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 19, 2024

ACING: Actor-Critic for Instruction Learning in Black-Box Large Language Models
Salma Kharrat, Fares Fourati, Marco Canini
Full Model Large Language Actor Critic High Performance Task Instruction Instruction Learning Continuum Armed Bandit
CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
Ye Liu, Rui Meng, Shafiq Jot, Silvio Savarese, Caiming Xiong, Yingbo Zhou, Semih Yavuz
Full Model Retrieval Benchmark Programming Task Text Retrieval Multilingual Text Generalist Learner Chinese CodEx Code Retrieval
DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
Vinay Kumar Sankarapu, Chintan Chitroda, Yashwardhan Rathore, Neeraj Kumar Singh, Pratinav Seth
Deep Learning Full Model Inherent Interpretability Interpretability Method Model Agnostic Explanation Model Transparency Built in Interpretability
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwarak Talupuru, Acyr Locatelli, Robert Kirk, Tim Rocktäschel, Edward Grefenstette, Max Bartolo
Strong Generalization Full Model Reasoning Task Large Language Procedural Knowledge Reasoning Gap
Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models
Jun Xiao, Zihang Lyu, Hao Xie, Cong Zhang, Yakun Ju, Changjian Shui, Kin-Man Lam
Full Model Diffusion Explainer Video Deblurring Blind Image Restoration
CoMeDi Shared Task: Models as Annotators in Lexical Semantics Disagreements
Zhu Liu, Zhen Hu, Ying Liu
Language Model Full Model Shared Task Individual Annotator Opinion Disagreement Similarity Score Lexical Semantics Disagreement Analysis Framework

November 16, 2024

ML$^2$Tuner: Efficient Code Tuning via Multi-Level Machine Learning Models
JooHyoung Cha, Munyoung Lee, Jinse Kwon, Jubin Lee, Jemin Lee, Yongin Kwon
Deep Learning Deep Learning Model Full Model

November 14, 2024

DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines
Junqi Liu, Yun Zhang, Xiaoqi Wang, Xu Long, Sam Kwong
Full Model Deep Transformer Video Coding Detection Loss Noticeable Difference
Enhancing Financial Domain Adaptation of Language Models via Model Augmentation
Kota Tanabe, Masanori Hirano, Kazuki Matoya, Kentaro Imajo, Hiroki Sakaji, Itsuki Noda
Large Language Model Language Model Domain Adaptation Full Model Soft Augmentation Financial Domain Financial Dataset

November 13, 2024

Model agnostic local variable importance for locally dependent relationships
Kelvyn K. Bladen, Adele Cutler, D. Richard Cutler, Kevin R. Moon
Full Model Human Relationship Model Agnostic Multi Class Classification Variable Importance
Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data
Anum Afzal, Juraj Vladika, Gentrit Fazlija, Andrei Staradubets, Florian Matthes
Full Model Retrieval Augmented Generation Domain Specific Retrieval Augmented Open Domain Large Language Confusion Matrix

November 12, 2024

Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach
Jiyao Li, Mingze Ni, Yongshun Gong, Wei Liu
Adversarial Attack Full Model Constructive Approach QuEry Based Attack Word Level Adversarial
PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
Yilun Liu, Yunpu Ma, Shuo Chen, Zifeng Ding, Bailan He, Zhen Han, Volker Tresp
Fine Tuning Full Model Parameter Efficient Fine Tuning Mixture of Expert Compositional Approach Scalable Solution
LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models
Anoop Cherian, Radu Corcodel, Siddarth Jain, Diego Romeres
Zero Shot Full Model World Event Physical Reasoning

Full Model

Papers

ACING: Actor-Critic for Instruction Learning in Black-Box Large Language Models

CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models

CoMeDi Shared Task: Models as Annotators in Lexical Semantics Disagreements

Benchmarking pre-trained text embedding models in aligning built asset information

CNMBert: A Model For Hanyu Pinyin Abbreviation to Character Conversion Task

Re-examining learning linear functions in context

ML$^2$Tuner: Efficient Code Tuning via Multi-Level Machine Learning Models

MARS: Unleashing the Power of Variance Reduction for Training Large Models

OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Models

Explanation for Trajectory Planning using Multi-modal Large Language Model for Autonomous Driving

DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines

Enhancing Financial Domain Adaptation of Language Models via Model Augmentation

Model agnostic local variable importance for locally dependent relationships

Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data

Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach

PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model

LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models