AI Wiki — Knowledge Base

Doc + Jev => DocJev @llama_index 团队最新开源文档分类与拆分工具 DocJev，给它一个 PDF/DOCX/PPTX 和一份用自然语言写的类别规则，它可以告诉你这份文档属于哪个类别，或者把一份“文件包”按边界拆成若干子文档并给出各自页码范围。开源…

Doc + Jev => DocJev @llama_index 团队最新开源文档分类与拆分工具 DocJev，给它一个 PDF/DOCX/PPTX 和一份用自然语言写的类别规则，它可以告诉你这份文档属于哪个类别，或者把一份“文件包”按边界拆成若干子文档并给出各自页码范围。开源地址：https://github.com/jerryjliu/docjev 核心架构：解析与决策分离 1. 解析层（O

agentsjerry-liu--x

20 Sept 2026

Search: “framework”

The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators

TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching

Toward individual-level calibration in affect recognition with perceptual adjustment queries

Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge

VLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models

Can conference review infrastructure keep up with the increasing volume of NON-SLOP research due to agentic tools? [D]

M1 Max 32GB, trying to run Qwen 3.8 27B at decent speeds and context

🚨 OBAMA ON AI: 'If we are thinking about AI just in terms of how do we cure cancer or get better energy, you can do that without having age…

Training a Neural Network on AMD MI50s Using Vulkan: Proof of ConceptOr: Why I Stopped Listening and Just Did It

Affective Shared Autonomy: Temporal Affect Dynamics and Subjective Evaluation in Bimanual Teleoperation Tasks

AgriScope: Pixel-Grounded Multimodal Understanding for Agricultural Images

AI-Driven Real-Time Relay Optimisation in Smart Urban NR-V2X Networks via Learning-to-Optimise Graph Neural Networks

AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention

ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization

Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents

Benchmarking LLM Compliance with China AI Generated Content Regulations

Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding

BinoGen: Scaling egocentric binocular data for embodied visual perception and learning

Building a Neural Network from Scratch: Implementation, Evaluation, and Optimization

Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment

Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code

Compositional Reasoning in Language Models under Reinforcement Learning Post-Training

CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement Learning

Deep Learning-Based Classification of Cognitive and Resting States Using Electroencephalography Signals

E-AVI: Evidence-Grounded Multimodal Assessment for Automated Video Interviews

Evaluating Communicative Success in Machine-Translated Conversation

FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models

Integrated Guidance and Control of a Mother-Child UAV-UGV System for Cooperative Missions

JointMatch: A Unified Heterogeneous Graph Neural Solver for Large-Scale Ride-Sharing Matching

Kinematics-Grounded Agentic AI for Robotic Additive Manufacturing Process Planning

LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents

Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations

Learning Slope-Adaptive Whole-Body Locomotion for Humanoid Robots in Roofing Construction

MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving

MiX: Micro-Inverted-Scaling for End-to-End Low-Bit Vision-Language Model Acceleration

Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning

Null importance: Disentangling relevance for interpretable machine learning

On the Inherent Privacy Amplification of Missing Data

Optimal Transport Metric Learning for Feature Alignment in Partially Supervised Segmentation

Physics-Informed Hemodynamic Modeling for Data-Free Prediction and Sparse-Data Assimilation

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates

Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure

RAUL: Reference-Assisted Ureteroscopy Localization for Skill Assessment

Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network

RotateIt! Fast and Reliable Single-Arm Garment Unfolding via Online-Adaptive Dynamic Rotation

SAGE-Yoga: Multi-Cue Learning for Yoga Pose Classification and Joint-Level Correction