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

December 21, 2024

Automated CVE Analysis: Harnessing Machine Learning In Designing Question-Answering Models For Cybersecurity Information Extraction
Tanjim Bin Faruk
Machine Learning Knowledge Graph Full Model Question Answering Product Design Domain Specific Threat Intelligence Security Context

December 20, 2024

The Only Way is Ethics: A Guide to Ethical Research with Large Language Models
Eddie L. Ungless, Nikolas Vitsakis, Zeerak Talat, James Garforth, Björn Ross, Arno Onken, Atoosa Kasirzadeh, Alexandra Birch
Natural Language Processing Full Model Large Language Practical Guide Intercultural Ethic Ethical Behavior Ethical Implication Research Ethic Ethical Discussion
BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models
Patrick Haller, Jonas Golde, Alan Akbik
Language Model Full Model Recurrent Neural Network Human Language Sample Efficient RNN Architecture RNN Based Model
Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference
Jorge García-Carrasco, Alejandro Maté, Juan Trujillo
Full Model Medical LLM Large Language Mechanistic Interpretability Fast Inference High Quality Subset Digital Circuit
From Model Based to Learned Regularization in Medical Image Registration: A Comprehensive Review
Anna Reithmeir, Veronika Spieker, Vasiliki Sideri-Lampretsa, Daniel Rueckert, Julia A. Schnabel, Veronika A. Zimmer
Full Model Medical Image Regularization Model Comprehensive Review Pre Registration Regularization Technique Supervised Regularization
Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models
Zhisheng Tang, Mayank Kejriwal
Full Model Path Breaking Emergence Human Like Large Language Cognitive Process Creative Task Emergent Structure Divergent Thinking
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du
Large Language Model Full Model Supervised Fine Tuning Large Scale Datasets Closed Source Large Language Model Tool Usage Feature Model Training Stage

December 19, 2024

Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations
Paolo Bova, Alessandro Di Stefano, The Anh Han
Full Model Improved Detection AI Capability Artificial Intelligence Policy Dangerous Capability
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
Reza Shirkavand, Peiran Yu, Shangqian Gao, Gowthami Somepalli, Tom Goldstein, Heng Huang
Diffusion Model Generative Model Knowledge Distillation Full Model Model Pruning Concept Removal Pruned Model
Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?
Mario Fritz
Full Model Cybersecurity Perspective Real World Deployment Chat Bot
ResoFilter: Rine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis
Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao, Tianyu Qi, Jun Liu, Ming Li
Large Language Model Fine Tuning Full Model Synthetic Data Large Language Data Augmentation Method Data Augmentation Technique Acoustic Resonance Pressure Filtration
ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
Shunlin Lu, Jingbo Wang, Zeyu Lu, Ling-Hao Chen, Wenxun Dai, Junting Dong, Zhiyang Dou, Bo Dai, Ruimao Zhang
Full Model Motion Generation Scaling Law Autoregressive Transformer Vq Vae Autoregressive Image Generation
Benign Overfitting in Out-of-Distribution Generalization of Linear Models
Shange Tang, Jiayun Wu, Jianqing Fan, Chi Jin
Full Model Distribution Generalization Ridge Regression Linear Ordered Data Benign Overfitting Parameterized Model
Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems
Genki Kusano, Kosuke Akimoto, Kunihiro Takeoka
Large Language Model Full Model Complex Prompt Recommendation System Large Language Recommendation Task Natural Language Input Recommendation Accuracy

December 18, 2024

A Unifying Information-theoretic Perspective on Evaluating Generative Models
Alexis Fox, Samarth Swarup, Abhijin Adiga
Full Model Information Theoretic Cross Entropy Anti Unification Agnostic Metric Generative Model Output Generative Evaluation
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
Yinlam Chow, Guy Tennenholtz, Izzeddin Gur, Vincent Zhuang, Bo Dai, Sridhar Thiagarajan, Craig Boutilier, Rishabh Agarwal, Aviral Kumar, Aleksandra Faust
Full Model Imitation Learning Large Language Inference Time Inference Task Inference Strategy Best of N
On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
Aditya Bhaskara, Agastya Vibhuti Jha, Michael Kapralov, Naren Sarayu Manoj, Davide Mazzali, Weronika Wrzos-Kaminska
Native Robustness Full Model Spectral Clustering Semidefinite Programming Stochastic Block Model Graph Partitioning Spectral Algorithm Spectral Filtering
The Multiplex Classification Framework: optimizing multi-label classifiers through problem transformation, ontology engineering, and model ensembling
Mauro Nievas Offidani, Facundo Roffet, Claudio Augusto Delrieux, Maria Carolina Gonzalez Galtier, Marcos Zarate
Machine Learning Full Model Supervised Learning Multi Label Classification Simple Classifier
jinns: a JAX Library for Physics-Informed Neural Networks
Hugo Gangloff, Nicolas Jouvin
Full Model Physic Informed Neural Network Optimization Process Trading Devil Flexible Framework JAX Primitive Open Source Python
Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model
Yuqiu Liu, Jingxuan Xu, Mauricio Soroco, Yunchao Wei, Wuyang Chen
Full Model Neural Field Efficient Inference Flow Field Dual Flow Perception Module SciML Model

Full Model

Papers

Automated CVE Analysis: Harnessing Machine Learning In Designing Question-Answering Models For Cybersecurity Information Extraction

The Only Way is Ethics: A Guide to Ethical Research with Large Language Models

BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference

From Model Based to Learned Regularization in Medical Image Registration: A Comprehensive Review

Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?

ResoFilter: Rine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

Benign Overfitting in Out-of-Distribution Generalization of Linear Models

Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems

A Unifying Information-theoretic Perspective on Evaluating Generative Models

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models

The Multiplex Classification Framework: optimizing multi-label classifiers through problem transformation, ontology engineering, and model ensembling

jinns: a JAX Library for Physics-Informed Neural Networks

Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model