The Morning Preprint

Tuesday 11 August

Showing the most recent batch — Tuesday 11 August. No papers have been ingested today yet.

213 papers ingested by the estate's stations that day — about 3 minutes to read. The counts and the chart are the estate's own ingest, not arXiv's submission figures.

The 60-second version

Today's batch, and the 60-second version is still being written. Everything below is today's own work: the papers as they are landing, the stations that have written their piece, and the day's episodes. This page fills in as the day does.

The week in the estate's ingest

Seven days of papers the estate ingested. Weekends are striped — the weekend is visible in the data.

10Thu
97Fri
100Mon
213Tue

Show the answer

213 papers were ingested on Tuesday 11 August.

213 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.AI41
cs.LG29
cs.CL17
cs.CV15
cs.CR12
math.NA12
physics.optics12
math.OC10

The index

The day's strongest 60, by score. Every title links its paper here and on arXiv.

  1. Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation [arXiv] [episode]
  2. Dispersion-managed octave soliton microcombs in heterostructured microresonators [arXiv]
  3. Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes [arXiv]
  4. CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning [arXiv] [episode]
  5. GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping with Vision Foundation Models [arXiv] [episode]
  6. Femtosecond Engineering of PolyMethylPentene(PMP) Nonlinearity via NA, Spin/orbital angular momentum (OAM), and In-Situ SC Diagnostics [arXiv]
  7. Walk-on-Spheres Monte Carlo and deep neural network approximations of elliptic PDEs with drift and killing [arXiv]
  8. ICM Out! Better Tournament Strategy from Computed Continuations, vs. Solvers and LLMs [arXiv]
  9. Avalon-ToM-Bench: Evaluating Fine-Grained Theory of Mind via Asymmetric Game Mechanics [arXiv]
  10. Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models [arXiv] [episode]
  11. Matryoshka Language Model Suites [arXiv]
  12. SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring [arXiv]
  13. Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation [arXiv]
  14. Multi-Agent AI Safety as an Institutional Design Problem [arXiv]
  15. SHE: Trajectory-driven Safety Harness Evolution for LLM Agents [arXiv]
  16. Multimodal Model Diffing for Feature Discovery and Control [arXiv]
  17. FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivity [arXiv]
  18. Toward a Dynamical Taxonomy of Insomnia: A Multiaxial Framework for Sleep-State Transitions and Architectural Failure [arXiv]
  19. Funnel-like protein energy landscapes emerge from functional evolution under thermal fluctuations [arXiv]
  20. Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling [arXiv]
  21. Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA [arXiv]
  22. GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis [arXiv]
  23. Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning [arXiv]
  24. High-speed volumetric amplitude-spectrum dynamic optical coherence tomography by neural network with multi-burst scanning [arXiv]
  25. CPDA: Class-Conditional Path Distribution Alignment for Unsupervised Time-Series Domain Adaptation [arXiv]
  26. Entropic Partial Optimal Transport and Partial Gromov--Wasserstein Distance between Gaussian Mixtures [arXiv]
  27. Deep Learning based Detection of Fishing Vessels and Fishing Monitoring using Nightlight Images [arXiv]
  28. LITEWAY: LIghtweight HAR via Temporal Efficient highWAY [arXiv] [episode]
  29. Learning to Modulate, Not to Cycle: Soft Actor---Critic Recovers Inverter-Style Heat-Pump Control [arXiv]
  30. ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents [arXiv]
  31. Hierarchical rank-evolving representation for physics-informed neural networks [arXiv]
  32. One Adapter Pair per Model: A Universal Activation Interface for Language Models [arXiv]
  33. STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework [arXiv]
  34. Carnot: Interpretable, Interactive, and Optimized Execution of Deep Research Queries [arXiv]
  35. VERDI:Verified Contradictions for Continual World-Model Optimization [arXiv]
  36. TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability [arXiv]
  37. Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents [arXiv]
  38. Training-Free Universal Approximation by Prompting Random Transformers [arXiv]
  39. From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation [arXiv]
  40. MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection [arXiv]
  41. In-situ integrated nonlocal Huygens metasurfaces enable robust vortex beams from multimode fibers [arXiv]
  42. Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks [arXiv]
  43. A fully integrated dispersion-managed femtosecond mode-locked laser [arXiv]
  44. DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation [arXiv]
  45. Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching [arXiv]
  46. A globally and superlinearly convergent QO-free method for nonlinear optimization on Riemannian manifolds [arXiv]
  47. Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness [arXiv]
  48. Towards Expert-level Medical AI for Real-time Video Consultations [arXiv]
  49. Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains [arXiv]
  50. BDH-CQ: In-Context Learning with Recurrent Latent Reasoning [arXiv]
  51. Consilience for Verifier-Free Test-Time Scaling [arXiv]
  52. From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch [arXiv]
  53. Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions [arXiv]
  54. Evolutionary Curriculum Learning Improves Biological Sequence Modeling [arXiv]
  55. A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning [arXiv]
  56. 108 ps coincidence time resolution through optimized scintillators, photodetectors, readout electronics, and DOI-based timing correction in orthogonally stacked detector configurations [arXiv]
  57. Wien-Filter Hamiltonian and Transfer Matrix [arXiv]
  58. Q-Steer: Action-Value Guidance for Molecular Policy Optimization [arXiv]
  59. Persistent Manifold Learning of Protein Properties [arXiv]
  60. Multi-modal transformer for signal classification in nanopore blockade experiments [arXiv]

Listen

Everything the estate published on 2026-08-11, in the player. Playing from this page is how the edition learns whether anyone did.