news

Oct 02, 2026 Our paper LATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target Discovery is now available on arXiv. LATS is accepted to NeurIPS 2026 Workshop on AI for Stochastic Dynamics.
Sep 27, 2026 Our paper Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery is now available on arXiv. This work is accepted to NeurIPS 2026.
Jul 06, 2026 Our paper Sampling Meets Interaction: Sequentially-Controlled Multi-Particle Flow-Maps for Efficient Inference-time Search is now available on arXiv.
Jul 03, 2026 Our paper BFMT: Enhancing Search Capabilities of Tree Sampler via Bootstrap Flow-Map Tree is now available on arXiv.
May 29, 2026 Our paper DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments is now available on arXiv. DiffVAS is accepted to AAMAS 2026.
May 27, 2026 Our paper PAPA: Online Personalized Active Preference Alignment is now available on arXiv. PAPA is accepted to ECML-PKDD 2026.
Oct 20, 2025 Our Paper DiffATD: Diffusion-guided Active Target Discovery is now available on arXiv. DiffATD is accepted to NeurIPS 2025.
Oct 17, 2025 Our Paper EM-PTDM: Expectation Maximized Permanent Temporary Diffusion Memory is now available on arXiv. EM-PTDM is accepted to NeurIPS 2025.