Model Releases
Fitting Vision Adapters at Frontier Scales
arXiv:2610.05897v1 Announce Type: new Abstract: Training a small projector between a frozen vision encoder and language model is an established approach to multimodal learning. As the parameter count
arXiv:2610.05897v1 Announce Type: new Abstract: Training a small projector between a frozen vision encoder and language model is an established approach to multimodal learning. As the parameter count of language models scales dramatically, we revisit which vision capabilities this approach can add while keeping their pretrained weights fixed. Here we train a 50M parameter projector from the vision encoder of Kimi K2.6 to GLM 5.2 and 5.3, both models without native vision capabilities, and further present a reproducible recipe for training these adapters at scale. We study the following: (a) how vision capabilities of multimodal models scale as purely the language model side scales, and (b) what specific vision capabilities are able to be imbued into a pure language model at scale, and which ones remain limited. We evaluate on MMMU-Pro and BLINK, examining both overall performance and results on individual visual tasks.
Related
- CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection
- MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning
- Separating perception from reasoning in vision-language models: a model-free render ceiling for crystal structures
- Do Visual Grounding Decoders Need Feed-Forward Networks? A Controlled Study over Frozen Vision-Language Features
Source: arXiv cs.CV | 2026-10-06