Pinned Repositories
babyai
BabyAI platform. A testbed for training agents to understand and execute natural language commands.
bib-baselines
elicit
ip_tool
This is an image processing toolbox that gives the functionality of selective blurring and object removal. It has a web-based GUI and can easily be used by following the instructions below. It incorporates: Selective Search based object selection Grab Cut based object selection Motion Blur Exemplar Based image inpainting TELEA image Inpaintaing
RLHF-APA
RL algorithm: Advantage induced policy alignment
strategic-lms-release
stream-of-search
Repository for the paper Stream of Search: Learning to Search in Language
synchromesh
Get language models to generate responses in a specific format reliably. Open source implementation of Synchromesh: Reliable code generation from pre-trained language models.
textboxes
Pytorch based implementation of the textboxes paper
kanishkg's Repositories
kanishkg/stream-of-search
Repository for the paper Stream of Search: Learning to Search in Language
kanishkg/synchromesh
Get language models to generate responses in a specific format reliably. Open source implementation of Synchromesh: Reliable code generation from pre-trained language models.
kanishkg/textboxes
Pytorch based implementation of the textboxes paper
kanishkg/bib-baselines
kanishkg/RLHF-APA
RL algorithm: Advantage induced policy alignment
kanishkg/babyai
BabyAI platform. A testbed for training agents to understand and execute natural language commands.
kanishkg/elicit
kanishkg/strategic-lms-release
kanishkg/academic-kickstart
Easily create a beautiful website using Academic and Hugo
kanishkg/bib-models
kanishkg/change-detection-test
A repository to investigate the failure of RL agents and their modules in capturing visual working memory or simple visual reasoning
kanishkg/boxing-gym
kanishkg/fb-15k-237
kanishkg/fb15k-237
kanishkg/flying-pigs
kanishkg/lab
A customisable 3D platform for agent-based AI research
kanishkg/langchain
⚡ Building applications with LLMs through composability ⚡
kanishkg/lm-pragmatics
Code and data for "A fine-grained comparison of pragmatic language understanding in humans and language models"
kanishkg/meetapp
meetapp
kanishkg/metaworld
An open source robotics benchmark for meta- and multi-task reinforcement learning
kanishkg/mlss
kanishkg/python-docs-samples
Code samples used on cloud.google.com
kanishkg/QDSyntheticData
kanishkg/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
kanishkg/socratic-tutor
Math tutor based on question asking
kanishkg/stat-nlp-nyu
Submissions rep
kanishkg/talking-heads
kanishkg/temporal-prediction
causal autoregressive next frame embedding prediction
kanishkg/unreal
Reinforcement learning with unsupervised auxiliary tasks
kanishkg/variational-item-response-theory-public
A PyTorch implementation of "Variational Item Response Theory: Fast Accurate, and Expressive"