activity
20242026
collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

IKNO: Infinite-order Kernel Neural Operators

Pengyuan Zhu, Ivor W. Tsang, Yueming Lyu

Neural operators have achieved significant success in modern scientific computing due to their flexibility and strong generalization capabilities. Existing models, however, primari…

cs.LG2026

Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field

Kim Yong Tan, Yueming Lyu, Ivor Tsang +1

Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, e…

cs.LG2026

Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation

Atsushi Nitanda, Dake Bu, Yueming Lyu +1

We study Slowly Annealed Langevin Dynamics (SALD), a sampler for tracking a path of moving target distributions and approximating the terminal target through time slowdown. We esta…

cs.LG2025

Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation

Kim Yong Tan, Yueming Lyu, Ivor Tsang +1

Diffusion models have been successful in learning complex data distributions. This capability has driven their application to high-dimensional multi-objective black-box optimizatio…

cs.LG2025

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity

Zhenglin Wan, Xingrui Yu, David Mark Bossens +5

Imitation learning (IL) has shown promise in various applications (e.g. robot locomotion) but is often limited to learning a single expert policy, constraining behavior diversity a…

cs.LG2025

MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

Chengqi Zheng, Jianda Chen, Yueming Lyu +5

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven constructio…