5arXiv cs.CL (Computation and Language)·
AlphaOracle: Deep learning framework for oracle bone script decipherment using human-workflow-inspired pipeline
AlphaOracle is a multi-stage deep learning framework for deciphering oracle bone script (OBS), modeled on expert philological workflows including morphological analysis, contextual retrieval, and classical source validation. Evaluated on 86 domain specialists, it reduced analysis time by 64% and achieved high usefulness ratings, with readings strongly agreeing with expert interpretations. The system also proposes a concrete resolution for the character 'Lao' with implications for Shang dynasty administrative history. The work demonstrates that AI systems aligned with domain expert workflows can advance progress on long-standing undeciphered script problems.
Related guides (1)
Related events (8)
Multi-expert routing system achieves near-oracle OCR accuracy on low-resource Manchu historical scripts
A new arXiv preprint presents a multi-expert OCR system for historical Manchu manuscripts, routing pages by visual style (regular script, running script, chancery hand) using a lightweight image classifier. The router achieves 99.3% page-level domain accuracy and matches a domain-label oracle, with character error rates of 0.30%, 1.57%, and 4.83% across three script styles. The approach reuses fine-tuning checkpoints as domain specialists, avoiding the need to train dedicated experts for each domain. The work addresses low-resource OCR for endangered historical scripts with a reproducible evaluation protocol.
XALPHA: Memory-driven AI agent for end-to-end quantitative trading alpha discovery
Researchers introduce XAlpha, an LLM-based agentic system for continuous hypothesis-to-code alpha factor discovery in quantitative finance. The system uses a multi-source memory architecture with three specialized 'brain' modules (Macro, Micro, Cross) to close the loop from financial hypothesis generation through code implementation, validation, and iterative feedback. Unlike prior LLM-based quant frameworks that automate isolated steps, XAlpha operates as an end-to-end research agent that accumulates and reuses discovery knowledge across cycles. Experiments on the CSI300 index show improved alpha discovery performance over representative baselines.
AllenAI olmocr: toolkit for linearizing PDFs for LLM datasets and training
olmocr is an open-source Python toolkit from AllenAI for converting PDFs into linearized text suitable for LLM training datasets. The repository has accumulated 18,143 stars with 295 added today, indicating sustained and active community interest. It addresses a practical bottleneck in data pipeline construction for training and fine-tuning language models on document-heavy corpora.
GLM-OCR: Fast and Accurate OCR System from zai-org
GLM-OCR is an open-source OCR project from zai-org built on the GLM model family, positioning itself as accurate, fast, and comprehensive. The repository has accumulated 6,787 GitHub stars with 82 added today, indicating notable community traction. It represents an application of large language/vision models to document understanding and text recognition tasks.
Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection
Loong is a long document translation agent that uses a 3E memory module (Essence-Exemplar-Entity) to store structured historical context, replacing passive full-context attention with RL-optimized adaptive context selection. The agent learns its context retrieval policy via reinforcement learning on self-sampled reasoning trajectories. Evaluations show average gains of up to 13.0 points across three metrics in English↔Chinese, German, and French translation directions, with strong generalization and robustness to noise in ultra-long documents.
AlphaEvolve: How our Gemini-powered coding agent is scaling impact across fields
DeepMind published a blog post detailing the real-world impact of AlphaEvolve, a Gemini-powered coding agent designed to discover and optimize algorithms. The post covers applications spanning business operations, infrastructure, and scientific research. AlphaEvolve represents a deployment of LLM-driven evolutionary algorithm search at scale across multiple domains.
Structural test oracle problem in LLM-as-judge synthetic corpora: silent failures and a validation protocol
A new arXiv paper reports a case where a shared decoding-budget parameter silently truncated hallucinated answers in a multilingual LLM-as-judge evaluation corpus, producing a spurious 32-point cross-lingual accuracy collapse that replicated robustly across sample sizes but was entirely artifactual. The authors argue this failure mode is structural to LLM-generated negative examples, which lack any mechanical item-level integrity check (the 'test oracle problem'), unlike corpora built from deterministic perturbation of gold answers. A second real bias (Markdown formatting preference) was simultaneously distorted in magnitude and sign by the same fault, illustrating that aggregate statistics cannot distinguish fabricated from distorted effects. The paper closes with a validation protocol for analysts working with oracle-less multilingual LLM-as-judge corpora.
OFASys: Multitask Multimodal Learning Framework from Alibaba/Qwen
Alibaba's Qwen team released OFASys, an open-source framework designed to simplify multimodal multitask learning, building on their earlier OFA unified pretrained model. The system aims to reduce engineering friction in setting up multi-task, multi-modal training pipelines, including data batching and training stability. It is positioned as infrastructure for building generalist AI models with minimal code overhead.