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

November 8, 2024

NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts
Yen-Ting Lin, Chao-Han Huck Yang, Zhehuai Chen, Piotr Zelasko, Xuesong Yang, Zih-Ching Chen, Krishna C Puvvada, Szu-Wei Fu, Ke Hu, Jun Wei Chiu, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank Wang
Language Model Full Model Mixture of Expert Speech to Text Multi Task Optimization Post OCR Task Expert
The effect of different feature selection methods on models created with XGBoost
Jorge Neyra, Vishal B. Siramshetty, Huthaifa I. Ashqar
Training Data Full Model Mixed Effect Feature Selection Data Dimensionality Prediction Accuracy XGBoost Model
LLMs as Method Actors: A Model for Prompt Engineering and Architecture
Colin Doyle
Full Model Medical LLM Prompt Engineering Complex Reasoning Task Architecture Design Mental Model LLM Prompt Actor Loss
HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysis
Saedeh Tahery, Fatemeh Hamid Akhlaghi, Termeh Amirsoleimani, Saeed Farzi, Carlo Strapparava
Full Model High Efficiency Biomedical Signal Bidirectional Encoders Electrocardiogram Dataset

November 7, 2024

SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, Song Han
Full Model Diffusion Explainer Connected Component Model Re Quantization
Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models
Shuhong Zheng, Zhipeng Bao, Ruoyu Zhao, Martial Hebert, Yu-Xiong Wang
Full Model Diffusion Explainer Denoising Diffusion Discriminative Task Diffusion Based Framework Dense Vision Task Generative Bridging Domain
DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models
Zijian Zhang, Vinay Setty, Yumeng Wang, Avishek Anand
Full Model Text Classification Neural Language Model Model Overfitting Interpretability Method Interactive Explanation Instance Based Explanation Causal Assumption Causal News Corpus
TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models
Jonathan Fhima, Elad Ben Avraham, Oren Nuriel, Yair Kittenplon, Roy Ganz, Aviad Aberdam, Ron Litman
Full Model Vision Language Optical Character Recognition Layout Generation
One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity
Sonia K. Murthy, Tomer Ullman, Jennifer Hu
Large Language Model Full Model Human Language Alignment Problem Population Level Population Diversity Conceptual Diversity
Repairing Neural Networks for Safety in Robotic Systems using Predictive Models
Keyvan Majd, Geoffrey Clark, Georgios Fainekos, Heni Ben Amor
Neural Network Full Model Robot Person Mobile Robot Robotic System Robot Learning Human SAFETY DNN Repair Robot Safety
Model and Deep learning based Dynamic Range Compression Inversion
Haoran Sun, Dominique Fourer, Hichem Maaref
Deep Learning Full Model Model Inversion Dynamic Range

November 6, 2024

Are Deep Learning Methods Suitable for Downscaling Global Climate Projections? Review and Intercomparison of Existing Models
Jose González-Abad, José Manuel Gutiérrez
Deep Learning Full Model Projection Bias Systematic Comparison Climate Downscaling Extrapolation Capability Regional Climate
Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks
Ryan Campbell, Nelson Lojo, Kesava Viswanadha, Christoffer Grondal Tryggestad, Derrick Han Sun, Sriteja Vijapurapu, August Rolfsen, Anant Sahai
Full Model Context Learning Efficient Hybrid Different Context Sequence Model Efficient Architecture Task Learning
A Novel Access Control and Privacy-Enhancing Approach for Models in Edge Computing
Peihao Li
Full Model Extreme Edge Watermarking Method Digital Computing Privacy Enhancing Technology Edge Model Access Control Model Ownership Verification
Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
Yuhao He, Jinyu Tian, Xianwei Zheng, Li Dong, Yuanman Li, Jiantao Zhou
Full Model Poisoning Attack Evasion Attack Singularity Free
Zero-shot Dynamic MRI Reconstruction with Global-to-local Diffusion Model
Yu Guan, Kunlong Zhang, Qi Qi, Dong Wang, Ziwen Ke, Shaoyu Wang, Dong Liang, Qiegen Liu
Diffusion Model Full Model Field Data Dynamic Magnetic Resonance Imaging

November 5, 2024

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models
Ying Zhou, Xinyao Wang, Yulei Niu, Yaojie Shen, Lexin Tang, Fan Chen, Ben He, Le Sun, Longyin Wen
Large Language Model Full Model Variational Autoencoder Latent Representation Synthetic Data Generation Latent Variable
Advancing Recycling Efficiency: A Comparative Analysis of Deep Learning Models in Waste Classification
Zhanshan Qiao
Deep Learning Full Model Comparative Study Support Vector Machine Advanced Textile Recycling Efficient Waste
Label Critic: Design Data Before Models
Pedro R. A. S. Bassi, Qilong Wu, Wenxuan Li, Sergio Decherchi, Andrea Cavalli, Alan Yuille, Zongwei Zhou
Full Model Pseudo Label Full Label Annotation Task

November 4, 2024

Multi-Transmotion: Pre-trained Model for Human Motion Prediction
Yang Gao, Po-Chien Luan, Alexandre Alahi
Full Model Cross Modal Trajectory Prediction Motion Prediction Human Motion Prediction Pose Prediction

Full Model

Papers

NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts

The effect of different feature selection methods on models created with XGBoost

LLMs as Method Actors: A Model for Prompt Engineering and Architecture

HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysis

SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models

DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models

TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models

One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

Repairing Neural Networks for Safety in Robotic Systems using Predictive Models

Model and Deep learning based Dynamic Range Compression Inversion

Are Deep Learning Methods Suitable for Downscaling Global Climate Projections? Review and Intercomparison of Existing Models

Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks

A Novel Access Control and Privacy-Enhancing Approach for Models in Edge Computing

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization

Zero-shot Dynamic MRI Reconstruction with Global-to-local Diffusion Model

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models

Advancing Recycling Efficiency: A Comparative Analysis of Deep Learning Models in Waste Classification

Label Critic: Design Data Before Models

Multi-Transmotion: Pre-trained Model for Human Motion Prediction