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 18, 2024

Graph-Driven Models for Gas Mixture Identification and Concentration Estimation on Heterogeneous Sensor Array Signals
Ding Wang, Lei Wang, Huilin Yin, Guoqing Gu, Zhiping Lin, Wenwen Zhang
Full Model Estimation Task Selective Focus Heterogeneous Sensor Sensor Array Gas Recognition Spore Concentration
A Survey on Inference Optimization Techniques for Mixture of Experts Models
Jiacheng Liu, Peng Tang, Wenfeng Wang, Yuhang Ren, Xiaofeng Hou, Pheng-Ann Heng, Minyi Guo, Chao Li
Timely Survey Full Model Mixture Component Expert Knowledge Mixture of Expert Input Mixture Merging Expert Efficient Expert
Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA
Lifeng Qiao, Peng Ye, Yuchen Ren, Weiqiang Bai, Chaoqi Liang, Xinzhu Ma, Nanqing Dong, Wanli Ouyang
Full Model Gene Representation
Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
Kunat Pipatanakul, Potsawee Manakul, Natapong Nitarach, Warit Sirichotedumrong, Surapon Nonesung, Teetouch Jaknamon, Parinthapat Pengpun, Pittawat Taveekitworachai, Adisai Na-Thalang, Sittipong Sripaisarnmongkol, Krisanapong Jirayoot, Kasima Tharnpipitchai
Language Model Full Model Single Parent Family Tropical Cyclone Textual Model Thai Language
Towards Efficient and Explainable Hate Speech Detection via Model Distillation
Paloma Piot, Javier Parapar
Language Model Full Model Hate Speech Hate Speech Detection Mutual Distillation Large Language Abusive Language
Self-control: A Better Conditional Mechanism for Masked Autoregressive Model
Qiaoying Qu, Shiyu Shen
Full Model Conditional Reasoning Autoregressive Generative Model Autoregressive Sequence Autoregressive Image Generation Self Restraint
Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
Xiu Yuan, Tongzhou Mu, Stone Tao, Yunhao Fang, Mengke Zhang, Hao Su
Full Model Robot Learning Policy Design Offline Policy Residual Reinforcement Learning Programmatic Policy
Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models
Xinxin Liu, Aaron Thomas, Cheng Zhang, Jianyi Cheng, Yiren Zhao, Xitong Gao
Fine Tuning Full Model Human Language Parameter Efficient Fine Tuning Sparse Update Salience Allocation
AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models
Tommy Nguyen, Mehmet Ergezer, Christian Green
Adversarial Attack Neural Radiance Field Full Model Positive Reinforcement Adversarial Noise

December 17, 2024

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
Keltin Grimes, Marco Christiani, David Shriver, Marissa Connor
Full Model Human Editing High Impact Concept Model Editing High Level Trojan Attack
Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality
Qitong Wang, Tang Li, Kien X. Nguyen, Xi Peng
Vision Language Model Fine Tuning Full Model Mixed Effect Exact Inference
CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models
Gaoyang Zhang, Bingtao Fu, Qingnan Fan, Qi Zhang, Runxing Liu, Hong Gu, Huaqi Zhang, Xinguo Liu
Full Model Text to Image Diffusion Model Text to Image Diffusion Spatial Relation Spatial Understanding Spatial Prior
StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
Yunzhi Yan, Zhen Xu, Haotong Lin, Haian Jin, Haoyu Guo, Yida Wang, Kun Zhan, Xianpeng Lang, Hujun Bao, Xiaowei Zhou, Sida Peng
Full Model Novel View Synthesis LiDAR Point Cloud View Synthesis Street View LiDAR Measurement
A Conformal Approach to Feature-based Newsvendor under Model Misspecification
Junyu Cao
Full Model Model Bias Real World Dataset Model Misspecification Data Driven Decision Distribution Free Conformal Method Newsvendor Problem Addressing Misspecification
Modality-Inconsistent Continual Learning of Multimodal Large Language Models
Weiguo Pian, Shijian Deng, Shentong Mo, Yunhui Guo, Yapeng Tian
Full Model Multimodal Large Language Model State of the Art Continual Continual Learning Scenario Modality Discrepancy
SnakModel: Lessons Learned from Training an Open Danish Large Language Model
Mike Zhang, Max Müller-Eberstein, Elisa Bassignana, Rob van der Goot
Language Model Natural Language Processing Full Model Critical Lesson Pre Training Corpus
PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model
Yuqing Wang, Zhongling Huang, Shuxin Yang, Hao Tang, Xiaolan Qiu, Junwei Han, Dingwen Zhang
Full Model Synthetic Aperture Radar Spectro Polarimetric Polarimetric Cue
LLMs are Also Effective Embedding Models: An In-depth Overview
Chongyang Tao, Tao Shen, Shen Gao, Junshuo Zhang, Zhen Li, Zhengwei Tao, Shuai Ma
Large Language Model Natural Language Processing Full Model Jina Embeddings Sparse Embeddings
ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
Romain Hardy, Sung Eun Kim, Pranav Rajpurkar
Full Model Hallucination Detection Radiology Report Medical AI Medical Information Mart for Intensive Fine Grained Hallucination
Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks
Xunkai Li, Zhengyu Wu, Jiayi Wu, Hanwen Cui, Jishuo Jia, Rong-Hua Li, Guoren Wang
Graph Neural Network Full Model Medical LLM Raw Data Graph Learning New Task Graph Model Graph Level Task

Full Model

Papers

Graph-Driven Models for Gas Mixture Identification and Concentration Estimation on Heterogeneous Sensor Array Signals

A Survey on Inference Optimization Techniques for Mixture of Experts Models

Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA

Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

Towards Efficient and Explainable Hate Speech Detection via Model Distillation

Self-control: A Better Conditional Mechanism for Masked Autoregressive Model

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models

AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality

CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models

StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models

A Conformal Approach to Feature-based Newsvendor under Model Misspecification

Modality-Inconsistent Continual Learning of Multimodal Large Language Models

SnakModel: Lessons Learned from Training an Open Danish Large Language Model

PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model

LLMs are Also Effective Embedding Models: An In-depth Overview

ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports

Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks