3 papers
cs.LG2026
LATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target Discovery
Binglin Ji, Anindya Sarkar, Hengchang Lu +3
While diffusion models excel at capturing complex data distributions, scientific discovery often requires steering generation toward specific, uncharacterized regions that maximize…
cs.LG2026
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…
cs.LG2026
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…