See-Kiong Ng

Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts

How to Cure Newton for Unlearning Neural Networks? An Empirical Study from the Hessian Perspective

RoboOmni: Proactive Robot Manipulation in Omni-modal Context

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment

WaterDrum: Watermark-based Data-centric Unlearning Metric

Projected Coupled Diffusion for Test-Time Constrained Joint Generation

Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning

NextQuill: Causal Preference Modeling for Enhancing LLM Personalization

Configuring Parallel Training of Neural Networks using Bayesian Optimization

Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

Escaping the Homophily Trap: A Threshold-free Graph Outlier Detection Framework via Clustering-guided Edge Reweighting

Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis

Adaptive Test-Time Compute Allocation via Training-Free Difficulty Proxies

Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding

Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads

Star-DS: Step-level Uncertainty-Aware Reasoning Data Selection in Reinforcement Learning for LLM Multi-step Reasoning

Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

PIED: Physics-Informed Experimental Design for Inverse Problems

Continual Multimodal Contrastive Learning

Efficient Top-m Data Values Identification for Data Selection

Confidence Elicitation: A New Attack Vector for Large Language Models

Efficient Inference for Large Language Model-based Generative Recommendation

Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

Source Attribution for Large Language Model-Generated Data

PLLaVA: Parameter-efficient LLaVA Extension from Image to Video Understanding

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

Prompt Optimization with Human Feedback

Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation