[CVPR'24] Validation-free few-shot adaptation of CLIP, using a well-initialized Linear Probe (ZSLP) and class-adaptive constraints (CLAP).

source code for NeurIPS'24 paper "Towards Calibrated Robust Fine-Tuning of Vision-Language Models"

A Python toolbox for conformal prediction research on deep learning models, using PyTorch.

[ICLR'24] Official code for "C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion"

The Code of SACP

Benchmarking LLMs via Uncertainty Quantification

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).

This repository contains a Jax implementation of conformal training corresponding to the ICLR'22 paper "learning optimal conformal classifiers".

Model calibration in CLIP Adapters

[ECCV 2024 - Oral Presentation] Python library that provides tools for calibrating object detectors and evaluating them

Code repository for the paper "Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction" @ ECCV 2024 (Oral)

Kandinsky conformal prediction for image segmentation algorithms

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

[EMNLP 2024] CompAct: Compressing Retrieved Documents Actively for Question Answering

Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

CaMML:Context-Aware MultiModal Learner for Large Models (ACL 2024)

E5-V: Universal Embeddings with Multimodal Large Language Models

[ICML'24] Open-Vocabulary Calibration for Fine-tuned CLIP

【ICLR 2024, Spotlight】Sentence-level Prompts Benefit Composed Image Retrieval

Findings of ACL'2023: Optimizing Test-Time Query Representations for Dense Retrieval