You may already be amazed by diffusion models for generating images and videos—but did you know they can also help wildlife conservation🐘? . We propose DiffOracle, combining diffusion models & game theory to stop poaching!. Arxiv:

RT @paularodrid: Excited to present our paper at #UAI2025 on Thursday 🇧🇷 . Can we predict which datasets transfer best when downstream deci….

Thanks for all my wonderful collaborators: Haichuan Wang, @pyrojewel419, Cheol Woo Kim, Mingxiao Song, Alayna Nguyen,@TonghanW , @haifengxu0 and @MilindTambe_AI.

Empirically, we find that our game-theoretic approach yields patrol strategies with significantly lower regret than baseline methods, resulting in more effective wildlife protection in national parks.

To solve the game with diffusion models, we use the double oracle framework. This introduces challenges—constrained strategy space and sampling from unnormalized distributions. We address them via a strategy of strategies and a twisted SMC sampler for precise utility estimation.

To account for imperfections in the learned diffusion model, we formulate a robust patrol optimization problem as a two-player zero-sum game between a ranger defender and a nature adversary that selects the worst-case poaching activity within a constrained space.

We use a conditional diffusion model to forecast the number of snares in each grid cell of the national park, capturing complex high-dimensional distributions. On poaching data from Murchison Falls National Park (Uganda), our model outperforms baselines in forecasting accuracy.

RT @MilindTambe_AI: Absolutely thrilled to be able host this alumni dinner for our Teamcore research group at #AAAI2025. It was (and it con….

RT @YuanqiD: Afterall, DiffOPT is accepted in @aistats_conf 2025! Generative priors are natural for optimization esp. formulated as samplin….

RT @YuanqiD: 📢📢📢 Happy to introduce Graph Generative Pre-trained Transformers (G2PT):. Can we tokenize graphs and train an autoregressive (….

RT @MilindTambe_AI: So fantastic to have @konglingkai_AI as a postdoc with us at @hseas. Excited for all our research collaboration!.

The interdisciplinary environment at @GTCSE has profoundly shaped my research philosophy. I am deeply grateful to my postdoc advisor @MilindTambe_AI for providing me with the opportunity to work on these amazing projects that contribute to society!.

RT @allen_dongxiawu: #NeurIPS I’m on the 2024-25 job market, seeking faculty positions and postdoc opportunities! My research focuses on Ba….

Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards.⏰: Sat, December 14,.🚩: SoLaR workshop: and GenAI4Health workshop: This is in collaboration with @Shresth_verma, @niclasboehmer, @MilindTambe_AI

Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis.⏰: Friday, December 13. This is in collaboration with @HessianLiu, Shangqing Xu, @leozhao_zhiyuan, @Harsha_64, Aditya B. Sasanur, Megha Sharma, @jiamingcui1997, @qingsongedu, @chaozhangcs, @badityap

Aligning Large Language Models with Representation Editing: A Control Perspective. ⏰: Thursday, December 12. This is in collaboration with: @Haorui_Wang123*, Wenhao Mu*,@YuanqiD, @yuchen_zhuang, @YifeiZhou02, Yue Song, @rongzhi_zhang, @kaiwang_gua, @chaozhangcs.

Unfortunately, I won’t be able to attend @NeurIPSConf this year due to visa issues. However, my amazing collaborators from @GTCSE and @hseas will be there to present three papers. I’d also be happy to connect and discuss remotely! Details are below. #NeurIPS2024.

RT @YuanqiD: Unfortunately, I cannot make NeurIPS this year, but I will be around Seattle starting later this week! So if anyone stops by S….

Happy to share RE-Control is accepted to #NeurIPS2024!.

RT @YuanqiD: 🧵1/6 Happy to introduce ChemFlow:.Navigating Chemical Space with Latent Flows.arXiv: Demos are availa….