HarshTrivedi
🤖 Building AI agents & interactive environments. E.g., 🌍 AppWorld (https://appworld.dev)
LUNR Lab @ Stony Brook UniversityUnited States
Pinned Repositories
malloc
An implementation of dynamic memory allocator in C using explicit free list, as according to the lab assignment of CS-APP book , reaching 91 % efficiency.
nmn-pytorch
Neural Module Network for VQA in Pytorch
packing-unpacking-pytorch-minimal-tutorial
Minimal tutorial on packing and unpacking sequences in pytorch
paraphrase-generation
Open-sourced implementation of this paper: https://goo.gl/EQLgnT
appworld
🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Paper.
ircot
Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23
multee
Repository for Repurposing Entailment for Multi-Hop Question Answering Tasks, NAACL19
musique
Repository for MuSiQue: Multi-hop Questions via Single-hop Question Composition, TACL 2022
teabreac
Repository for Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts, EMNLP22
HarshTrivedi's Repositories
HarshTrivedi/packing-unpacking-pytorch-minimal-tutorial
Minimal tutorial on packing and unpacking sequences in pytorch
HarshTrivedi/malloc
An implementation of dynamic memory allocator in C using explicit free list, as according to the lab assignment of CS-APP book , reaching 91 % efficiency.
HarshTrivedi/phd-advice
A list of advisory blogs and resources that I have found useful so far.
HarshTrivedi/DecomP-ODQA
Official repository for ODQA experiments from Decomposed Prompting: A Modular Approach for Solving Complex Tasks, ICLR23
HarshTrivedi/firewebsite
FIRE 2015/16 webapp
HarshTrivedi/llm_server
HarshTrivedi/Awesome-Papers-Autonomous-Agent
A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents.
HarshTrivedi/awesome-tips
HarshTrivedi/coin-betting-optimizers-pytorch
Pytorch implementations of Coin Betting Optimizers
HarshTrivedi/retriever_server
Retriever Server (for various datasets like HotpotQA, IIRC, StrategyQA etc)
HarshTrivedi/allennlp
An open-source NLP research library, built on PyTorch.
HarshTrivedi/allennlp-website
The public website for AllenNLP.
HarshTrivedi/aneesh_help
HarshTrivedi/awesome-language-agents
List of language agents based on paper "Cognitive Architectures for Language Agents"
HarshTrivedi/beaker-vllm
HarshTrivedi/beakerizer
HarshTrivedi/chainlit
Build Python LLM apps in minutes ⚡️
HarshTrivedi/contrib
Implementations of ideas from recent papers
HarshTrivedi/debate_passages
This is for personal use, and needs to be public for some reason.
HarshTrivedi/haystack_wrapper
A wrapper around the haystack library for my experiments.
HarshTrivedi/jiant-fork
jiant is a software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks.
HarshTrivedi/notion-backup
Automatic Notion workspace backup to Google Drive, Dropbox, pCloud, Nextcloud or to your local machine.
HarshTrivedi/numnet_plus
This is the official code repository for NumNet+(https://leaderboard.allenai.org/drop/submission/blu418v76glsbnh1qvd0)
HarshTrivedi/optuna
A hyperparameter optimization framework
HarshTrivedi/paragraph2sentences
HarshTrivedi/ParlAI
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
HarshTrivedi/skiff-harsht-demo
HarshTrivedi/sublime-vscode-theme
A theme for VSCode that makes it look just like Sublime Text
HarshTrivedi/system-2-research
System 2 Reasoning Link Collection
HarshTrivedi/tnt
Simple tools for logging and visualizing, loading and training