🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Students and alumni from Prof. Polo Chau's group (Duen Horng "Polo" Chau) are presenting Transformer Explainer next month at IEEE VIS! You can try the tool today and join the crowd of over 60,000 fellow users who are learning more about transformers through GPT-2! poloclub.github.io/transformer-ex…

😎 Our paper on the LLM safety landscape has been accepted at NeurIPS Conference 2024! #Safety #LLM #MachineLearning

Congratulations to all the teams at IEEE VIS that are making data accessible, informative, and beautiful. Eighteen Georgia Tech teams have new innovations in visual analytics at the conference, Oct. 13-18. We created our own dynamic interactive visuals to show the people and

CSE Prof. Duen Horng "Polo" Chau and his group are presenting two papers and two posters this week at IEEE VIS! Check out the interactive graphic 🔗👇 for a peek of all Georgia Tech research presented this week, including award-winning work on Transformer Explainer! public.tableau.com/views/VIS2024/…

🚀Excited to present Diffusion Explainer at the IEEE VIS tomorrow at 1:45pm EST in the AI & LLM session! Try it now: poloclub.github.io/diffusion-expl… #StableDiffusion #GenerativeAI #AI #Visualization #IEEEVIS2024

Excited to share Dense Associative Memory through the Lens of Random Features accepted to #NeurIPS2024🎉 DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights! Distributed memory for DenseAMs, unlocked🔓

Trustworthy machine learning focuses on building AI systems people can rely on: fair, transparent, secure, and aligned with human values. 🛡️ Learn more about our NeurIPS '24 joint research Georgia Tech & IBM Research , introducing the 'safety basin' concept, in the thread! 👇

How big of a deal is artificial intelligence to CSE? Big enough that one-third of our faculty have papers accepted to one of the world's largest conferences on impactful #AI research! Meet our researchers here at the GT @ #NeurIPS2024 website: sites.gatech.edu/research/neuri…

🚀 Effective Guidance for Model Attention with Simple Yes-no Annotations Excited to share that I'll be presenting our recent work 🎨CRAYON🖍️ at IEEE Big Data soon! Catch me at 2pm in the Deep Learning II session!

Gradient descent alone tends to converge to local minima. Momentum frames optimization as a ball with mass moving down a hill. By adding inertia, the ball resists settling in small basins, allowing it to arrive at the global minimum.

Introducing ConceptAttention, an approach to interpreting diffusion transformer models! Write a prompt, choose some concepts, generate an image, and get high-quality heatmaps of text concepts. Our method outperforms existing methods like cross attention. Link to demo 👇

All three RPT cases from the School of CSE this year have been approved! Join us in congratulating the following faculty on their promotions! 🥳🎉 -B. Aditya Prakash, professor -Chao Zhang, associate professor (w/tenure) -Xiuwei Zhang, associate professor (w/tenure)

Diffusion Transformers aren't just generative models, but also powerful multi-modal encoders. ConceptAttention creates rich heatmaps of text concepts in images from DiT representations. This even works on real images, and can be applied to tasks like segmentation! Demo 👇

Create heatmaps that localize text concepts in generated videos. We discovered that our approach, ConceptAttention, can be directly extended from image generation to video generation models! It's amazing how simple techniques often generalize way better than more complex ones.

Diffusion models leverage a variety of samplers. Deterministic methods like DDIM produce orderly paths. In contrast, stochastic samplers like DDPM produce chaotic trajectories. Despite their differences, both methods draw valid samples from the underlying distribution.

I've been putting together an interactive tool called DiffusionLab for explaining the geometric intuition behind diffusion and flow based generative models. Sampling is actually being done in the browser using Tensorflow.js! It is still in the very early stages.

Guardrail models like 🛡️ Llama Guard do more than filtering — we repurpose them to track how safety risk evolves 📉 through a response. This gives rise to the STAR ⭐ score: a fine-grained signal for finetuning LLMs more safely 🤖🔒 Curious how it works? More in the thread 👇

🚨 New work: We rethink how we finetune safer LLMs — not by filtering after the generation, but by tracking safety risk token by token during training. We repurpose guardrail models like 🛡️ Llama Guard and Granite Guardian to score evolving risk across each response 📉 — giving