--- title: Logics-PPT-Qwen3.6-35B-A3B-RL canonical_url: "https://www.modelscope.ai/models/Alibaba-DT/Logics-PPT-Qwen3.6-35B-A3B-RL" md_url: "https://www.modelscope.ai/models/Alibaba-DT/Logics-PPT-Qwen3.6-35B-A3B-RL.md" repository: Alibaba-DT/Logics-PPT-Qwen3.6-35B-A3B-RL last_updated: 2026-09-21 license: apache-2.0 model_type: - qwen3_5_moe architectures: - Qwen3_5MoeForConditionalGeneration base_model: - Logics-MLLM/Logics-PPT-Qwen3.6-35B-A3B-SFT base_model_relation: finetune parameters: 35.1B tensor_type: - BF16 library_name: - pytorch - transformer - safetensors frameworks: - pytorch downloads: 211 stars: 0 tags: - presentation-generation - html-generation - slide-generation - code-generation - reinforcement-learning - grpo - verifiable-rewards - moe - agentic-post-training - multimodal-layout - openclaw --- # Logics-PPT-Qwen3.6-35B-A3B-RL > Logics-PPT-Qwen3.6-35B-A3B-RL - An open-source model by Alibaba-DT on ModelScope. Logics-PPT-Qwen3.6-35B-A3B-RL Alibaba-DT/Logics-PPT-Qwen3.6-35B-A3B-RL is a 35.1B-parameter machine learning model on ModelScope. licensed under apache-2.0. derived from Logics-MLLM/Logics-PPT-Qwen3.6-35B-A3B-SFT. - **Repository**: Alibaba-DT/Logics-PPT-Qwen3.6-35B-A3B-RL - **License**: apache-2.0 - **Parameters**: 35.1B - **Base model**: Logics-MLLM/Logics-PPT-Qwen3.6-35B-A3B-SFT - **Tags**: presentation-generation, html-generation, slide-generation, code-generation, reinforcement-learning, grpo, verifiable-rewards, moe, agentic-post-training, multimodal-layout, openclaw - **Downloads**: 211 - **Stars**: 0 - **Last updated**: 2026-09-21 Source: https://www.modelscope.ai/models/Alibaba-DT/Logics-PPT-Qwen3.6-35B-A3B-RL --- # Logics-PPT-Qwen3.6-35B-A3B-RL > Model card for Logics-PPT-Qwen3.6-35B-A3B-RL. 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-RL 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-RL** under the Apache-2.0 license. - This model is the reinforcement-learning checkpoint for the 35B-A3B MoE presentation-generation backbone. - The technical report is currently under review. A citation link will be added after public release. ## 🔎 Overview **Logics-PPT-Qwen3.6-35B-A3B-RL** is a reinforcement-learning-refined presentation-generation model built on top of **Logics-PPT-Qwen3.6-35B-A3B-SFT**. The model targets **single-page HTML presentation generation** and is optimized with **GRPO-based reinforcement learning** using **verifiable post-render visual rewards**. Rather than using an opaque learned critic or VLM judge for training-time reward assignment, this model is refined using deterministic, rule-based reward functions computed on fully rendered slides. ### Verifiable aesthetic rewards The RL stage optimizes five visual dimensions: 1. **aspect-ratio compliance** 2. **whitespace adequacy** 3. **element-collision avoidance** 4. **visual balance** 5. **font readability** These rewards are computed after rendering, using a browser-based pipeline with **headless Chromium / Playwright** and semantic bounding-box extraction. This design is intended to make slide-aesthetic refinement: - transparent, - stable, - auditable, - and directly tied to rendered outputs. ## 🧠 Training Recipe ### Initialization The RL policy is initialized from the selected MoE SFT checkpoint: - **Logics-PPT-Qwen3.6-35B-A3B-SFT** The paper chooses RL initialization checkpoints by favoring strong in-domain performance while preserving out-of-domain generalization on the GDPVal PPT subset. ### RL data selection Two RL data-selection strategies are studied: - **task-hard** - **aesthetic-hard** These strategies expose the model to: - globally difficult presentation-generation tasks, and - backbone-specific visual failure modes after SFT. ### RL optimization details The paper trains the model with **GRPO** using long-horizon rollouts. Reported shared settings include: - 8 prompts per step - 8 rollouts per prompt - 64 rollouts per update - rollout temperature 1.0 - top-k = 50 - total sequence length 131,072 - per-turn response cap 8,192 tokens - up to 128 actions per trajectory - one RL epoch The study also compares runs: - **with KL anchor** - **without KL anchor** For the MoE backbone, the paper reports especially strong gains in visual-aesthetic metrics. ## 📊 Experimental Results ### Main benchmark results ### Verifiable aesthetic scores The strongest reported 35B-A3B RL variant reaches: | Metric group | PresentBench | GDPVal (PPT subset) | | --- | ---: | ---: | | Aspect ratio | 1.00 | 0.83 | | Whitespace | 0.87 | 0.78 | | Element collision avoidance | 0.85 | 0.75 | | Visual balance | 0.64 | 0.52 | | Font readability | 1.00 | 0.87 | | **Total** | **4.36** | **3.75** | These are the strongest overall reported aesthetic totals for the MoE backbone in the paper. ### Human evaluation note The paper additionally reports a blinded human evaluation comparing post-RL models against their pre-RL counterparts. For the MoE backbone, the post-RL model achieves: - **82.4%** win rate in **visual quality** - **71.8%** win rate in **overall quality** on the reported sample and annotation protocol. ## 🎯 Intended Use This model is intended for **research use** in: - reinforcement learning for presentation generation - verifiable reward design for slide aesthetics - post-render optimization of HTML slides - MoE-based long-horizon agentic generation - presentation-intelligence systems This checkpoint is especially useful for studies focused on: - visual refinement after SFT, - deterministic reward shaping, - and RL for structured multimodal outputs. ## ⚠️ Limitations - This model is optimized for **visual-aesthetic refinement**, not only for benchmark-level semantic score. - As discussed in the paper, content-quality reward modeling remains an open direction. - The model is optimized for **single-page HTML slide generation**, not native PowerPoint editing. - Real use still requires an external framework for prompting, tool invocation, rendering, and file handling. - Reported behavior depends on the exact rollout and rendering setup used in the study. ## 🚀 Quickstart ### Transformers: text-generation smoke test ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Logics-MLLM/Logics-PPT-Qwen3.6-35B-A3B-RL" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, dtype=torch.bfloat16, device_map="auto", ) model.eval() messages = [{ "role": "user", "content": ( "Generate a visually polished slide deck as separate HTML slides. " "Keep the canvas at 16:9, avoid overlap, maintain visual balance, " "use readable fonts, and reduce excessive whitespace." ), }] 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.