주민건
기록 = 성장
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Kaiyu Yang
Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language
We propose LENS, a modular approach for tackling computer vision problems byleveraging the power of large language models (LLMs). Our system uses alanguage model to reason over outputs from a set of independent and highlydescriptive vision modules that provide exhaustive information about an imag…
William Berrios
ViNT: A Foundation Model for Visual Navigation
A foundation model for visual navigation that generalizes across environments and robots, and can be readily adapted to downstream tasks.
Dhruv Shah
Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
Generative AI and large language models hold great promise in enhancingcomputing education by powering next-generation educational technologies forintroductory programming. Recent works have studied these models for differentscenarios relevant to programming education; however, these works are li…
Tung PhungUnderstanding Social Reasoning in Language Models with Language Models
As Large Language Models (LLMs) become increasingly integrated into oureveryday lives, understanding their ability to comprehend human mental statesbecomes critical for ensuring effective interactions. However, despite therecent attempts to assess the Theory-of-Mind (ToM) reasoning capabilities o…
Kanishk GandhiBring Your Own Data! Self-Supervised Evaluation for Large Language Models
With the rise of Large Language Models (LLMs) and their ubiquitous deploymentin diverse domains, measuring language model behavior on realistic data isimperative. For example, a company deploying a client-facing chatbot mustensure that the model will not respond to client requests with profanity.…
Neel JainMedical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
The Segment Anything Model (SAM) has recently gained popularity in the fieldof image segmentation. Thanks to its impressive capabilities in all-roundsegmentation tasks and its prompt-based interface, SAM has sparked intensivediscussion within the community. It is even said by many prestigious exp…
Junde WuSAM on Medical Images: A Comprehensive Study on Three Prompt Modes
The Segment Anything Model (SAM) made an eye-catching debut recently andinspired many researchers to explore its potential and limitation in terms ofzero-shot generalization capability. As the first promptable foundation modelfor segmentation tasks, it was trained on a large dataset with an unpre…
Dongjie Cheng영과일 회장 모임
LLM Powered Autonomous Agents
Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it c…
Lilian Weng
GitHub - ChaoningZhang/MobileSAM: This is the offiicial code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight
This is the offiicial code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight - GitHub - ChaoningZhang/MobileSAM: This is the offiicial code for Faster Segment Anything (Mob...
ChaoningZhang