Modelpublic

zhanglx/TWN-4B

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes

Model Card

TWN-4B

The 4B version of Think When Needed (TWN), a framework for adaptive reasoning-driven multimodal embeddings. TWN introduces a dual-LoRA architecture on top of Qwen3-VL-4B-Instruct with a learned routing gate that adaptively activates chain-of-thought reasoning.

Weight Structure

TWN-4B/
  reasoning/                 # LoRA adapter for CoT generation
    adapter_config.json
    adapter_model.safetensors
  embedding/                 # LoRA adapter for embedding extraction
    adapter_config.json
    adapter_model.safetensors
  gate_mlp.pt                # Routing gate MLP weights
  queries.pt                 # Learnable query embeddings

Citation

bibtex

@article{zhang2026thinkneeded,
      title={Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture},
      author={Longxiang Zhang and Weilong Dai and Guanghao Zhang and Hao Jiang and Pipei Huang},
      year={2026},
      eprint={2605.14448},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2605.14448},
}