3 papers
cs.LG2026
The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes
Dylan Jayabahu
Linear probes that decode the truth from a language model's activations have been proposed as deception monitors, and a truth probe scoring below chance on a model trained to decei…
cs.LG2026
The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning
Dylan Jayabahu, Tinuade Adeleke
Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's own answer probability takes to…
cs.CV2024
Dataset for Real-World Human Action Detection Using FMCW mmWave Radar
Dylan jayabahu, Parthipan Siva
Human action detection using privacy-preserving mmWave radar sensors is studied for its applications in healthcare and home automation. Unlike existing research, limited to simulat…