Current benchmarks for evaluating the chemical reasoning capabilities of Large Language Models (LLMs) are limited by oversimplified tasks, lack of process-level evaluation, and misalignment with expert-level chemistry skills. To address these issues, we introduce SUPERChem, a benchmark of 500 expert-curated reasoning-intensive chemistry problems, covering diverse subfields and provided in both multimodal and text-only formats. Original content and an iterative curation pipeline eliminate flawed items and mitigate data contamination. Each problem is paired with an expert-authored solution path, enabling Reasoning Path Fidelity (RPF) scoring to evaluate reasoning quality beyond final-answer accuracy. Evaluations against a human baseline of 40.3% accuracy show that even the best-performing model, GPT-5 (High), reaches only 38.5%, followed closely by Gemini 2.5 Pro (37.9%) and DeepSeek-V3.1-Think (37.3%). SUPERChem elicits multi-step, multimodal reasoning, reveals model-dependent effects of visual information, and distinguishes high-fidelity reasoners from heuristic ones. By providing a challenging benchmark and a reliable evaluation framework, SUPERChem aims to facilitate the advancement of LLMs toward expert-level chemical intelligence. The dataset of the benchmark is available at https://huggingface.co/datasets/ZehuaZhao/SUPERChem.

Model validation, long taken to be "solved" via the train-test paradigm, has become one of the central challenges in modern machine learning and artificial intelligence.

This work presents a case study of a heterogeneous multiphysics solver from the nuclear fusion domain. At the macroscopic scale, an auto-differentiable ODE solver in JAX computes the evolution of the pulsed power circuit and bulk plasma parameters for a compressing Z Pinch. The ODE solver requires a closure for the impedance of the plasma load obtained via root-finding at every timestep, which we solve efficiently using gradient-based Newton iteration. However, incorporating non-differentiable production-grade plasma solvers like Gkeyll (a C/CUDA plasma simulation suite) into a gradient-based workflow is non-trivial. The ''Tesseract'' software addresses this challenge by providing a multi-physics differentiable abstraction layer made fully compatible with JAX (through the `tesseract_jax` adapter). This architecture ensures end-to-end differentiability while allowing seamless interchange between high-fidelity solvers (Gkeyll), neural surrogates, and analytical approximations for rapid, progressive prototyping.

Despite the striking successes of deep neural networks trained with gradient-based optimization, these methods differ fundamentally from their biological counterparts. This gap raises key questions about how nature achieves robust, sample-efficient learning at minimal energy costs and solves the credit-assignment problem without backpropagation. We take a step toward bridging contemporary AI and computational neuroscience by studying how neural dynamics can support fully local, distributed learning that scales to simple machine-learning benchmarks. Using tools from statistical mechanics, we identify conditions for the emergence of robust dynamical attractors in random asymmetric recurrent networks. We derive a closed-form expression for the number of fixed points as a function of self-coupling strength, and we reveal a phase transition in their structure: below a critical self-coupling, isolated fixed points coexist with exponentially many narrow clusters showing the overlap-gap property; above it, subdominant yet dense and extensive clusters appear. These fixed points become accessible, including to a simple asynchronous dynamical rule, after an algorithm-dependent self-coupling threshold. Building on this analysis, we propose a biologically plausible algorithm for supervised learning with any binary recurrent network. Inputs are mapped to fixed points of the dynamics, by relaxing under transient external stimuli and stabilizing the resulting configurations via local plasticity. We show that our algorithm can learn an entangled version of MNIST, leverages depth to develop hierarchical representations and increase hetero-association capacity, and is applicable to several architectures. Finally, we highlight the strong connection between algorithm performance and the unveiled phase transition, and we suggest a cortex-inspired alternative to self-couplings for its emergence.

Model validation, long taken to be "solved" via the train-test paradigm, has become one of the central challenges in modern machine learning and artificial intelligence.

This work walks through different visualization techniques for combinatorial search landscapes, focusing on multimodality. We discuss different techniques from the landscape analysis literature, and how they can be combined to provide a more comprehensive view of the search landscape. We also include examples and discuss relevant work to show how others have used these techniques in practice, based on the geometric and aesthetic elements of the Grammar of Graphics. We conclude that there is no free lunch in visualization, and provide recommendations for future work as there are several paths to continue the work in this field.

Artificial intelligence is set to revolutionize social and political life in unpredictable ways, raising questions about the principles that ought to guide its development and regulation. By examining digital advertising and social media algorithms, this article highlights how artificial intelligence already poses a significant threat to the republican conception of liberty -- or freedom from unaccountable power -- and thereby highlights the necessity of protecting republican liberty when integrating artificial intelligence into society. At an individual level, these algorithms can subconsciously influence behavior and thought, and those subject to this influence have limited power over the algorithms they engage. At the political level, these algorithms give technology company executives and other foreign parties the power to influence domestic political processes, such as elections; the multinational nature of algorithm-based platforms and the speed with which technology companies innovate make incumbent state institutions ineffective at holding these actors accountable. At both levels, artificial intelligence has thus created a new form of unfreedom: digital domination. By drawing on the works of Quentin Skinner, Philip Pettit, and other republican theorists, this article asserts that individuals must have mechanisms to hold algorithms (and those who develop them) accountable in order to be truly free.