Full Model

"Full Model" research encompasses the development and improvement of large-scale machine learning models across diverse applications, aiming to enhance performance, efficiency, and robustness. Current research focuses on addressing model vulnerabilities (e.g., adversarial attacks, hallucinations), improving efficiency for resource-constrained devices, and developing specialized models for specific domains (e.g., finance, astronomy, medical imaging). This work is significant for advancing AI capabilities in various fields and for mitigating potential risks associated with deploying complex models in real-world settings.

Papers

October 16, 2024

Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
Ce Zhang, Simon Stepputtis, Katia Sycara, Yaqi Xie
Vision Language Model Full Model Test Time Adaptation Multi Modal Representation Test Time Domain Adaptation
Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
Luis Barroso-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, C. Lawrence Zitnick, Zachary W. Ulissi
Full Model Material Discovery Material Design Material Data
Evaluating Morphological Compositional Generalization in Large Language Models
Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Lonneke van der Plas, Duygu Ataman
Large Language Model Full Model Large Language Linguistic Generalization
Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models
Amin Abolghasemi, Leif Azzopardi, Seyyed Hadi Hashemi, Maarten de Rijke, Suzan Verberne
Large Language Model Full Model Global Evaluation Implicit Bias Document Intelligence Human Writer Attribution Quality
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
Qinfeng Li, Yangfan Xie, Tianyu Du, Zhiqiang Shen, Zhenghan Qin, Hao Peng, Xinkui Zhao, Xianwei Zhu, Jianwei Yin, Xuhong Zhang
Large Language Model Full Model Capability Evolution Edge Deployment Model Protection Proprietary Large Language Model
Incorporating Long-term Data in Training Short-term Traffic Prediction Model
Xiannan Huang, Shuhan Qiu, Yan Cheng, Quan Yuan, Chao Yang
Training Data Full Model Long Term Traffic Prediction Short Term Traffic Traffic State Sequence

October 15, 2024

DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
Shangqian Gao, Chi-Heng Lin, Ting Hua, Tang Zheng, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
Full Model Large Language Structural Pruning
MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
Pei Wang, Yanan Wu, Zekun Wang, Jiaheng Liu, Xiaoshuai Song, Zhongyuan Peng, Ken Deng, Chenchen Zhang, Jiakai Wang, Junran Peng, Ge Zhang, Hangyu Guo, Zhaoxiang Zhang, Wenbo Su, Bo Zheng
Full Model Benchmark Dataset Large Language Multi Granularity Instruction Dataset ML Agent Bench
Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models
María Victoria Carro, Francisca Gauna Selasco, Denise Alejandra Mester, Mario Alejandro Leiva
Full Model Causal Pattern Large Language Cognitive Bias Optical Illusion
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
Fan Yang, Yihao Huang, Kailong Wang, Ling Shi, Geguang Pu, Yang Liu, Haoyu Wang
Adversarial Attack Full Model Vision Language Adversarial Perturbation Universal Adversarial Multimodal Loss
A model learning framework for inferring the dynamics of transmission rate depending on exogenous variables for epidemic forecasts
Giovanni Ziarelli, Stefano Pagani, Nicola Parolini, Francesco Regazzoni, Marco Verani
Full Model Data Assimilation Epidemic Forecasting Transmission Data Exogenous Variable
Data Quality Control in Federated Instruction-tuning of Large Language Models
Yaxin Du, Rui Ye, Fengting Yuchi, Wanru Zhao, Jingjing Qu, Yanfeng Wang, Siheng Chen
Full Model Instruction Tuning Large Language Data Quality Federated Instruction Tuning Hierarchical Training
Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari
Large Language Model Full Model Jailbreak Attack Large Language Attack Success Rate Jigsaw Puzzle Malicious Query
Tending Towards Stability: Convergence Challenges in Small Language Models
Richard Diehl Martinez, Pietro Lesci, Paula Buttery
Language Model Full Model Low Resource Language Core Stability Training Dynamic Smaller Language Model Representational Capacity Convergence Performance

October 14, 2024

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning
Bokai Hu, Sai Ashish Somayajula, Xin Pan, Zihan Huang, Pengtao Xie
Large Language Model Reinforcement Learning Full Model Natural Language Language Generation Large Language NLU Model BERT Large
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
Ziyue Li, Tianyi Zhou
Large Language Model Full Model Mixture of Expert Representation Finetuning Task Specific Embeddings
Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning
Kuofeng Gao, Huanqia Cai, Qingyao Shuai, Dihong Gong, Zhifeng Li
Full Model Mathematical Reasoning Large Language Critique Ability Self Correction
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Junyu Chen, Han Cai, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Yao Lu, Song Han
Full Model Supervised Autoencoder Variational Autoencoder Autoencoder Based
TRESTLE: A Model of Concept Formation in Structured Domains
Christopher J. MacLellan, Erik Harpstead, Vincent Aleven, Kenneth R. Koedinger
Full Model Hierarchical Classification Human Learning Classification Tree Concept Formation Classification Paradigm Structured Domain
Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
Jiaxiang Gou, Luping Ji, Pei Liu, Mao Ye
Full Model Loss Function Vision Language Multiple Instance Learning Whole Slide Image Instance Level

Full Model

Papers

Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models

Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models

Evaluating Morphological Compositional Generalization in Large Language Models

Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Incorporating Long-term Data in Training Short-term Traffic Prediction Model

DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models

MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models

Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models

A model learning framework for inferring the dynamics of transmission rate depending on exogenous variables for epidemic forecasts

Data Quality Control in Federated Instruction-tuning of Large Language Models

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

Tending Towards Stability: Convergence Challenges in Small Language Models

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

TRESTLE: A Model of Concept Formation in Structured Domains

Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification