AROMA: Adaptive Representation-Oriented Multimodal Actuation for Vision-Language Model Control
cs.LG, cs.CL, cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- CounterCount: Diagnosing Knowledge Bias in How Vision-Language Models Count Attributes
- Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
- HoloCount: A Holistic Visual Counting Benchmark for MLLMs
- The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs
- Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions
- CountQA: How Well Do MLLMs Count in the Wild?
- Steering Language Models With Activation Engineering
- Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
- Representation Engineering: A Top-Down Approach to AI Transparency
- GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis