Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2606. 00651v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to relevant experts, yet introduce a critical vulnerability: Safety Sparsity, where safety capabilities concentrate in few experts, making them susceptible to adversarial bypassing.
arXiv:2605. 21422v3 Announce Type: replace Abstract: As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization.
arXiv:2601. 22813v2 Announce Type: replace Abstract: The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs.
arXiv:2606. 01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience.
arXiv:2602. 03018v2 Announce Type: replace Abstract: Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selection notoriously hard.
arXiv:2602. 16763v2 Announce Type: replace Abstract: Artificial intelligence benchmarks are an important mechanism for measuring model progress and guiding deployment decisions.
arXiv:2603. 12996v2 Announce Type: replace Abstract: Parallel decoding for Diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneously requires accounting for inter-token dependencies.
arXiv:2606. 01375v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly entering students' learning practices, but their educational value depends on whether they support reasoning or enable task completion without engagement.
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv:2606. 00442v1 Announce Type: new Abstract: Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks.
arXiv:2512. 10234v2 Announce Type: replace-cross Abstract: Even LLMs that appear safe during evaluation can still produce harmful responses in deployment.
arXiv:2605. 26684v2 Announce Type: replace-cross Abstract: Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks.
arXiv:2602. 03554v2 Announce Type: replace-cross Abstract: Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning.
arXiv:2605. 12400v2 Announce Type: replace-cross Abstract: We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories.
arXiv:2605. 14791v2 Announce Type: replace-cross Abstract: Recent advances in artificial intelligence (AI) agents are pushing AI beyond tools toward autonomous scientific discovery.
arXiv:2605. 12813v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs.
arXiv:2605. 21648v2 Announce Type: replace Abstract: We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos, and show that it predicts a simple, no-cost change to standard practice: \emph{front-loaded} dropout schedules cut test loss by \(18\)--\(35\%\) over constant dropout in MLPs and Vision Transformers at fixed budget.
arXiv:2606. 01730v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as heuristic advisors for black-box optimization, yet their suggestions and self-reported confidence are not necessarily calibrated to downstream objective values.
arXiv:2606. 00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated.
arXiv:2606. 00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing.