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 13, 2024

Learning Structural Causal Models from Ordering: Identifiable Flow Models
Minh Khoa Le, Kien Do, Truyen Tran
Full Model Causal Inference Causal Graph Structural Causal Model Order Matter Structural Causal
FDM-Bench: A Comprehensive Benchmark for Evaluating Large Language Models in Additive Manufacturing Tasks
Ahmadreza Eslaminia, Adrian Jackson, Beitong Tian, Avi Stern, Hallie Gordon, Rajiv Malhotra, Klara Nahrstedt, Chenhui Shao
Full Model Large Language Comprehensive Benchmark Open Source Model 3D Printing
Is it the model or the metric -- On robustness measures of deeplearning models
Zhijin Lyu, Yutong Jin, Sneha Das
Native Robustness Deep Learning Model Full Model Deepfake Detection
Activation Sparsity Opportunities for Compressing General Large Language Models
Nobel Dhar, Bobin Deng, Md Romyull Islam, Kazi Fahim Ahmad Nasif, Liang Zhao, Kun Suo
Full Model Edge Device AI Model Local Model Activation Sparsity

December 12, 2024

Agtech Framework for Cranberry-Ripening Analysis Using Vision Foundation Models
Faith Johnson, Ryan Meegan, Jack Lowry, Peter Oudemans, Kristin Dana
Computer Vision Full Model General Analysis Vision Foundation Model Crop Breeding Aerial Photography Berry Picking Agricultural Machinery
V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
Junqi Ge, Ziyi Chen, Jintao Lin, Jinguo Zhu, Xihui Liu, Jifeng Dai, Xizhou Zhu
Vision Language Model Full Model Multimodal Context Multimodal Sequence
Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Clinical Pathology Analysis
Shengxuming Zhang, Weihan Li, Tianhong Gao, Jiacong Hu, Haoming Luo, Mingli Song, Xiuming Zhang, Zunlei Feng
Full Model High Efficiency Feature Extraction Pathology Data
Shiksha: A Technical Domain focused Translation Dataset and Model for Indian Languages
Advait Joglekar, Srinivasan Umesh
Full Model Neural Machine Translation Technical Report Indian Language Parallel Corpus Translation Model Translation Datasets

December 11, 2024

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models
Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, Tomer Michaeli
Full Model Pre Trained Stable Diffusion Human Editing Flow Based Pre Trained Text to Image Inversion Method
Novel 3D Binary Indexed Tree for Volume Computation of 3D Reconstructed Models from Volumetric Data
Quoc-Bao Nguyen-Le, Tuan-Hy Le, Anh-Triet Do
Full Model 3D Reconstruction Automatic Volume Reconstruction Algorithm Volumetric Data Mesh Generation 3D Volume
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Yuxi Li, Zhibo Zhang, Kailong Wang, Ling Shi, Haoyu Wang
Full Model Jailbreak Attack Safety Alignment Target Model
DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models
Kevin Miao, Harsh Agrawal, Qihang Zhang, Federico Semeraro, Marco Cavallo, Jiatao Gu, Alexander Toshev
Full Model 3D Reconstruction 3D Generation 3D Asset Multi View Diffusion 3D Prior
Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
Hee-Seon Kim, Minbeom Kim, Changick Kim
Adversarial Attack Full Model Text Modality Large Vision Language Model Vision Language Task State Perturbation

December 10, 2024

Distributed Gradient Descent with Many Local Steps in Overparameterized Models
Heng Zhu, Harsh Vardhan, Arya Mazumdar
Full Model Gradient Descent Federated Averaging Model Convergence Local Gradient Local SGD
How to Choose a Threshold for an Evaluation Metric for Large Language Models
Bhaskarjit Sarmah, Mingshu Li, Jingrao Lyu, Sebastian Frank, Nathalia Castellanos, Stefano Pasquali, Dhagash Mehta
Large Language Model Full Model Evaluation Metric Large Language Risk Assessment Canonical Threshold Faithfulness Metric LLM Based Metric
RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models
Greg Heinrich, Mike Ranzinger, Hongxu (Danny)Yin, Yao Lu, Jan Kautz, Andrew Tao, Bryan Catanzaro, Pavlo Molchanov
Vision Language Model Full Model Multi Resolution Radio Source Multi Teacher Distillation Agglomerative Hierarchical Clustering
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
Tong Wu, Yinghao Xu, Ryan Po, Mengchen Zhang, Guandao Yang, Jiaqi Wang, Ziwei Liu, Dahua Lin, Gordon Wetzstein
Full Model Text to Image Generation Text to Image Diffusion Visual Attribute Fine Grained Attribute
Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Model
Donghwna Lee, Kyungha Min, Kirok Kim, Seyoung Jeong, Jiwoo Jeong, Wooju Kim
Full Model Text to Image Diffusion Model Diffusion Explainer Hybrid Fusion Person Name Person Image Generation
Model predictive control-based trajectory generation for agile landing of unmanned aerial vehicle on a moving boat
Ondřej Procházka, Filip Novák, Tomáš Báča, Parakh M. Gupta, Robert Pěnička, Martin Saska
Full Model Unmanned Aerial Vehicle Unmanned Surface Precision Landing
PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models
Zining Wnag, Jinyang Guo, Ruihao Gong, Yang Yong, Aishan Liu, Yushi Huang, Jiaheng Liu, Xianglong Liu
Full Model Practical Algorithm Sparsity Increase Random Sparsification Model Sparsification Sparsity Aware Post Training Sparsity

Full Model

Papers

Learning Structural Causal Models from Ordering: Identifiable Flow Models

FDM-Bench: A Comprehensive Benchmark for Evaluating Large Language Models in Additive Manufacturing Tasks

Is it the model or the metric -- On robustness measures of deeplearning models

Activation Sparsity Opportunities for Compressing General Large Language Models

Agtech Framework for Cranberry-Ripening Analysis Using Vision Foundation Models

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Clinical Pathology Analysis

Shiksha: A Technical Domain focused Translation Dataset and Model for Indian Languages

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Novel 3D Binary Indexed Tree for Volume Computation of 3D Reconstructed Models from Volumetric Data

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models

DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation

Distributed Gradient Descent with Many Local Steps in Overparameterized Models

How to Choose a Threshold for an Evaluation Metric for Large Language Models

RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models

FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models

Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Model

Model predictive control-based trajectory generation for agile landing of unmanned aerial vehicle on a moving boat

PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models