AI, ML, and Computer Vision Meetup - August 27, 2026

Join our virtual meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision.

Diffusion-based image editing and personalization models have made it increasingly easy to manipulate and replicate visual concepts from only a few reference images. However, existing protection methods often overfit to a single attack model and fail to generalize across diverse editing pipelines. In this presentation, I will discuss recent advances in concept protection for generative AI systems, focusing on targeted perturbation strategies and style-sensitive diffusion representations. I will also present experimental findings across multiple editing and fine-tuning scenarios, highlighting the challenges of robustness, transferability, and imperceptibility in practical protection settings. Finally, I will discuss open problems and future directions toward trustworthy generative content ownership.

This talk will explore practical workflows for building, evaluating, and improving modern computer vision systems. We’ll dive into real-world approaches to dataset curation, model analysis, multimodal AI workflows, and production-ready vision pipelines using open-source technologies.

The session is designed for engineers, researchers, and AI practitioners looking to better understand how teams are developing and scaling computer vision applications today. Expect practical demos, technical insights, and discussions around the evolving AI tooling ecosystem.

AI has demonstrated a lot of new possibilities, from drafting emails to image editing and generation. The efficacy of AI models is largely built upon a standard machine learning pipeline, where data is fed into models to get representations and predictions, and the performance is evaluated with controlled benchmarks and metrics. However, the mismatch arises when we try to transit this pipeline to the interaction with the real world and use AI for scientific discovery. Beyond close-set decisions, scientists want to discover new categories and propose new hypotheses. In this talk, I will share how I address the challenges of AI for science from the perspectives of data-centric methods and interpretability approaches.

Computer-use agents have converged on one recipe: a vision-language model reads screenshots, emits mouse and keyboard actions, and is post-trained with SFT then multi-turn RL on verifiable outcomes. This talk traces where that recipe has landed across the recent generation of open GUI specialists and closed frontier systems, and the failure modes that persist: grounding on dense or non-standard UIs, credit assignment over long horizons, irreversible actions. It then turns to the environment problem. RL needs millions of resettable episodes, so recent work generates the screen instead of capturing it, action-conditioned latent-diffusion renderers that predict the next frame from cursor and key events. What they simulate well, and where they drift.