3

A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

A physics-grounded benchmark, CrashTwin, that stress-tests whether generative world models obey physical laws in safety-critical multi-agent collisions, exposing physical violations hidden behind high perceptual quality.

The Last Human-Written Paper: Agent-Native Research Artifacts

A machine-executable format that replaces traditional papers with structured, agent-consumable research artifacts capturing logic, code, exploration, and evidence.

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment

A token-level confidence-calibrated negative preference alignment method for LLM unlearning that removes undesirable knowledge without requiring retention data or contrastive pairs.

DeepOSets: Non-Autoregressive In-Context Learning of Supervised Learning Operators

A non-autoregressive architecture combining DeepONets with DeepSets for in-context operator learning, achieving orders-of-magnitude parameter reduction and stronger noise robustness over transformer baselines.

A-CONECT: Designing AI-based Conversational Chatbot for Early Dementia Intervention

We develop a chatbot for early dementia prevention and leverage LLMs to build digital twins to evaluate chatbots.

A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection

We develop a hybrid federated learning for learning financial-crime predictive models from horizontal and vertical federated data structures.

FedNoisy: A Federated Noisy Label Learning Benchmark

The recent decade witnessed a surge of increase in financial crimes across the public and private sectors, with an average cost of scams of $102m to financial institutions in 2022. Developing a mechanism for battling financial crimes is an impending …

Precautionary Unfairness in Self-Supervised Contrastive Pre-training

Recently, self-supervised contrastive pre-training has become the de facto regime, that allows for efficient downstream fine-tuning. Meanwhile, its fairness issues are barely studied, though they have drawn great attention from the machine learning …