Estimated Team Strength

Estimating team strength, or the overall capability of a system composed of multiple interacting agents, is a burgeoning research area across diverse fields. Current research focuses on developing robust methods for assessing team strength in various contexts, including multi-robot systems (using control barrier functions to maintain communication graph robustness), multimodal models for emotion recognition (leveraging optimal transport and multimodal foundation models), and language models (exploring techniques like concept distillation and dynamic logit fusion to improve weaker models). These advancements have significant implications for improving the performance and reliability of complex systems, ranging from autonomous robotics to AI-driven decision-making in healthcare and other domains.

Papers

November 7, 2023

CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
Angelika Romanou, Syrielle Montariol, Debjit Paul, Leo Laugier, Karl Aberer, Antoine Bosselut
Real World Causal Discovery Causal Structure Causal Relationship Causal Reasoning Estimated Team Strength Causal Interpretation Rule Abstraction

October 23, 2023

Strong and Efficient Baselines for Open Domain Conversational Question Answering
Andrei C. Coman, Gianni Barlacchi, Adrià de Gispert
Open Domain Question Answering Estimated Team Strength Dense Passage Retrieval Efficient Baseline Open Domain Conversational Question Answering

October 19, 2023

Probing LLMs for hate speech detection: strengths and vulnerabilities
Sarthak Roy, Ashish Harshavardhan, Animesh Mukherjee, Punyajoy Saha
Large Language Model Medical LLM Hate Speech Hate Speech Detection Context Example Security Vulnerability Estimated Team Strength Toxic Language

October 2, 2023

Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification
Eurico Almeida, Bruno Silva, Jorge Batista
Diversity Awareness Estimated Team Strength Decouple Re Identification Multi Branch Identification Task

September 29, 2023

STRONG -- Structure Controllable Legal Opinion Summary Generation
Yang Zhong, Diane Litman
Estimated Team Strength Abstract Argumentation Controllable Summarization Legal Summarization Argument Role

September 20, 2023

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration
Xinghao Wu, Xuefeng Liu, Jianwei Niu, Guogang Zhu, Shaojie Tang
Full Potential Personalized Federated Learning Estimated Team Strength Personalized Model Client Collaboration Efficient Collaboration Unknown Distribution

September 19, 2023

Generative AI vs. AGI: The Cognitive Strengths and Weaknesses of Modern LLMs
Ben Goertzel
Generative AI AI System Artificial General Intelligence Cognitive Architecture Estimated Team Strength Cognitive System Physical Weakness Human Level Modern LLM

September 10, 2023

Machine Translation Models Stand Strong in the Face of Adversarial Attacks
Pavel Burnyshev, Elizaveta Kostenok, Alexey Zaytsev
Adversarial Attack Human Face Machine Translation Model Estimated Team Strength Gradient Based Attack Differentiable Framework Text Perturbation

August 22, 2023

Careful at Estimation and Bold at Exploration
Xing Chen, Yijun Liu, Zhaogeng Liu, Hechang Chen, Hengshuai Yao, Yi Chang
Policy Gradient Estimation Task Environment Exploration Action Space Estimated Team Strength Exploration Method

August 10, 2023

Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge
Jun Ma, Yao Zhang, Song Gu, Cheng Ge, Shihao Ma, Adamo Young, Cheng Zhu, Kangkang Meng, Xin Yang, Ziyan Huang, Fan Zhang, Wentao Liu, YuanKe Pan, Shoujin Huang, Jiacheng Wang, Mingze Sun, Weixin Xu, Dengqiang Jia, Jae Won Choi, Natália Alves, Bram de Wilde, Gregor Koehler, Yajun Wu, Manuel Wiesenfarth, Qiongjie Zhu, Guoqiang Dong, Jian He, the FLARE Challenge Consortium, Bo Wang
Artificial Intelligence Challenge Task Unlabeled Data Estimated Team Strength Abdominal Organ Segmentation Abdominal Multi Organ Segmentation

July 26, 2023

Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength
Tongya Zheng, Tianli Zhang, Qingzheng Guan, Wenjie Huang, Zunlei Feng, Mingli Song, Chun Chen
Graph Neural Network Estimated Team Strength Artefact PARTICLE Granular Material Molecular Fragment

July 20, 2023

Prediction of Handball Matches with Statistically Enhanced Learning via Estimated Team Strengths
Florian Felice, Christophe Ley
Machine Learning Model Human Prediction Estimated Team Strength Handball Match

July 18, 2023

BOLD: A Benchmark for Linked Data User Agents and a Simulation Framework for Dynamic Linked Data Environments
Tobias Käfer, Victor Charpenay, Andreas Harth
New Benchmark Estimated Team Strength Simulation Framework Smart Building Linked Data

June 28, 2023

Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs
Chenglu Sun, Shuo Shen, Sijia Xu, Weidong Zhang
Deep Reinforcement Learning Diversity Awareness Estimated Team Strength Advanced AI Google Research Football AI Competition Interactive Reinforcement Learning Artificial Intelligence Training

June 1, 2023

May 31, 2023

Large Language Models Are Not Strong Abstract Reasoners
Gaël Gendron, Qiming Bao, Michael Witbrock, Gillian Dobbie
Language Model Estimated Team Strength Abstract Reasoning LLM Generation Generalisation Ability

May 24, 2023

May 22, 2023

Finding the Pillars of Strength for Multi-Head Attention
Jinjie Ni, Rui Mao, Zonglin Yang, Han Lei, Erik Cambria
Self Supervised Human Attention Feature Selection Attention Head Estimated Team Strength Pillar Domain

Estimated Team Strength

Papers

CRAB: Assessing the Strength of Causal Relationships Between Real-world Events

Strong and Efficient Baselines for Open Domain Conversational Question Answering

Probing LLMs for hate speech detection: strengths and vulnerabilities

Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification

STRONG -- Structure Controllable Legal Opinion Summary Generation

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

Generative AI vs. AGI: The Cognitive Strengths and Weaknesses of Modern LLMs

Machine Translation Models Stand Strong in the Face of Adversarial Attacks

Careful at Estimation and Bold at Exploration

Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge

Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength

Prediction of Handball Matches with Statistically Enhanced Learning via Estimated Team Strengths

BOLD: A Benchmark for Linked Data User Agents and a Simulation Framework for Dynamic Linked Data Environments

Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs

Strengths and Weaknesses of 3D Pose Estimation and Inertial Motion Capture System for Movement Therapy

Differential Diffusion: Giving Each Pixel Its Strength

Large Language Models Are Not Strong Abstract Reasoners

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction

Finding the Pillars of Strength for Multi-Head Attention