---
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: peft
license: apache-2.0
language:
  - en
tags:
  - lora
  - multimodal
  - embedding
  - retrieval
  - chain-of-thought
  - qwen3-vl
pipeline_tag: feature-extraction
---

# TWN-8B

The 8B version of [Think When Needed (TWN)](https://github.com/winterfell00/Think-When-Needed), a framework for adaptive reasoning-driven multimodal embeddings. TWN introduces a dual-LoRA architecture on top of [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) with a learned routing gate that adaptively activates chain-of-thought reasoning.

## Weight Structure

```
TWN-8B/
  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},
}
```