Comparing Machine Learning and Interpolation Methods for Loop-Level Calculations