Self-Saliency: aligning VLM attention with the image regions they describe
orlitany · x · 2026-10-13
In a new paper, Uri Berger and colleagues (with Gal Chechik) ask whether vision-language models actually look at the image regions they describe. They propose Self-Saliency, a method for aligning a VLM's visual attention with its reasoning text to probe and improve grounding.
More from Research
- DOE puts $159M into Genesis projects, expanding OSPREY agent that runs particle accelerators — omnivaughn · 2026-10-14
- Real2Sim gets easy with coding models, but sim-to-real physics and contact solvers lag — jonstephens85 · 2026-10-14
- MIT CSAIL's InstructMesh makes genAI 3D models you can actually 3D print — MIT_CSAIL · 2026-10-14
- Swing Choreo launches with a self-built motion benchmark: 61/100 vs 38 for the next best — andrew_n_carr · 2026-10-13
- No public benchmark for motion generation, so Swing built one: Choreo scores 61 vs 38 — andrew_n_carr · 2026-10-13
- Swing shows compute-quality frontier for motion models: gains came from data selection, not scale — andrew_n_carr · 2026-10-13