5 papers
Bootstrap Stochastic Interpolant Tree for Inference-time Search Under Sparse Reward
Binglin Ji, Anindya Sarkar, Yevgeniy Vorobeychik
Tree-based samplers offer a compelling alternative for scalable inference-time search, bypassing the per-step reward and gradient dependencies that introduce systematic bias into S…
BFMT: Enhancing Search Capabilities of Tree Sampler via Bootstrap Flow-Map Tree
Binglin Ji, Anindya Sarkar, Hengchang Lu +4
The ability to efficiently navigate high-dimensional spaces to identify optimal candidates-whether designing targeted molecular structures or generating images with preferred attri…
Sampling Meets Interaction: Sequentially-Controlled Multi-Particle Flow-Maps for Efficient Inference-time Search
Binglin Ji, Anindya Sarkar, Hengchang Lu +2
While generative models have enabled training-free reward alignment, existing particle-based methods are fundamentally constrained by their propensity to local exploration within n…
Active Target Discovery under Uninformative Prior: The Power of Permanent and Transient Memory
Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik
In many scientific and engineering fields, where acquiring high-quality data is expensive--such as medical imaging, environmental monitoring, and remote sensing--strategic sampling…
Online Feedback Efficient Active Target Discovery in Partially Observable Environments
Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik
In various scientific and engineering domains, where data acquisition is costly--such as in medical imaging, environmental monitoring, or remote sensing--strategic sampling from un…