Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs
Hamed Damirchi, Ignacio Meza De la Jara, Damith Ranasinghe +2
As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practica…
cs.LG2025
Decomposing Task Vectors for Refined Model Editing
Hamed Damirchi, Ehsan Abbasnejad, Zhen Zhang +1
Large pre-trained models have transformed machine learning, yet adapting these models effectively to exhibit precise, concept-specific behaviors remains a significant challenge. Ta…
cs.LG2025
The Quest for Winning Tickets in Low-Rank Adapters
Hamed Damirchi, Cristian Rodriguez-Opazo, Ehsan Abbasnejad +2
The Lottery Ticket Hypothesis (LTH) suggests that over-parameterized neural networks contain sparse subnetworks ("winning tickets") capable of matching full model performance when…