Yew-Soon Ong

Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector Merging

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

Masked Skill Token Training for Hierarchical Off-Dynamics Transfer

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

An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems

FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information Seeking

EvoCF: Multi-agent Collaboration with Memory-guided Evolutionary Counterfactual Planning

Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs

RAISE the Bar: Ensemble-based Online Reinforcement Learning for Dynamic Workflow Scheduling

ReconstructionNet: A Neural Network Architecture for Uncertainty-Aware Predictions with Explainability

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework

HypoSpace: Evaluating LLM Creativity as Set-Valued Hypothesis Generators under Underdetermination

Domain Bridging: Enabling Adaptation without Peeking at Target Data

Deterministic Transport-Based Sampling via Wasserstein Gradient Flows

Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models

Machine Unlearning via Task Simplex Arithmetic

InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning

Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization

Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices

Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity

Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning

Unified (Semi) Unbalanced and Classic Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization

Novelty Unlocking with Multiobjective Generative Models: Batch Diversity of Human Motions

Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection

Geo-3DGS: Multi-view Geometry Consistency for 3D Gaussian Splatting and Surface Reconstruction

SIG: Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs

A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver

Auto-Ensemble Structure Learning of Large Gaussian Bayesian Networks

Looks Great, Functions Better: Physics Compliance Text-to-3D Shape Generation