This is an interactive app that allow users play around with the clip model to analyze images

Repository for Vision-and-Language Navigation via Causal Learning (Accepted by CVPR 2024)

PyTorch implementation of FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models (CVPR-2024)

An integer linear program solver using a Lagrange decomposition into binary decision diagrams. Lagrange multipliers are updated through dual block coordinate ascent.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Targeted Adversarial Training for Image Classification

A python implementation of the paper "Scalable Recognition with a Vocabulary Tree, D. Nister, H. Stewenius, 2006"

Learning Bottleneck Concepts in Image Classification (CVPR 2023)

Repo for "Synergy of Sight and Semantics: Visual Intention Understanding with CLIP"

💭 Intentonomy: towards Human Intent Understanding [CVPR 2021]

Code release for the WACV 2025 paper: Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion

CSI-IMD Dataset Repository

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

[ICLR2025] A versatile image-to-image visual assistant, designed for image generation, manipulation, and translation based on free-from user instructions.

Fusion Transformer with Object Mask Guidance for Image Forgery Analysis

Climate Data Set

Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.

This is the official repository of our NeurIPS 2025 paper "MaxSup: Overcoming Representation Collapse in Label Smoothing"

Google Research

This is the official implementation of our ACL 2025 Main paper "Balancing Diversity and Risk in LLM Sampling".

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"