Get started
Author

Yakov Pyotr Shkolnikov

Observed name: Shkolnikov, Yakov Pyotr
OpenAlex ID: A5128270676
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University) · 1
PDF
Composable Trust for Language Models: A proven boundary and a measured defense
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University) · 1
PDF
Artificial Id: Drive and Persistent Alignment in Agentic AI
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University)
PDF
Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University)
PDF
Learnable Pulse Accumulation for On-Device Speech Recognition: How Much Attention Do You Need?
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University)
PDF
Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University)
PDF
Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices
2026 · Shkolnikov, Yakov Pyotr · arXiv (Cornell University)
PDF
Works count: 7
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type