TACO-Group

All

14 repositories

Re-Align
Public
A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.
alignment safety vlm post-training ppo hallucination dpo large-language-models llm rlhf
Python
•
Apache License 2.0
•0•25•0•0•Updated Feb 19, 2025Feb 19, 2025
OpenEMMA
Public
OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.
machine-learning networking algorithms transportation artificial-intelligence perception autonomous-car autonomous-driving autonomous-vehicles emma
Python
•
Apache License 2.0
•67•499•13•0•Updated Feb 19, 2025Feb 19, 2025
TrustEval-toolkit
Public
TrustEval: A modular and extensible toolkit for comprehensive trust evaluation of generative foundation models (GenFMs)
Python
•
MIT License
•2•0•0•0•Updated Feb 17, 2025Feb 17, 2025
taco-group.github.io
Public
HTML
•0•1•0•0•Updated Feb 11, 2025Feb 11, 2025
STAMP
Public
[ICLR'25] Official Implementation of STAMP: Scalable Task And Model-agnostic Collaborative Perception
transportation autonomous autonomous-driving autonomous-vehicles v2x v2v collaborative-learning intelligent-transportation cooperative-perception
Python
•
MIT License
•1•14•0•0•Updated Feb 4, 2025Feb 4, 2025
HFMF
Public
HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection
computer-vision deep-learning transformer vision deepfakes diffusion-models
Jupyter Notebook
•2•8•0•0•Updated Jan 6, 2025Jan 6, 2025
Video-Quality-Assessment-A-Comprehensive-Survey
Public
The Most Comprehensive Survey of Video Quality Assessment to Date.
visual vision vqa video-understanding iqa video-compression image-quality-assessment video-quality video-quality-assessment visual-perception
1•63•1•0•Updated Dec 24, 2024Dec 24, 2024
AutoTrust
Public
AutoTrust, a groundbreaking benchmark designed to assess the trustworthiness of DriveVLMs. This work aims to enhance public safety by ensuring DriveVLMs operate reliably across critical dimensions.
Python
•
Apache License 2.0
•2•38•0•0•Updated Dec 24, 2024Dec 24, 2024
FaceLock
Public
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
computer-vision image-editing privacy-protection diffusion-models generative-ai genai generative-editing
Python
•0•23•0•0•Updated Dec 17, 2024Dec 17, 2024
SleeperMark
Public
Apache License 2.0
•0•9•0•0•Updated Dec 6, 2024Dec 6, 2024
MWFormer
Public
[TIP2024] MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
image computer-vision cv ml transformer vision image-restoration image-enhancement vision-transformer
Python
•3•45•2•0•Updated Dec 6, 2024Dec 6, 2024
opencda-loop
Public
0•17•0•0•Updated Sep 28, 2024Sep 28, 2024
CoMamba
Public
CoMamba: Real-time Cooperative Perception Unlocked with State Space Models
Python
•
Other
•0•21•2•0•Updated Sep 20, 2024Sep 20, 2024
COVER
Public
🏆 [CVPRW 2024] COVER: A Comprehensive Video Quality Evaluator. 🥇 Winner solution for Video Quality Assessment Challenge at the 1st AIS 2024 workshop @ CVPR 2024
Python
•
MIT License
•4•50•4•0•Updated Jul 18, 2024Jul 18, 2024