Thursday, August 13, 2026

1. Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting
   T2arXiv AI/CL/LG（论文）

   A study shows that in financial time-series forecasting, activation calibration for post-training quantization (PTQ) has little effect at 8 bits but becomes the primary determinant of predictive performance at 4 bits. Based on S&P 500 cross-sectional volatility forecasting, covering 7 neural architectures, 8 walk-forward test years (2018-2025), and 560 trained models, default absolute-maximum calibration removes 11-62% of the full-precision mean information coefficient under static 4-bit quantization of weights and activations, while percentile calibration recovers 53-94% of this degradation. The preferred activation range varies across market periods, making activation calibration a first-class deployment decision for reliable 4-bit PTQ in financial forecasting.

2. Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagram Parsing and Understanding
   T2arXiv AI/CL/LG（论文）

   Diagram-MMU is a new multi-modal benchmark designed to assess MLLMs' ability to parse and understand scientific diagrams. It features 3.7K curated diagrams and 18.3K human-validated questions across six domains, covering three tasks: diagram-to-code parsing, diagram-to-code editing, and diagram question answering, each also evaluated under agentic settings. Evaluation of 12 MLLMs reveals that diagram-to-code tasks are more challenging than diagram question answering: models can reason well over diagrams but struggle to parse and edit them, highlighting the need to enhance diagram-to-code generation. Under agentic settings, most models improve parsing and editing but degrade on question answering, while Claude-4.6 Opus consistently improves across all three tasks. This benchmark provides a robust testbed for improving scientific diagram understanding in tools like OpenAI Prism and has implications for scientific writing and collaboration.

1. alchemy-utils 0.1a0: A SQLAlchemy-Backed Multi-Database Toolkit
   T2Simon Willison 博客（Atom）

   Simon Willison has released alchemy-utils 0.1a0, a database-agnostic Python library and CLI utility built on SQLAlchemy. Its core API mirrors sqlite-utils, including insert, upsert, create, and table introspection methods, but works across multiple database engines. The prototype was created with AI coding agents Codex and GPT-5.6 Sol Ultra in a remarkably short time—Willison described it as a 'shower project' that took very few follow-up prompts to reach an alpha release. It currently supports PostgreSQL, SQLite, and DuckDB, and includes a uvx-based CLI for tasks like listing rows from a Postgres table or importing CSV data into DuckDB. The project also demonstrates how AI agents can accelerate tool development, with performance optimizations cutting a DuckDB import from nearly an hour down to about 35 seconds.

—

—

—