HallE_Control

Object control software

Controlling object hallucination in large multimodal models

HallE-Control: Controlling Object Hallucination in LMMs

GitHub

28 stars
1 watching
1 forks
Language: Python
last commit: over 2 years ago

Related projects:

RepositoryDescriptionStars
x-plug/mplug-halowlEvaluates and mitigates hallucinations in multimodal large language models82
bradyfu/woodpeckerA method to correct hallucinations in multimodal large language models without requiring retraining617
yiyangzhou/lureAnalyzing and mitigating object hallucination in large vision-language models to improve their accuracy and reliability.136
robotology/whole-body-controllersDevelops control algorithms for humanoid robots using Simulink-based whole-body controllers125
junyangwang0410/haelmA framework for detecting hallucinations in large language models17
billchan226/halcAn implementation of an object hallucination reduction method using a PyTorch framework and various decoding algorithms.72
lalbj/paiImproves the performance of large language models by intervening in their internal workings to reduce hallucinations83
1zhou-wang/memvrAn implementation of a method to mitigate hallucinations in large language models using visual re-tracing28
yfzhang114/llava-alignDebiasing techniques to minimize hallucinations in large visual language models75
byucamacholab/autogatorSoftware package for camera-assisted motion control and experiment configuration of photonic integrated circuit interrogation platforms.6
junyangwang0410/amberAn LLM-free benchmark suite for evaluating MLLMs' hallucination capabilities in various tasks and dimensions98
vectara/hallucination-leaderboardCompares performance of large language models on generating coherent summaries from short documents1,281
aroongta/carla_controllerAutomated driving and path tracking control system using Carla-Vehicle assets.11
armomu/ergoudanA character controller demo using Babylon.js and Havok physics for third-person movement60
tianyi-lab/hallusionbenchAn image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy259