3 citations · 3 across the 3 of their papers we have counts for
3 papers
cs.LG2026
Steering Interference Reflects the Model's Defaults, Not the Behavior Directions
Srikanth Malla, Chiho Choi, Joon Hee Choi
Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activations, and adding that directio…
cs.LG2026
The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists
Srikanth Malla, Chiho Choi, Joon Hee Choi
Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023), fine-tuning attacks (Qi et al., 2024), and activation-sp…
cs.CV2019★ 3 cited
NEMO: Future Object Localization Using Noisy Ego Priors
Srikanth Malla, Isht Dwivedi, Behzad Dariush +1
Predicting the future trajectory of agents from visual observations is an important problem for realization of safe and effective navigation of autonomous systems in dynamic enviro…