---
title: Logics-PPT-Qwen-3.6-35B-A3B-SFT
canonical_url: "https://www.modelscope.ai/models/Alibaba-DT/Logics-PPT-Qwen-3.6-35B-A3B-SFT"
md_url: "https://www.modelscope.ai/models/Alibaba-DT/Logics-PPT-Qwen-3.6-35B-A3B-SFT.md"
repository: Alibaba-DT/Logics-PPT-Qwen-3.6-35B-A3B-SFT
last_updated: 2026-09-21
license: apache-2.0
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - Qwen/Qwen3.6-35B-A3B
base_model_relation: finetune
parameters: 35.1B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 170
stars: 0
tags:
  - presentation-generation
  - html-generation
  - slide-generation
  - code-generation
  - supervised-fine-tuning
  - moe
  - agentic-post-training
  - multimodal-layout
  - openclaw
---

# Logics-PPT-Qwen-3.6-35B-A3B-SFT

> Logics-PPT-Qwen-3.6-35B-A3B-SFT - An open-source model by Alibaba-DT on ModelScope. Logics-PPT-Qwen3.6-35B-A3B-SFT

Alibaba-DT/Logics-PPT-Qwen-3.6-35B-A3B-SFT is a 35.1B-parameter machine learning model on ModelScope. licensed under apache-2.0. derived from Qwen/Qwen3.6-35B-A3B.

- **Repository**: Alibaba-DT/Logics-PPT-Qwen-3.6-35B-A3B-SFT
- **License**: apache-2.0
- **Parameters**: 35.1B
- **Base model**: Qwen/Qwen3.6-35B-A3B
- **Tags**: presentation-generation, html-generation, slide-generation, code-generation, supervised-fine-tuning, moe, agentic-post-training, multimodal-layout, openclaw
- **Downloads**: 170
- **Stars**: 0
- **Last updated**: 2026-09-21

Source: https://www.modelscope.ai/models/Alibaba-DT/Logics-PPT-Qwen-3.6-35B-A3B-SFT

---

# Logics-PPT-Qwen3.6-35B-A3B-SFT

> Model card for Logics-PPT-Qwen3.6-35B-A3B-SFT. The technical report is under review and a public link will be added when available.
Note: This model was previously named Logics-PPT-Qwen-3.6-35B-A3B-SFT and has been renamed to Logics-PPT-Qwen3.6-35B-A3B-SFT on 2026-09-20 for naming consistency.


## 📰 News

- **[2026.09.20]** Released **Logics-PPT-Qwen3.6-35B-A3B-SFT** under the Apache-2.0 license.
- This model is the supervised fine-tuning (SFT) checkpoint for the MoE presentation-generation backbone in our presentation-intelligence pipeline.
- The technical report is currently under review. A citation link will be added after public release.

## 🔎 Overview

**Logics-PPT-Qwen3.6-35B-A3B-SFT** is a presentation-generation model built on top of
**Qwen3.6-35B-A3B**, an MoE backbone, for **single-page HTML slide generation**.

The model is trained for **end-to-end presentation generation** through a slide-wise HTML
generation paradigm within the **OpenClaw** framework. In our study, Single-HTML is adopted
as the final generation setting because it offers stronger robustness and optimization efficiency
than multi-page HTML and Python-based generation.

This release corresponds to the **SFT stage** of our unified training pipeline for
presentation intelligence:

1. **Cross-validated data synthesis**
2. **Guided supervised fine-tuning**
3. **Reinforcement learning with verifiable rewards**

This checkpoint is the final **pre-RL SFT model** for the 35B-A3B MoE backbone.

### Why this model?

PPT generation is a long-horizon task that jointly requires:

- document understanding,
- information acquisition,
- content organization,
- layout planning,
- and visually coherent slide construction.

This model is designed to improve presentation generation beyond a generic base model through:

- **cross-validated synthetic task and rubric construction**
- **teacher-enhanced trajectory distillation**
- **mixed-teacher supervision**
- **lightweight filtering of low-quality trajectories**

The goal of this SFT stage is to substantially improve both:
- benchmark-level presentation quality, and
- basic slide aesthetics before RL refinement.

## 🧠 Training Recipe

### Stage 1: Cross-validated data synthesis

The paper constructs a synthetic PPT-generation training corpus through a five-stage pipeline:

- source profiling
- task construction
- rubric generation
- principle audit
- rubric tightening



### Stage 2: Guided SFT with mixed teachers

The model is trained from **Qwen3.6-35B-A3B** using supervised fine-tuning on distilled
presentation-generation trajectories.

Teacher models:

- **Qwen-3.8-Max**: strong general coding and agentic reasoning
- **GLM-5.2**: presentation-specialized teacher

Teacher guidance is strengthened through progressively richer prompts:

- **Base**
- **Pro**
- **Max**

Training corpora are combined under:
- **Single**
- **Mixed**
- **Mixed+Filter**

The released model corresponds to the **selected mixed+filter checkpoint** used as the
RL initialization for the MoE backbone.

Selected setting for this release:

- **Target backbone:** Qwen-3.6-35B-A3B
- **Training regime:** mixed + filter
- **Selected teacher composition:** `qwen + glm_pro (filter)`

## 📊 Experimental Results

### Main SFT results

Reported overall benchmark scores from the paper:

| Model | PresentBench | GDPVal (PPT subset) |
| --- | ---: | ---: |
| Qwen3.6-35B-A3B (base / no train) | 64.93 | 74.01 |
| **Logics-PPT-Qwen3.6-35B-A3B-SFT** | **74.28** | **78.17** |

Compared with the base model, this SFT checkpoint improves:

- **PresentBench:** **64.93 → 74.28** (**+9.35**)
- **GDPVal (PPT subset):** **74.01 → 78.17** (**+4.16**)

These results show that the SFT pipeline produces substantial gains on both the in-domain
benchmark and the external PPT evaluation subset.

### Aesthetic metric snapshot

The paper also reports rule-based aesthetic scores for the selected SFT checkpoint:

| Metric group | PresentBench | GDPVal (PPT subset) |
| --- | ---: | ---: |
| Aspect ratio | 0.99 | 0.88 |
| Whitespace | 0.89 | 0.73 |
| Element collision avoidance | 0.74 | 0.49 |
| Visual balance | 0.58 | 0.54 |
| Font readability | 0.95 | 0.80 |
| **Total** | **4.16** | **3.44** |

## 🎯 Intended Use

This model is intended for **research use** in:

- automatic presentation generation
- HTML-based slide generation
- multimodal layout generation
- long-horizon agentic generation
- supervised post-training for deck synthesis
- MoE backbones for structured generation

It is especially suitable for research on systems that:
- read source materials,
- plan a multi-slide presentation,
- generate one HTML file per slide,
- and render outputs for downstream evaluation or refinement.

## ⚠️ Limitations

- This is an **SFT checkpoint**, not the final RL-refined model.
- Although it significantly improves overall presentation quality, post-render visual issues may still remain,
  including:
  - excessive whitespace,
  - imperfect balance,
  - element overlap,
  - and other fine-grained layout defects.
- The model is optimized for **single-slide HTML generation** rather than native `.pptx` output.
- Real deployment still requires the broader agent and rendering stack used in the paper.
- Performance depends on task prompting, reference-material access, and rendering setup.

## 🚀 Quickstart

### Transformers: text-generation smoke test

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Logics-MLLM/Logics-PPT-Qwen3.6-35B-A3B-SFT"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

messages = [{
    "role": "user",
    "content": (
        "Create an 8-slide presentation as separate HTML slides for a technical topic. "
        "Use a consistent design system, clear hierarchy, and readable visual layout."
    ),
}]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    output = model.generate(
        **inputs,
        max_new_tokens=2048,
        do_sample=True,
        temperature=1.0,
        top_p=0.95,
        top_k=20,
    )

completion = output[0, inputs["input_ids"].shape[-1]:]
print(tokenizer.decode(completion, skip_special_tokens=True))
```


This is only a minimal text-generation smoke test.  
Actual presentation generation in our setup additionally uses:

- the OpenClaw-style agent framework,
- task instruction files and reference materials,
- browser rendering



## 📚 Citation

The technical report is currently under review.  
Citation information will be added after public release.

## 🙏 Acknowledgements

We thank the Qwen, GLM, OpenClaw, PresentBench, and GDPVal teams and the broader research communities working on agentic generation, presentation intelligence, and reinforcement learning for LLMs.

## License

The model weights are released under the Apache License 2.0.