-
Carnegie Mellon University
- Pittsburgh, PA, USA
- https://ggare-cmu.github.io/
- in/gautam-gare
- https://scholar.google.com/citations?user=BX4jUxEAAAAJ
- https://www.ri.cmu.edu/ri-people/gautam-gare/
Highlights
- Pro
Stars
Predict risk, rank priorities, and coordinate follow ups for Maternity and Diabetics
rakshanda-cmu / pdd
Forked from promptdriven/pddPrompt Driven Development Command Line Interface
A Real Estate Dataset Analysis codebase - As trial for SnapHomz
Attributes should come from images, not class names — distribution-conditioned attribute selection for CLIP. Interpretable, class-name-free zero-shot and few-shot classification. [ECCV 2026 Workshops]
Devkit and documentation for the NVIDIA Physical AI Autonomous Vehicles Dataset
NVIDIA CoC Autolabeler is an open autolabeling pipeline for autonomous vehicles that generates Chain-of-Causation reasoning labels and meta-actions from raw driving clips.
[ICLR2026] AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
A list of recent papers about adversarial learning
A PyTorch implementation of Pix2Seq for object detection, where detection is formulated as an autoregressive sequence generation task. This implementation supports both standard transformer and Lla…
LaTeX template for a CMU Robotics Institute Thesis
PaperBanana: Automating Academic Illustration For AI Scientists
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Optimize prompts, code, and more with AI-powered Reflective Optimization
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
neeharperi / LLaMA-Factory
Forked from hiyouga/LlamaFactoryUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
LLM Council works together to answer your hardest questions
[ECCV 2024] Soft Prompt Generation for Domain Generalization
Prefix-Tuning: Optimizing Continuous Prompts for Generation
A high-throughput and memory-efficient inference and serving engine for LLMs
manugaurdl / moondream
Forked from m87-labs/moondreamtiny vision language model