Create README.md

# BiPS — Bi-directional Perceptual Shaping for Multimodal Reasoning

This model card describes **BiPS (Bi-directional Perceptual Shaping)**, a **training-time** framework proposed in *“See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning”* [CVPR 2026].

- Paper: https://arxiv.org/abs/2512.22120
- Code: https://github.com/zss02/BiPS

## What is BiPS?

Many VLMs fail on multimodal reasoning because they **look at the wrong visual evidence** (especially for charts, thin lines, intersections, and small regions). BiPS improves **question-conditioned visual grounding** by turning “where-to-look” supervision into training signals—**without requiring extra tools at inference time**.

## Key idea

BiPS trains a VLM with two complementary view transformations:

- **Evidence-Preserving View**: keep only the visual evidence needed to answer, reduce distractions.
→ enforce **consistency** between predictions from the original image and the preserved view.

- **Evidence-Ablated View**: remove the key evidence so the image no longer supports the answer.
→ enforce **separation** so the model cannot rely on shortcuts.

These constraints are typically implemented with **KL-based objectives** and can be integrated into **GRPO** training.

## Why it matters

- Better **fine-grained evidence alignment**
- Less “guessing” from language priors
- **No additional inference overhead** (views are used only during training)

## How to use

BiPS is mainly a **training recipe**. To apply it:
1. Follow the official repo to set up dependencies and scripts.
2. Train your base VLM with BiPS-generated **preserve/ablate** views.
3. Use the resulting checkpoint as a standard VLM at inference time (no extra steps).

## Citation
If you find this work helpful in your research, please cite our paper:

```bibtex
@article {zhang2025bips,
title={See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning},
author={Zhang, Shuoshuo and Zhang, Yizhen and Fu, Jingjing and Song, Lei and Bian, Jiang and Yang, Yujiu and Wang, Rui},
journal={arXiv preprint arXiv:2512.22120},
year={2025}
}
```

README.md

@@ -0,0 +1,14 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+tags:
+  - multimodal
+  - vision-language
+  - vlm
+  - vqa
+  - chart-understanding
+  - reinforcement-learning
+  - grpo
+library_name: transformers
+---