1 citations · 1 across the 4 of their papers we have counts for
4 papers
Beyond the Beep: Scalable Collision Anticipation and Real-Time Explainability with BADAS-2.0
Roni Goldshmidt, Hamish Scott, Lorenzo Niccolini +1
We present BADAS-2.0, the second generation of our collision anticipation system, building on BADAS-1.0, which showed that fine-tuning V-JEPA2 on large-scale ego-centric dashcam da…
BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data
Roni Goldshmidt, Hamish Scott, Lorenzo Niccolini +3
Existing collision prediction methods often fail to distinguish between ego-vehicle threats and random accidents not involving the ego vehicle, leading to excessive false alerts in…
Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On
Roni Goldshmidt
Interpretability in Vision-Language Models (VLMs) is crucial for trust, debugging, and decision-making in high-stakes applications. We introduce PixelSHAP, a model-agnostic framewo…
TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation
Roni Goldshmidt, Miriam Horovicz
As large language models (LLMs) become increasingly prevalent in critical applications, the need for interpretable AI has grown. We introduce TokenSHAP, a novel method for interpre…