ECCV 2025 talk: Analyzing internal representations of multimodal LLMs
abursuc · x · 2026-09-08
A talk at ECCV 2025: researcher quobbe presented "Analyzing Internal Representations of Multimodal LLMs," interpretability work examining the internal representations of multimodal large language models.
More from Research
- ECCV paper shows scene coordinate regression models leak training-scene geometry — ducha_aiki · 2026-09-08
- Physicist: Navier-Stokes is physically meaningless at scales with possible singularities — MilesCranmer · 2026-09-08
- Denny Zhou: Least-to-Most Prompting Was an Early Agent Harness, Hitting 99% on SCAN — denny_zhou · 2026-09-08
- ECCV 2026 Workshop on Privacy-Preserving Visual Localization Features Brachmann, Pollefeys Talks — ducha_aiki · 2026-09-08
- MBZUAI launches Abu Dhabi deep phenotyping study for disease prediction — thamar_solorio · 2026-09-08
- Boundary-aware self-distillation precisely tunes LLM safety refusal boundaries — MultiverseComputingCAI · 2026-09-08