Inference Task

Inference tasks, encompassing the process of deriving conclusions from data or premises, are a central focus in machine learning, particularly within natural language processing and computer vision. Current research emphasizes improving the efficiency and accuracy of inference, focusing on model architectures like transformers and graph neural networks, and employing techniques such as chain-of-thought prompting, contrastive learning, and Bayesian inference to address challenges like bias, hallucination, and computational cost. These advancements have significant implications for various applications, including question answering, knowledge base construction, and real-time decision-making in resource-constrained environments.

Papers

December 20, 2023

Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes
Leonardo Banchi
Memory Trace Stochastic Process Quantum Advantage Inference Task Quantum Model Memory Efficiency Quantum Simulation Quantum Simulator

October 19, 2023

Contrastive Learning for Inference in Dialogue
Etsuko Ishii, Yan Xu, Bryan Wilie, Ziwei Ji, Holy Lovenia, Willy Chung, Pascale Fung
Contrastive Learning Scientific Inference Dialogue Utterance Inference Task Inductive Reasoning Semantic Gap Inductive Inference Inference Scheme

October 16, 2023

Theory of Mind for Multi-Agent Collaboration via Large Language Models
Huao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Michael Lewis, Katia Sycara
Multi Agent Reinforcement Learning Multi Agent Theoretical Understanding Human Mind LLM Based Agent Multi Agent Collaboration Inference Task

October 15, 2023

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
Boan Liu, Liang Ding, Li Shen, Keqin Peng, Yu Cao, Dazhao Cheng, Dacheng Tao
Language Model Mixture of Expert Large Scale Language Model Inference Task Representation Diversity Orthogonal Gradient

August 25, 2023

LLM2KB: Constructing Knowledge Bases using instruction tuned context aware Large Language Models
Anmol Nayak, Hari Prasad Timmapathini
Large Language Model Natural Language Processing Context Information Human Instruction Knowledge Base Inference Task Dense Passage Retrieval KG Completion

August 18, 2023

Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
Pengbo Hu, Ji Qi, Xingyu Li, Hong Li, Xinqi Wang, Bing Quan, Ruiyu Wang, Yi Zhou
Reasoning Task Visual Reasoning Multi Hop Reasoning Inference Task Tree of Thought

July 5, 2023

SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space
Lasha Abzianidze, Joost Zwarts, Yoad Winter
Natural Language Inference Strong Consistency Deep Space Spatial Reasoning Inference Task

July 1, 2023

InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs
Dalong Zhang, Xianzheng Song, Zhiyang Hu, Yang Li, Miao Tao, Binbin Hu, Lin Wang, Zhiqiang Zhang, Jun Zhou
Graph Neural Network Inference Task Graph Inference GNN Inference Scalable Architecture

May 26, 2023

With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness
Julius Steen, Juri Opitz, Anette Frank, Katja Markert
Robust Version Inference Task Faithfulness Test NLI Model Little Help NLI Datasets

May 24, 2023

Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds
Victoria Basmov, Yoav Goldberg, Reut Tsarfaty
Medical LLM Textual Entailment Inference Task Blind Spot Light Curtain Grammatical Inference

May 23, 2023

Sources of Hallucination by Large Language Models on Inference Tasks
Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Javad Hosseini, Mark Johnson, Mark Steedman
Natural Language Inference Content Hallucination Limited Memorization Source Table Inference Task

April 8, 2023

Training Neural Networks for Execution on Approximate Hardware
Tianmu Li, Shurui Li, Puneet Gupta
Neural Network Deep Learning Inference Task Approximate Computing Hardware Approximation

December 31, 2022

Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning
Wen Wu, Peng Yang, Weiting Zhang, Conghao Zhou, Xuemin, Shen
Deep Reinforcement Learning Edge Network Inference Task Collaborative Deep Neural Network Inference

November 24, 2022

Attention-based Feature Compression for CNN Inference Offloading in Edge Computing
Nan Li, Alexandros Iosifidis, Qi Zhang
Edge Computing Autoencoder Architecture Inference Task Feature Compression CNN Inference Device Edge Co Inference

October 24, 2022

Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing
Nan Li, Alexandros Iosifidis, Qi Zhang
Mobile Edge Computing Graph Reinforcement Learning Computation Offloading Inference Task Early Exit Multi Access Edge Computing

June 25, 2022

Multi-Variate Time Series Forecasting on Variable Subsets
Jatin Chauhan, Aravindan Raghuveer, Rishi Saket, Jay Nandy, Balaraman Ravindran
Scientific Inference Time Series Forecasting Multivariate Time Series Forecasting Forecasting Model Inference Task High Quality Subset

June 3, 2022

Multi-user Co-inference with Batch Processing Capable Edge Server
Wenqi Shi, Sheng Zhou, Zhisheng Niu, Miao Jiang, Lu Geng
Inference Task Collaborative Inference Neural Network Inference Edge Server Sub Task Decomposition

May 2, 2022

Paragraph-based Transformer Pre-training for Multi-Sentence Inference
Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti
Fact Checking Pre Trained Transformer Inference Task Multi Task Inference Sentence Inference

Inference Task

Papers

Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes

Contrastive Learning for Inference in Dialogue

Theory of Mind for Multi-Agent Collaboration via Large Language Models

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer

LLM2KB: Constructing Knowledge Bases using instruction tuned context aware Large Language Models

Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning

SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space

InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs

With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness

Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds

Sources of Hallucination by Large Language Models on Inference Tasks

Training Neural Networks for Execution on Approximate Hardware

Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning

Attention-based Feature Compression for CNN Inference Offloading in Edge Computing

Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing

Multi-Variate Time Series Forecasting on Variable Subsets

Multi-user Co-inference with Batch Processing Capable Edge Server

Paragraph-based Transformer Pre-training for Multi-Sentence Inference