Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering.

As 4, number M 100) of FedA M = 1000performs faster gradient Model trained T1 2 {0,20,40,60,80,100}, whereT1 =0 Figure 5(a), we random performs margin20%intest model.

To show that the larger library allows our model to generate more unique molecules, we provide quality scores of our model (FREED(PE)) trained with the small library and the large, unfiltered libraryinTable2andTable3. Lastly, for 5ht1b, the scaffold and the generated molecule are docked in different binding sites. Since the generated molecule of 5ht1b is twice the size of the 5ht1b scaffold, we assume that the generated molecule could not fit in the originalbindingpocket. In this experiment, we tested our model's performance on the larger action space. We constructed a fragment library of 350 fragments and a fragment library of 1k fragments and trained our model on both libraries.

Infederated learning, itiscommon toassume thatclients arealwaysavailable to participate in training, which may not be feasible with user devices in practice.

Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate that explanations achieve this goal? Some research argues that explanations should help teach a student (either human or machine) to simulate the model being explained, and that the quality of explanations can be measured by the simulation accuracy of students on unexplained examples. In this work, leveraging meta-learning techniques, we extend this idea to improve the quality of the explanations themselves, specifically by optimizing explanations such that student models more effectively learn to simulate the original model. We train models on three natural language processing and computer vision tasks, and find that students trained with explanations extracted with our framework are able to simulate the teacher significantly more effectively than ones produced with previous methods. Through human annotations and a user study, we further find that these learned explanations more closely align with how humans would explain the required decisions in these tasks.

Navigating the vast chemical space of druggable compounds is a formidable challenge in drug discovery, where generative models are increasingly employed to identify viable candidates. Conditional 3D structure-based drug design (3D-SBDD) models, which take into account complex three-dimensional interactions and molecular geometries, are particularly promising. Scaffold hopping is an efficient strategy that facilitates the identification of similar active compounds by strategically modifying the core structure of molecules, effectively narrowing the wide chemical space and enhancing the discovery of drug-like products. However, the practical application of 3D-SBDD generative models is hampered by their slow processing speeds. To address this bottleneck, we introduce TurboHopp, an accelerated pocket-conditioned 3D scaffold hopping model that merges the strategic effectiveness of traditional scaffold hopping with rapid generation capabilities of consistency models. This synergy not only enhances efficiency but also significantly boosts generation speeds, achieving up to 30 times faster inference speed as well as superior generation quality compared to existing diffusion-based models, establishing TurboHopp as a powerful tool in drug discovery.

We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost $18/hour versus $60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks.