hiyenwong/ai_collection - Page 9

dual-hypothesis-reasoning-framework-llm-guardrails

Skill derived from arXiv:2607.17575 - A Dual-Hypothesis Reasoning Framework for LLM Guardrails

harness-engineering-llm-driven-gpu-kernel-generation

Skill derived from arXiv:2607.17979 - Harness Engineering for LLM-Driven GPU Kernel Generation

selectinfer-selective-neuron-loading-computation-device-llms

Skill derived from arXiv:2607.18081 - SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs

stress-testing-concept-erasure-large-language-model-agents

Skill derived from arXiv:2607.17890 - Stress Testing Concept Erasure with Large Language Model Agents

environment-free-synthetic-data-generation-api-calling-agents

Skill derived from arXiv:2607.16900 - Environment-free Synthetic Data Generation for API-Calling Agents

oracle-gap-signal-fidelity-fixed-pool-diagnostic-test-time-collaboration

Skill derived from arXiv:2607.17531 - Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration

progressive-disclosure-you-need-long-context-agents

Skill derived from arXiv:2607.17598 - Is Progressive Disclosure All You Need for Long-Context Agents?

training-continuous-chain-thought-models-tale-two-regimes

Skill derived from arXiv:2607.16972 - Training Continuous Chain of Thought Models: A Tale of Two Regimes

quantum-financial-time-series

Quantum LSTM and Quantum Reservoir Computing for financial time series forecasting - hybrid quantum-classical architectures for market prediction.

quantum-finance

Quantum computing applications in finance: portfolio optimization, option pricing, risk management, financial simulations, and quantum economics using quantum algorithms (QAOA, quantum annealing, quantum Monte Carlo, amplitude estimation, entangled neural…

agent-skills-large-language

Agent Skills for Large Language Models

agent0

Agent0

agentic-evolution-path-evolving-llms

Agentic Evolution is the Path to Evolving LLMs

agentic-hives-self-organizing-multi

Agentic Hives - Self-Organizing Multi-Agent Systems

autoskill-experience-driven-skill-self

AutoSkill - Experience-Driven Skill Self-Evolution

caster-multi-agent-orchestration-routing

CASTER - Multi-Agent Orchestration Routing

live-evo-online-evolution-agentic

Live-Evo - Online Evolution of Agentic Memory

se-search-self-evolving-search

SE-Search - Self-Evolving Search Agent

self-improving-llm-agents-test

Self-Improving LLM Agents at Test-Time

serp-self-evolutionary-replanning

SERP - Self-Evolutionary RePlanning

memex-rl

Memex(RL)

memrl

MemRL

nngpt-rethinking-automl-llms

NNGPT - Rethinking AutoML with LLMs

learn-like-humans-meta-cognitive

Learn Like Humans - Meta-cognitive Reflection

audited-skill-graph-self-improvement

Audited Skill-Graph Self-Improvement

darwin-g-del-machine

Darwin Gödel Machine

e-spl

E-SPL

ice-strategy

ICE Strategy

remember-me-refine-me-procedural

Remember Me, Refine Me - Procedural Memory

reveal

ReVeal

agentic-evolution-path-to-evolving-llms

Agentic Evolution is the Path to Evolving LLMs: Proposes that LLM evolution should be driven by agentic interactions rather than passive fine-tuning. Models evolve through interaction with environments, tools, and other agents, developing capabilities via…

e-spl-evolutionary-system-prompt-learning

E-SPL (Evolutionary System Prompt Learning): Evolutionary system prompt learning for self-evolving LLMs. Uses reinforcement learning to optimize system prompts, enabling LLMs to improve themselves through interaction without external supervision. Activation:…

training-free-relaxed-speculative-deoding

A Practical Investigation of Training-free Relaxed Speculative Decoding

bus-brain-inspired-self-reflection-vlm

BUS (Brain-Inspired Unsupervised Self-Reflection) methodology for training Vision-Language Models to self-correct reasoning without labeled supervision. Implements unsupervised reflection via brain-inspired feedback loops, enabling VLMs to review and improve…

dynamic-neural-manifolds-neuromorphic-control

Dynamic neural manifolds for flexible closed-loop control on neuromorphic hardware. Implements a ring attractor spiking network on the SpiNNaker 2 chip where sensory-modulated heterogeneous inhibition, multiplicative gain, and transient currents drive rapid…

intrinsic-noise-consolidation-doob

Doob-Barrier-Conditioned Diffusion methodology for turning analog neuromorphic device noise into a continual-learning consolidation resource. Casts per-synapse consolidation as a Doob h-transform: condition each weight's stochastic dynamics on never crossing…

stst-jepa-eeg-foundation

STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture for EEG self-supervised learning. Combines latent-prediction objective with auxiliary signal-reconstruction term under spatiotemporal block masks. Pretrained on 47,703 EEG…

a-multi-agent-system-for-autonomous-fine-tuning-fr

A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study - Clinical notes contain many of the signs and symptoms that bring patients to care, yet this information rarely reaches structured fields.…

evidence-grounded-verified-agentic-reasoning-a-pat

Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs - Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from…

internet-of-agentic-things-networked-ai-agents-for

Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration - The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physic...