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 14, 2024

Model-Based Differentially Private Knowledge Transfer for Large Language Models
Zhaomin Wu, Jizhou Guo, Junyi Hou, Bingsheng He, Lixin Fan, Qiang Yang
Large Language Model Full Model Domain Knowledge Large Language Domain Specific Task Domain Specific Model
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu, Chao Cui, Vasant G Honavar
Language Model Full Model Alignment Problem Large Language Efficient Fine Tuning Demonstration Data Conditioned Imitation

October 13, 2024

Self-Data Distillation for Recovering Quality in Pruned Large Language Models
Vithursan Thangarasa, Ganesh Venkatesh, Nish Sinnadurai, Sean Lie
Large Language Model Full Model Quality Issue Structured Pruning Shot Pruning
Dynamic Estimation of Learning Rates Using a Non-Linear Autoregressive Model
Ramin Okhrati
Full Model Learning Rate Non Autoregressive Online Estimation Large Learning Rate
EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models
Eungbean Lee, Somi Jeong, Kwanghoon Sohn
Full Model Image Translation Exemplar Image Data Driven Decision Exemplar Based Brownian Bridge
AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model
Yuchen Li, Li Zhang, Youwei Liang, Pengtao Xie
Semantic Segmentation Fine Tuning Full Model Segment Anything Model Segmentation Task Accurate Segmentation Segment Anything Interactive Prompting Body Segmentation
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
Chengshuai Shi, Kun Yang, Jing Yang, Cong Shen
Reinforcement Learning Transformer Megatron Decepticons Full Model Context Learning Multi Agent Capability Evolution Game Playing Agent

October 12, 2024

Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting
Chunlin Tian, Li Li, Kahou Tam, Yebo Wu, Chengzhong Xu
Full Model Heterogeneous Federated Learning Split and Fit
ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
Hongbin Xu, Weitao Chen, Zhipeng Zhou, Feng Xiao, Baigui Sun, Mike Zheng Shou, Wenxiong Kang
Full Model 3D Generation 3D Content Generation Large Reconstruction Model Large Scale Reconstruction
Exploring Channel Distinguishability in Local Neighborhoods of the Model Space in Quantum Neural Networks
Sabrina Herbst, Sandeep Suresh Cranganore, Vincenzo De Maio, Ivona Brandic
Full Model Quantum Machine Learning Deep Space Quantum Neural Network Neighborhood Level Quantum Model Variational Ansatz
Reinforcement Learning in Hyperbolic Spaces: Models and Experiments
Vladimir Jaćimović, Zinaid Kapić, Aladin Crnkić
Reinforcement Learning Full Model Action Space Optical Experiment Black Box Optimization Unknown Environment Hyperbolic Space Dynamical Model
Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models
Raghav Singhal, Kaustubh Ponkshe, Praneeth Vepakomma
Fine Tuning Full Model Federated Prompt Cooperation Flawed Foundation Efficient Fine Tuning Numerical Aggregation
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Yige Yuan, Bingbing Xu, Teng Xiao, Liang Hou, Fei Sun, Huawei Shen, Xueqi Cheng
Full Model Raw Data Test Time Adaptation Stronger Generalizability Time Adaptation
Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models
Sathya Kamesh Bhethanabhotla, Omar Swelam, Julien Siems, David Salinas, Frank Hutter
Zero Shot Full Model Time Series Forecasting State Space Forecast Utterance Auto Regressive Zero Shot Model Progressive Fusion Mamba
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
Wenlong Deng, Yize Zhao, Vala Vakilian, Minghui Chen, Xiaoxiao Li, Christos Thrampoulidis
Full Model Fine Tuned Model Encoder Model Extreme Value Parameter Pruning
\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments
Debanjan Ghosh, Sophia Chan
Full Model Direct Assessment Instruction Datasets Language Proficiency

October 11, 2024

EasyHeC++: Fully Automatic Hand-Eye Calibration with Pretrained Image Models
Zhengdong Hong, Kangfu Zheng, Linghao Chen
Full Model Calibration Performance Robot Arm Hand Eye Calibration Arm Movement Pre Trained Classifier
The Impact of Visual Information in Chinese Characters: Evaluating Large Models' Ability to Recognize and Utilize Radicals
Xiaofeng Wu, Karl Stratos, Wei Xu
Full Model Chinese Character Critique Ability Multilingual Glyph Text Character Grouping
Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks
Isha Gupta, Hidde Lycklama, Emanuel Opel, Evan Rose, Anwar Hithnawi
Full Model Poisoning Attack Data Poisoning Attack Model Complexity Vulnerable Population Target Population Mini Giant
Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models
Pascl Zwick, Kevin Roesch, Marvin Klemp, Oliver Bringmann
Full Model Text to Image Diffusion Model Text to Image Diffusion Consistent Anonymization Effect Face Anonymization Full Body Anonymization

Full Model

Papers

Model-Based Differentially Private Knowledge Transfer for Large Language Models

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

Self-Data Distillation for Recovering Quality in Pruned Large Language Models

Dynamic Estimation of Learning Rates Using a Non-Linear Autoregressive Model

EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models

AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model

Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models

Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting

ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model

Exploring Channel Distinguishability in Local Neighborhoods of the Model Space in Quantum Neural Networks

Reinforcement Learning in Hyperbolic Spaces: Models and Experiments

Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models

MITA: Bridging the Gap between Model and Data for Test-time Adaptation

Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments

EasyHeC++: Fully Automatic Hand-Eye Calibration with Pretrained Image Models

The Impact of Visual Information in Chinese Characters: Evaluating Large Models' Ability to Recognize and Utilize Radicals

Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks

Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models