hiyenwong/ai_collection - 5ページ

arxiv-2607-21268-pai-econ-claude-a-gated-human-in-the-loop-multi-ag

pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory (arXiv: 2607.21268)

原文の言語: 英語

arxiv-2607-21273-the-dark-room-in-the-reward-channel-dense-predicti

The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- an (arXiv: 2607.21273)

原文の言語: 英語

arxiv-2607-21274-a-comparative-evaluation-of-embeddings-and-llms-in

A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset (arXiv: 2607.21274)

原文の言語: 英語

arxiv-2607-21291-adaptive-depth-sparse-framework-similarity-driven

Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs (arXiv: 2607.21291)

原文の言語: 英語

arxiv-2607-21292-an-llm-driven-workflow-for-automated-process-contr

An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Pro (arXiv: 2607.21292)

原文の言語: 英語

arxiv-2607-21302-expert-behavior-prior-reinforcement-learning

Expert Behavior Prior Reinforcement Learning (arXiv: 2607.21302)

原文の言語: 英語

arxiv-2607-21324-gradrag-cross-component-prompt-adaptation-for-coor

GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG (arXiv: 2607.21324)

原文の言語: 英語

arxiv-2607-21325-toward-cryptographically-verifiable-authorization

Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, p (arXiv: 2607.21325)

原文の言語: 英語

arxiv-2607-21327-from-static-bibliometrics-to-dynamic-knowledge-gra

From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Scie (arXiv: 2607.21327)

原文の言語: 英語

arxiv-2607-21345-regulating-autonomous-and-agentic-ai

Regulating autonomous and agentic AI (arXiv: 2607.21345)

原文の言語: 英語

arxiv-2607-21412-euclid-mcp-a-model-context-protocol-server-for-det

Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog (arXiv: 2607.21412)

原文の言語: 英語

arxiv-2607-21419-pats-policy-aware-training-scaffolding-for-agentic

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning (arXiv: 2607.21419)

原文の言語: 英語

arxiv-2607-21461-arex-towards-a-recursively-self-improving-agent-fo

AREX: Towards a Recursively Self-Improving Agent for Deep Research (arXiv: 2607.21461)

原文の言語: 英語

arxiv-2607-21482-agentic-coding-without-the-cloud-evaluating-open-w

Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data (arXiv: 2607.21482)

原文の言語: 英語

arxiv-2607-21488-compact-latent-coordination-for-autonomous-vehicle

Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections (arXiv: 2607.21488)

原文の言語: 英語

arxiv-2607-21495-toward-continuous-assurance-for-the-democratizatio

Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry (arXiv: 2607.21495)

原文の言語: 英語

arxiv-2607-21503-agentic-context-management-solving-agent-memory-an

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architec (arXiv: 2607.21503)

原文の言語: 英語

arxiv-2607-21518-same-dangerous-objective-opposite-advice-direct-ex

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation (arXiv: 2607.21518)

原文の言語: 英語

arxiv-2607-21522-gs-agent-creating-4d-physical-worlds-with-generati

GS-Agent: Creating 4D Physical Worlds With Generative Simulation (arXiv: 2607.21522)

原文の言語: 英語

arxiv-2607-21552-mirror-learning-from-the-other-view-for-multi-moda

MIRROR: Learning from the Other View for Multi-Modal Reasoning (arXiv: 2607.21552)

原文の言語: 英語

arxiv-2607-21557-openforgerl-train-harness-native-agents-in-any-env

OpenForgeRL: Train Harness-native Agents in Any Environment (arXiv: 2607.21557)

原文の言語: 英語

arxiv-search-fix

Workaround for arxiv-search SSL issues when using python httpx

原文の言語: 英語

evaluating-encoding-strategies-biological-neural-networks

Skill for understanding and applying the research from arXiv:2607.13644 "Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks"

原文の言語: 英語

h2sd-hybrid-hindsight-self-distillation

Hybrid Hindsight Self-Distillation for Reinforcement Learning with Verifiable Rewards

原文の言語: 英語

hybrid-neural-network-visual-tracking

Skill for implementing and understanding the theory-grounded hybrid neural network (HTNN) that integrates artificial neural networks (ANNs) with continuous attractor neural networks (CANNs) for stable visual object tracking, as proposed in arXiv:2606.22604.

原文の言語: 英語

model-agnostic-meta-learning-differentiable-mpc

Model-Agnostic Meta Learning (MAML) framework for Differentiable Model Predictive Control (MPC) to enable adaptive control strategies across varying scenarios. Combines meta-learning with differentiable MPC for real-time adaptability without extensive…

原文の言語: 英語

agentic-coding-and-persistent-returns-to-expertise

Agentic coding and persistent returns to expertise

原文の言語: 英語

arxiv-2607-17602-exploring-brain-networks

Exploring Brain Networks Using Noninvasive Electrophysiological Measurements: Methods and Applications

原文の言語: 英語

visual-semantic-decoding-ecog

End-to-end deep learning framework for decoding visual semantic categories from ECoG signals during video stimulus presentation.

原文の言語: 英語

eeg-based-lm-evaluation

Skill for evaluating language models using EEG signals to examine human-like next-word prediction behavior based on arXiv:2607.16549. Enables fine-grained analysis of cognitive plausibility of language models during reading comprehension tasks.

原文の言語: 英語

exploring-brain-networks-eeg-meg

Skill for exploring brain networks using noninvasive electrophysiological measurements (EEG/MEG) based on arXiv:2607.17602v1. Covers forward/inverse problems, source reconstruction, connectivity measures, and analysis pipelines.

原文の言語: 英語

snn-fmri-visual-decoding

Spiking Neural Networks for fMRI-Based Visual Semantic Decoding - methodology for using SNN-derived visual features as alternative targets for fMRI-based visual decoding, demonstrating stronger alignment with fMRI responses and improved visual semantic…

原文の言語: 英語

spectralot-brain-alignment

Fast Whole-Brain, Geometry-Aware Functional Alignment for Cross-Subject Decoding using Spectral Optimal Transport (SpectralOT) method for fMRI data analysis

原文の言語: 英語

spiking-neural-networks-fmri-visual-decoding

Methodology for using Spiking Neural Network (SNN)-derived visual features as targets for fMRI-based visual semantic decoding, showing superior alignment with brain activity compared to traditional ANN features.

原文の言語: 英語

stsbench-dorsal-stream-visual-cortex

STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex - Skill for understanding and applying the methods from arXiv:2607.15631

原文の言語: 英語

visual-cortex-diffusion-inference

Skill for understanding and applying the mechanistic model of perceptual inference in visual cortex equivalent to a minimal diffusion model (arXiv:2607.15693). Enables extraction of principles linking sparse coding, recurrent dynamics, and diffusion model…

原文の言語: 英語

visual-place-recognition-rate-encoded-snn-stdp

Skill for understanding and implementing the discrete tensor-native STDP-based SNN visual place recognition pipeline from arXiv:2607.13584v1. Use when working with spiking neural networks for visual place recognition, loop closure in SLAM, or neuromorphic…

原文の言語: 英語

rgflow-transformer-eeg

RG-Flow Transformer for encoding scale-free dynamics in scarce EEG data - uses renormalization-group inductive bias to improve interpretability and spectral exponent recovery from limited neural recordings

原文の言語: 英語

arxiv-safe-access

Best practices for safely accessing arXiv programmatically, avoiding common pitfalls with HTTP, SSL, and automated tools.

原文の言語: 英語

fast-whole-brain-spectralot-alignment

Functional alignment method for fMRI using SpectralOT to embed cortical geometry into Laplace-Beltrami eigenmodes for cross-subject decoding

原文の言語: 英語