30 citations · 30 across the 10 of their papers we have counts for
3 papers · 2 filters
AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors
Mohamed Eltahir, Fardows Adam, Duaa M. Tahir +6
When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modality, or on internal read-outs, which originate too early to r…
GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
Mohamed Eltahir, Lama Ayash, Ali Habibullah +2
Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mitigation is to first select a…
VideoAtlas: Navigating Long-Form Video in Logarithmic Compute
Mohamed Eltahir, Ali Habibullah, Yazan Alshoibi +3
Extending language models to video introduces two challenges: representation, where existing methods rely on lossy approximations, and long-context, where caption- or agent-based p…