The widespread adoption of Large Language Models (LLMs) has raised significant privacy concerns regarding the exposure of personally identifiable information (PII) in user prompts. To address this challenge, we propose a query-unrelated PII masking strategy and introduce PII-Bench, the first comprehensive evaluation framework for assessing privacy protection systems. PII-Bench comprises 2,842 test samples across 55 fine-grained PII categories, featuring diverse scenarios from single-subject descriptions to complex multi-party interactions. Each sample is carefully crafted with a user query, context description, and standard answer indicating query-relevant PII. Our empirical evaluation reveals that while current models perform adequately in basic PII detection, they show significant limitations in determining PII query relevance. Even state-of-the-art LLMs struggle with this task, particularly in handling complex multi-subject scenarios, indicating substantial room for improvement in achieving intelligent PII masking.

This paper proposes a new 3D molecule generation framework, called GOAT, for fast and effective 3D molecule generation based on the flow-matching optimal transport objective. Specifically, we formulate a geometric transport formula for measuring the cost of mapping multi-modal features (e.g., continuous atom coordinates and categorical atom types) between a base distribution and a target data distribution. Our formula is solved within a unified, equivalent, and smooth representation space. This is achieved by transforming the multi-modal features into a continuous latent space with equivalent networks. In addition, we find that identifying optimal distributional coupling is necessary for fast and effective transport between any two distributions. We further propose a flow refinement and purification mechanism for optimal coupling identification. By doing so, GOAT can turn arbitrary distribution couplings into new deterministic couplings, leading to a unified optimal transport path for fast 3D molecule generation. The purification filters the subpar molecules to ensure the ultimate generation performance. We theoretically prove the proposed method indeed reduced the transport cost. Finally, extensive experiments show that GOAT enjoys the efficiency of solving geometric optimal transport, leading to a double speedup compared to the sub-optimal method while achieving the best generation quality regarding validity, uniqueness, and novelty.

Can we train a molecule generator that can generate 3D molecules from a new domain, circumventing the need to collect data? This problem can be cast as the problem of domain adaptive molecule generation. This work presents a novel and principled diffusion-based approach, called GADM, that allows shifting a generative model to desired new domains without the need to collect even a single molecule. As the domain shift is typically caused by the structure variations of molecules, e.g., scaffold variations, we leverage a designated equivariant masked autoencoder (MAE) along with various masking strategies to capture the structural-grained representations of the in-domain varieties. In particular, with an asymmetric encoder-decoder module, the MAE can generalize to unseen structure variations from the target domains. These structure variations are encoded with an equivariant encoder and treated as domain supervisors to control denoising. We show that, with these encoded structural-grained domain supervisors, GADM can generate effective molecules within the desired new domains. We conduct extensive experiments across various domain adaptation tasks over benchmarking datasets. We show that our approach can improve up to 65.6% in terms of success rate defined based on molecular validity, uniqueness, and novelty compared to alternative baselines.

The large-scale multiobjective optimization problem (LSMOP) is characterized by simultaneously optimizing multiple conflicting objectives and involving hundreds of decision variables. Many real-world applications in engineering fields can be modeled as LSMOPs; simultaneously, engineering applications require insensitivity in performance. This requirement usually means that the results from the algorithm runs should not only be good for every run in terms of performance but also that the performance of multiple runs should not fluctuate too much, i.e., the algorithm shows good insensitivity. Considering that substantial computational resources are requested for each run, it is essential to improve upon the performance of the large-scale multiobjective optimization algorithm, as well as the insensitivity of the algorithm. However, existing large-scale multiobjective optimization algorithms solely focus on improving the performance of the algorithms, leaving the insensitivity characteristics unattended. In this work, we propose an evolutionary algorithm for solving LSMOPs based on Monte Carlo tree search, the so-called LMMOCTS, which aims to improve the performance and insensitivity for large-scale multiobjective optimization problems. The proposed method samples the decision variables to construct new nodes on the Monte Carlo tree for optimization and evaluation. It selects nodes with good evaluation for further search to reduce the performance sensitivity caused by large-scale decision variables. We compare the proposed algorithm with several state-of-the-art designs on different benchmark functions. We also propose two metrics to measure the sensitivity of the algorithm. The experimental results confirm the effectiveness and performance insensitivity of the proposed design for solving large-scale multiobjective optimization problems.

We define very large multi-objective optimization problems to be multiobjective optimization problems in which the number of decision variables is greater than 100,000 dimensions. This is an important class of problems as many real-world problems require optimizing hundreds of thousands of variables. Existing evolutionary optimization methods fall short of such requirements when dealing with problems at this very large scale. Inspired by the success of existing recommender systems to handle very large-scale items with limited historical interactions, in this paper we propose a method termed Very large-scale Multiobjective Optimization through Recommender Systems (VMORS). The idea of the proposed method is to transform the defined such very large-scale problems into a problem that can be tackled by a recommender system. In the framework, the solutions are regarded as users, and the different evolution directions are items waiting for the recommendation. We use Thompson sampling to recommend the most suitable items (evolutionary directions) for different users (solutions), in order to locate the optimal solution to a multiobjective optimization problem in a very large search space within acceptable time. We test our proposed method on different problems from 100,000 to 500,000 dimensions, and experimental results show that our method not only shows good performance but also significant improvement over existing methods.