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.

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.

Contemporary ML separates the static structure of parameters from the dynamic flow of inference, yielding systems that lack the sample efficiency and thermodynamic frugality of biological cognition. In this theoretical work, we propose \textbf{Memory-Amortized Inference (MAI)}, a formal framework rooted in algebraic topology that unifies learning and memory as phase transitions of a single geometric substrate. Central to our theory is the \textbf{Homological Parity Principle}, which posits a fundamental dichotomy: even-dimensional homology ($H_{even}$) physically instantiates stable \textbf{Content} (stable scaffolds or ``what''), while odd-dimensional homology ($H_{odd}$) instantiates dynamic \textbf{Context} (dynamic flows or ``where''). We derive the logical flow of MAI as a topological trinity transformation: \textbf{Search $\to$ Closure $\to$ Structure}. Specifically, we demonstrate that cognition operates by converting high-complexity recursive search (modeled by \textit{Savitch's Theorem} in NPSPACE) into low-complexity lookup (modeled by \textit{Dynamic Programming} in P) via the mechanism of \textbf{Topological Cycle Closure}. We further show that this consolidation process is governed by a topological generalization of the Wake-Sleep algorithm, functioning as a coordinate descent that alternates between optimizing the $H_{odd}$ flow (inference/wake) and condensing persistent cycles into the $H_{even}$ scaffold (learning/sleep). This framework offers a rigorous explanation for the emergence of fast-thinking (intuition) from slow-thinking (reasoning) and provides a blueprint for post-Turing architectures that compute via topological resonance.

In distributed and federated learning algorithms, communication overhead is often reduced by performing multiple local updates between communication rounds. However, due to data heterogeneity across nodes and the local gradient noise within each node, this strategy can lead to the drift of local models away from the global optimum. To address this issue, we revisit the well-known federated learning method Scaffold (Karimireddy et al., 2020) under a gradient tracking perspective, and propose a unified spatio-temporal gradient tracking algorithm, termed ST-GT, for distributed stochastic optimization over time-varying graphs. ST-GT tracks the global gradient across neighboring nodes to mitigate data heterogeneity, while maintaining a running average of local gradients to substantially suppress noise, with slightly more storage overhead. Without assuming bounded data heterogeneity, we prove that ST-GT attains a linear convergence rate for strongly convex problems and a sublinear rate for nonconvex cases. Notably, ST-GT achieves the first linear speed-up in communication complexity with respect to the number of local updates per round $τ$ for the strongly-convex setting. Compared to traditional gradient tracking methods, ST-GT reduces the topology-dependent noise term from $σ^2$ to $σ^2/τ$, where $σ^2$ denotes the noise level, thereby improving communication efficiency.

Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage complementary RGB images to compensate for missing geometry, most methods still follow a Completion-by-Inpainting paradigm, synthesizing missing structures from fused latent features. We empirically show that this paradigm often results in structural inconsistencies and topological artifacts due to limited geometric and semantic constraints. To address this, we rethink the task and propose a more robust paradigm, termed Completion-by-Correction, which begins with a topologically complete shape prior generated by a pre-trained image-to-3D model and performs feature-space correction to align it with the partial observation. This paradigm shifts completion from unconstrained synthesis to guided refinement, enabling structurally consistent and observation-aligned reconstruction. Building upon this paradigm, we introduce PGNet, a multi-stage framework that conducts dual-feature encoding to ground the generative prior, synthesizes a coarse yet structurally aligned scaffold, and progressively refines geometric details via hierarchical correction. Experiments on the ShapeNetViPC dataset demonstrate the superiority of PGNet over state-of-the-art baselines in terms of average Chamfer Distance (-23.5%) and F-score (+7.1%).

We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in which agents can easily reward hack, such as by hardcoding test cases or editing the testing files. We measure reward hacking in three ways: held out unit tests, LLM judges, and test file edit detection. We verify these methods against human review and each other. We find the LLM judge to be highly effective at detecting reward hacking in unambiguous cases, and observe only minimal improvement from the use of held out test cases. In addition to testing many models using Inspect's basic_agent scaffold, we also measure reward hacking rates for three popular proprietary coding agents: OpenAI's Codex, Anthropic's Claude Code, and Google's Gemini CLI Using GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro, respectively. We observe explicit reward hacking by both Codex and Claude Code, and misaligned behavior by all three agents. Our codebase can be found at https://github.com/JonathanGabor/EvilGenie.

The discovery of high-performance photosensitizers has long been hindered by the time-consuming and resource-intensive nature of traditional trial-and-error approaches. Here, we present \textbf{A}I-\textbf{A}ccelerated \textbf{P}hoto\textbf{S}ensitizer \textbf{I}nnovation (AAPSI), a closed-loop workflow that integrates expert knowledge, scaffold-based molecule generation, and Bayesian optimization to accelerate the design of novel photosensitizers. The scaffold-driven generation in AAPSI ensures structural novelty and synthetic feasibility, while the iterative AI-experiment loop accelerates the discovery of novel photosensitizers. AAPSI leverages a curated database of 102,534 photosensitizer-solvent pairs and generate 6,148 synthetically accessible candidates. These candidates are screened via graph transformers trained to predict singlet oxygen quantum yield ($ϕ_Δ$) and absorption maxima ($λ_{max}$), following experimental validation. This work generates several novel candidates for photodynamic therapy (PDT), among which the hypocrellin-based candidate HB4Ph exhibits exceptional performance at the Pareto frontier of high quantum yield of singlet oxygen and long absorption maxima among current photosensitizers ($ϕ_Δ$=0.85, $λ_{max}$=650nm).

Recent strides in molecular design have introduced advanced generative models that excel in de-novo generation and optimization within 3D molecular space (Isert et al. [2023]).