arXiv Computer Vision
FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
1d ago
Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment
arXiv:2609.02573v1 Announce Type: new Abstract: Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. I...
arXiv AI
Aug 11
TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
arXiv:2601. 03100v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) typically rely on a single late-layer feature from a frozen vision encoder, leaving the encoder's rich hierarchy of visual cues under-utilized.
arXiv AI
Aug 11
Vision-Language Grounding as Bidirectional Concept Correspondence
arXiv:2608. 07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region.
Hugging Face Trending Papers
Jul 27
MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning
Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.
arXiv Computer Vision
2d ago
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
arXiv:2607.04801v2 Announce Type: replace Abstract: Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve e...
Hugging Face Trending Papers
Jul 6
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independently trained concept adapters in a shared weight space (via federated averaging, gradient fusion, or orthogonality constraints) suffer from identity confusion and style bleeding and require joint retraining.