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 5, 2024

MegaCOIN: Enhancing Medium-Grained Color Perception for Vision-Language Models
Ming-Chang Chiu, Shicheng Wen, Pin-Yu Chen, Xuezhe Ma
Vision Language Model Full Model Multimodal Phenomenon Human Annotation Visual Task Human Labeled Bitcoin User Color Perception

December 4, 2024

A Contemporary Overview: Trends and Applications of Large Language Models on Mobile Devices
Lianjun Liu, Hongli An, Pengxuan Chen, Longxiang Ye
Full Model Financial Application Low Latency Recent Trend Large Language Mobile Device AI Application Mobile AI LLM Capability
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
Ao Wang, Hui Chen, Jianchao Tan, Kefeng Zhang, Xunliang Cai, Zijia Lin, Jungong Han, Guiguang Ding
Full Model Large Vision Language Model Vision Paper Key Value Cache KV Cache Key Value Efficient Generation
RedStone: Curating General, Code, Math, and QA Data for Large Language Models
Yaoyao Chang, Lei Cui, Li Dong, Shaohan Huang, Yangyu Huang, Yupan Huang, Scarlett Li, Tengchao Lv, Shuming Ma, Qinzheng Sun, Wenhui Wang, Furu Wei, Ying Xin, Mao Yang, Qiufeng Yin, Xingxing Zhang
Full Model Language Understanding Domain Specific Pre Training Real World Code Large Language Domain Expertise
EchoONE: Segmenting Multiple echocardiography Planes in One Model
Jiongtong Hu, Wei Zhuo, Jun Cheng, Yingying Liu, Wufeng Xue, Dong Ni
Full Model Multi View Mask Guided Segmentation Foundation Model Echocardiography Dataset

December 3, 2024

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
Hieu Tran, Zonghai Yao, Junda Wang, Yifan Zhang, Zhichao Yang, Hong Yu
Full Model Information Retrieval Large Language Reasoning System Knowledge Intensive Task
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
Zongru Wu, Pengzhou Cheng, Lingyong Fang, Zhuosheng Zhang, Gongshen Liu
Full Model Backdoor Attack Backdoor Defense Generative LLM Retraining Method Backdoor Sample
AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation
Jaehyun Choi, Junwon Ko, Dong-Jae Lee, Junmo Kim
Domain Adaptation Full Model Curriculum Learning Unseen Domain Hopfield Network Open Set Domain Adaptation
LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models
Fan-Yun Sun, Weiyu Liu, Siyi Gu, Dylan Lim, Goutam Bhat, Federico Tombari, Manling Li, Nick Haber, Jiajun Wu
Full Model Differentiable Optimization 3D Layout Layout Representation

December 2, 2024

Recurrent Neural Network on PICTURE Model
Weihan Xu
Full Model Recurrent Neural Network Intensive Care Unit Intensive Care
Mastering Board Games by External and Internal Planning with Language Models
John Schultz, Jakub Adamek, Matej Jusup, Marc Lanctot, Michael Kaisers, Sarah Perrin, Daniel Hennes, Jeremy Shar, Cannada Lewis, Anian Ruoss, Tom Zahavy, Petar Veličković, Laurel Prince, Satinder Singh, Eric Malmi, Nenad Tomašev
Large Language Model Language Model Full Model Human Language Monte Carlo Tree Search Board Game Language Model Inference Search Based Planning
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger, Prithviraj Singh Shahani, Fedor Ryzhenkov, Jacob Haimes, Felix Hofstätter, Teun van der Weij
Full Model Gaussian Noise Unsupervised Method Hidden Knowledge Noise Injection Stable Bagging Sandbox Environment Frontier AI
DiffPatch: Generating Customizable Adversarial Patches using Diffusion Model
Zhixiang Wang, Guangnan Ye, Xiaosen Wang, Siheng Chen, Zhibo Wang, Xingjun Ma, Yu-Gang Jiang
Full Model Diffusion Explainer Adversarial Patch Patch Generation Physical Adversarial Patch Adversarial Patch Generation
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration
Hao Li, Xiang Chen, Jiangxin Dong, Jinhui Tang, Jinshan Pan
Full Model Image Restoration Image Pair Flawed Foundation Universal Image Degradation Representation Training Datasets
MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models
Xiaomin Li, Xu Jia, Qinghe Wang, Haiwen Diao, Mengmeng Ge, Pengxiang Li, You He, Huchuan Lu
Full Model Multimodal Large Language Model Video Generation Text to Video Multimodal Representation Motion Transfer Text to Video Diffusion Model
MFTF: Mask-free Training-free Object Level Layout Control Diffusion Model
Shan Yang
Fine Grained Full Model Text to Image Generation Mask Guided Image Editing Model

December 1, 2024

EventGPT: Event Stream Understanding with Multimodal Large Language Models
Shaoyu Liu, Jianing Li, Guanghui Zhao, Yunjian Zhang, Xin Meng, Fei Richard Yu, Xiangyang Ji, Ming Li
Language Model Full Model Multimodal Large Language Model Event Stream
Enhancing the Generalization Capability of Skin Lesion Classification Models with Active Domain Adaptation Methods
Jun Ye
Domain Adaptation Full Model Skin Lesion
LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models
Muhammad Fetrat Qharabagh, Mohammadreza Ghofrani, Kimon Fountoulakis
Full Model Visual Perception Automatic Counting Object Counting Large Vision Language Based Counting
Multi-Agent Collaboration in Incident Response with Large Language Models
Zefang Liu
Full Model Large Language Intelligent Agent Cybersecurity Perspective Multi Agent Collaboration Agent Interaction Incident Management

Full Model

Papers

MegaCOIN: Enhancing Medium-Grained Color Perception for Vision-Language Models

A Contemporary Overview: Trends and Applications of Large Language Models on Mobile Devices

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

RedStone: Curating General, Code, Math, and QA Data for Large Language Models

EchoONE: Segmenting Multiple echocardiography Planes in One Model

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining

AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation

LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models

Recurrent Neural Network on PICTURE Model

Mastering Board Games by External and Internal Planning with Language Models

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models

DiffPatch: Generating Customizable Adversarial Patches using Diffusion Model

FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models

MFTF: Mask-free Training-free Object Level Layout Control Diffusion Model

EventGPT: Event Stream Understanding with Multimodal Large Language Models

Enhancing the Generalization Capability of Skin Lesion Classification Models with Active Domain Adaptation Methods

LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models

Multi-Agent Collaboration in Incident Response with Large Language Models