AI Wiki — Knowledge Base

是我见过OCR效果最好的一个了，人眼都难以分辨的，它能处理的十分准确，而且速度非常的快。llamaindex 真不愧是文档解析界的一哥啊。

是我见过OCR效果最好的一个了，人眼都难以分辨的，它能处理的十分准确，而且速度非常的快。llamaindex 真不愧是文档解析界的一哥啊。 The best 'raw' frontier model for document parsing is gemini 3 flash, but the issue is that since then the flash models have gotte

model-releasesjerry-liu--x

9 Aug 2026

Search: “models”

Foundation Model-Enabled Efficient Data Sampling (FEEDS): A label-efficient training strategy for pan-cancer, multi-tracer PET/CT datasets

INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators

MazzikaAI: A knowledge-based performance-to-prompt compiler for real-time Arabic maqam accompaniment with a streaming text-to-music model

Physics-informed Diffusion Generative Model for Time-Series Data Synthesis in Dynamic Systems

The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM

Toward the Cognitive--Physical Limits of Embodied Intelligence through a World-Model-Centric Autonomous Racing Agent

You chose the best model. Why is your agent still failing?

A foundation model of numerical intelligence with cross-disciplinary generalization

An invertible generative model for forward and inverse problems

Diminishing Returns of Intelligence: The Non-Linear Relationship Between LLM Scale and User Perception in Short-Duration Open-Ended Social Human-Robot Interactions

DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology

Emotion in an active inference model of human driving

MaxModShift: Model Privacy via Designed Shifts

Multilingual Agent-Based World Modeling for Social Science

One Model to Magnify Them All: Efficient Scale-Invariant Histopathology via Conditional Normalization and Continuous Magnification Training

Toward Mask Annotation-Free Surgical Instrument Segmentation from Endoscopic Images Using Text-Prompted Segment Anything Model 3 (SAM3)

Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model

In-depth look at OpenAI's model training, dangerous decisions, and cluelessness before the HuggingFace hack; despite delaying Astra, OpenAI still doesn't get it (Zvi Mowshowitz/Don't Worry About the Vase)

是我见过OCR效果最好的一个了，人眼都难以分辨的，它能处理的十分准确，而且速度非常的快。llamaindex 真不愧是文档解析界的一哥啊。

Now we have a timeline of the OpenAI accidental attack against Hugging Face

An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

Clinician input steers AI toward accurate and harmful recommendations

DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model

Uncertainty-Aware World Model for Aerial Image-Goal Navigation

AMA: MiniMax H3 Team — Ask us anything about our open video generation model, training, and future plans

Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations

FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized audio together, with up to 20-second clip…

Koopman-Based Nonlinear Identification and Model Predictive Control of a Turbofan Engine

LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content

The death of SLMs?

Can Training Logs Make Model Comparisons More Precise?

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse

Cura 1T: Specialized Model for Agentic Healthcare

Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement

Scaling agentic AI: How UiPath built its high-performance GPU platform on AI Hypercomputer

Development and Validation of a Dynamic Kidney Failure Prediction Model based on Deep Learning: A Real-World Study with External Validation

Douyin Multimodal Embedding Model Technical Report

Isotonic Bradley-Terry Model for Paired Comparison Data

VARPose: Flexible 2D Pose Densification via Visual Autoregressive Modeling for Enhanced 3D Lifting

ActionParty: Multi-Subject Action Binding in Generative Video Games

An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks

Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review

China&#8217;s Alibaba takes another swipe at America’s AI supremacy

The Morphological Core of Dungan: A Two-Dialect Finite-State Model and a Multi-Genre Evaluation

Encrypted Clouds?

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

AuricularWorld: Hierarchical Action-Guided World Modeling for Fine-Grained Auricular Structure Segmentation from CT Scans

China’s Alibaba takes another swipe at America’s AI supremacy