
Our paper “LitForager: Exploring Multimodal Literature Foraging Strategies in Immersive Sensemaking” has been accepted to #ISMAR2025 as a #TVCG paper! 🎉✨

PhD Student @ Georgia Tech | Spatial Computing & HCI Research

Our paper “LitForager: Exploring Multimodal Literature Foraging Strategies in Immersive Sensemaking” has been accepted to #ISMAR2025 as a #TVCG paper! 🎉✨

Big reasoning speedups are here. 1,000× faster training and 280× less compute than any looped model. All done using a fully trainable energy from the 80s Keep reading to hear how energy is the right paradigm for reasoning With @HughBlayney @jcrwhittington @prefrontal_ai 🧵/10

Here's this year’s lineup of papers, workshops, doctoral colloquium presentations, and more from @GeorgiaTech at @ieeevis #IEEEVIS2026! 🎉 Check out the schedule below—including our Best Short Paper, Honorable Mention winner—and come say hello!

Frontier AI labs are talking more than ever about 𝐀𝐈 𝐬𝐚𝐟𝐞𝐭𝐲 🛡️ while releasing models faster than ever 🚀 We don’t release frontier models. But we do take their safety seriously 😄 Our 𝐄𝐌𝐍𝐋𝐏 𝟐𝟎𝟐𝟔 Main paper, 𝐑𝐄𝐂𝐀𝐏, studies how flawed reasoning can undermine model safety, and how to train reasoning models to recognize, override, and recover from unsafe trajectories 🔄🤖 Made a short video explaining the idea 🎬 Huge thanks to @pinyuchenTW, Eric Smith, @songjiang24, Hongyuan Zhan, @haozhu_wang, @mapa4u, @PoloChau, and @jianfengchi 🙌 #AISafety #LLM #EMNLP2026

📄 Paper: arxiv.org/abs/2607.28583 💻 Code: github.com/AlexanderHYang/cr… 📺 Full talk: youtube.com/watch?v=zaG0kN3M…

✨ With CrossAtlas, we: 🖥️ Compare projections for XR-to-desktop collaboration 👥 Study 48 participants across three spatial layouts 💡 Find equirectangular stays more robust as curvature increases

Excited to share our work at #ISMAR2026 🇮🇹! Our paper, “CrossAtlas: Evaluating Projection Techniques for Spatial Referencing in Cross-Reality Collaboration,” has been accepted to the IEEE TVCG journal track! ✨

🚨 New paper alert! 🚨 Can you believe it? Flawed thinking helps reasoning models learn better! Injecting just a bit of flawed reasoning can collapse safety by 36% 😱 — but we teach large reasoning models to fight back 💪🛡️. Introducing RECAP 🔄: an RL post-training method that trains models to override unsafe reasoning, reroute to safe & helpful answers, and stay robust — all without extra training cost. ✨ Safer reasoning 🤖 ✨ Stronger jailbreak resistance 🔓 ✨ Lower overrefusal 🙅 ✨ Preserved core reasoning capability 🧠 #LLM #ReasoningModels #RLHF #AISafety #Alignment #MachineLearning

📄 Paper: arxiv.org/abs/2508.15043 💻 Code: github.com/AlexanderHYang/Li… A huge thank-you to my amazing collaborators Elliott Faa, Weijian Liu, Shunan Guo, @PoloChau, and @yalong_yang for making this work possible! 🙌

✨ With LitForager, researchers can: 📚 Organize papers in 3D to reveal connections 🔎 Discover papers with intelligent recommendations (topics, citations, co-authors) 👐 Interact naturally with gestures, voice & menus ⚡ Understand papers faster with AI insights

“I did it to make my presentations look humorous. Nobody at MIT taught us DEI or respect.” - Excuse given by MIT Media Lab researcher who has received many recognitions. NOTE: Most MIT Media Lab researchers I know are highly respectful and morally upright.
Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? 😡

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 @GeorgiaTech & @IBMResearch , introducing the 'safety basin' concept, in the thread! 👇

🎉The coolest #CSE school in the world is hiring multiple faculty members! Application link below👇

Introducing KnowledgeVIS! 🧠 KnowledgeVIS is a #visualization tool that compares fill-in-the-blank LLM prompts, revealing stereotypes & biases 💯 Paper: arxiv.org/abs/2403.04758 Code: github.com/AdamCoscia/Knowle… Check out how KnowledgeVIS helps NLP practitioners evaluate LLMs: 🧵

Two papers in the same session @ieeevis. Great collaborations with Xiaojuan Ma's lab @hkust, particularly @qian_hci, who is leading the composite vis. @luttul0110 presenting. +Sungwon, Chris North @VT_CS, @ticahere @hpfister @HarvardVCG and DoD for embodied data transformation!
Hello, #ieeevis! We're excited to share our work from @GeorgiaTech at this year's @ieeevis conference. Check out our papers, posters, and more at #VIS2024

Hello, #ieeevis! We're excited to share our work from @GeorgiaTech at this year's @ieeevis conference. Check out our papers, posters, and more at #VIS2024