AI Native Foundation

That's all for AI Native Today Paper Digest. Follow our account for the latest insights on AI Native, and join us at member.ainativefoundation.org. If you found this helpful, a like or repost on the first tweet of this thread would be greatly appreciated!

13. One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems 🔑 Keywords: Multi-Agent Framework, Narrative Pacing, Spatial Consistency, Production-Level Quality Control, 3D-Grounded First-Frame Generation 💡 Category: Generative Models 🌟 Research Objective: - To introduce a hierarchical multi-agent framework that efficiently generates short dramas from a single sentence by ensuring narrative pacing, spatial consistency, and quality control. 🛠️ Research Methods: - Implementing a multi-agent debate-based story generation module for narrative coherence. - A 3D-grounded first-frame generation mechanism to maintain spatial reference. - Multi-stage reviewer loops for error detection and targeted revision across production stages. 💬 Research Conclusions: - The proposed framework, "One Sentence, One Drama," successfully improves narrative quality, cross-clip consistency, and the overall viewing experience, outperforming existing production pipelines. 👉 Paper link: huggingface.co/papers/2605.22…

8. SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation 🔑 Keywords: SpaceDG, spatial reasoning, visual degradation, MLLMs, robust spatial intelligence 💡 Category: Multi-Modal Learning 🌟 Research Objective: - The study introduces the SpaceDG dataset and benchmark to evaluate and enhance the robustness of multimodal language models (MLLMs) in spatial reasoning under conditions of visual degradation. 🛠️ Research Methods: - Construction of the SpaceDG dataset using a degradation synthesis engine for realistic simulation of nine types of visual degradation in approximately 1 million QA pairs from indoor scenes. - Development of the SpaceDG-Bench with human-verified questions to evaluate the impact of visual degradations on spatial reasoning across multiple reasoning categories. 💬 Research Conclusions: - Findings reveal that existing MLLMs show significant performance gaps under visual degradations, exposing critical robustness issues. - Fine-tuning on the SpaceDG dataset improves model robustness to visual degradations, sometimes even surpassing human performance without performance drops on unaltered images. 👉 Paper link: huggingface.co/papers/2605.22…

7. Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving 🔑 Keywords: Sensor2Sensor, Autonomous Driving Systems, diffusion models, 4D Gaussian Splatting, multi-modal sensor suite 💡 Category: Robotics and Autonomous Systems 🌟 Research Objective: - The paper aims to create a high-fidelity, multi-modal sensor suite from in-the-wild dashcam videos to aid in the training and validation of Autonomous Driving Systems. 🛠️ Research Methods: - The proposed Sensor2Sensor uses 4D Gaussian Splatting for rendering and a diffusion architecture for generative conversion, addressing the lack of paired training data by converting real AV logs into dashcam-style videos. 💬 Research Conclusions: - Sensor2Sensor successfully transforms challenging internet and dashcam footage into realistic multi-modal data formats, expanding the available data sources for autonomous vehicle development. 👉 Paper link: huggingface.co/papers/2605.22…

📚 AI Native Daily Paper Digest - 2026-05-22🌟 Follow @AINativeF for the latest insights on AI Native. Covering AI research papers from Hugging Face, featured in the image. 💡 Stay updated with the latest research trends and dive deep into the future of AI! 🚀 #AI #HuggingFace #AIPaper #AINative #AINF — Appendix: Today's AI research papers — 1. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation 2. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards 3. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps 4. PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects 5. Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning 6. Forecasting Scientific Progress with Artificial Intelligence 7. Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving 8. SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation 9. Q-ARVD: Quantizing Autoregressive Video Diffusion Models 10. Unsupervised Process Reward Models 11. KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving 12. Swift Sampling: Selecting Temporal Surprises via Taylor Series 13. One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems

6. Forecasting Scientific Progress with Artificial Intelligence 🔑 Keywords: AI Systems, Scientific Forecasting, CUSP Benchmark, Uncertainty Estimation, Domain-dependent Limitations 💡 Category: AI Systems and Tools 🌟 Research Objective: - The study aims to evaluate AI's capability to predict scientific progress using a new framework, CUSP, in the context of domain-based systematic overconfidence and inconsistent performance. 🛠️ Research Methods: - Introduction of a temporally grounded evaluation framework, including CUSP, which analyzes feasibility assessment, mechanistic reasoning, generative solution design, and temporal prediction across multi-disciplinary scientific events. 💬 Research Conclusions: - Current AI models exhibit systemic limitations across domains, failing to reliably predict scientific advances and exhibiting overconfidence with strong response biases, highlighting the unreliability of AI systems as predictive tools for scientific progress. 👉 Paper link: huggingface.co/papers/2605.22…

5. Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning 🔑 Keywords: Reinforcement Learning, Spreadsheet Automation, Domain-Specific Benchmarks, Spreadsheet Gym, LLM-Based Interactions 💡 Category: Reinforcement Learning 🌟 Research Objective: - To enhance the performance of AI spreadsheet agents in realistic Excel environments through the development of the Spreadsheet-RL framework, allowing for improved handling of both general and domain-specific tasks. 🛠️ Research Methods: - Implementation of a reinforcement learning fine-tuning framework with an automated pipeline for scalable data collection from online forums and the introduction of a Domain-Spreadsheet benchmark dataset. - Developing a Spreadsheet Gym environment to expose Excel functionalities for multi-turn RL training within a Python sandbox. 💬 Research Conclusions: - Spreadsheet-RL significantly boosts AI agent effectiveness, nearly doubling the Pass@1 rates on spreadsheet task benchmarks, highlighting a strong potential for generalization and real-world applications in spreadsheet automation. 👉 Paper link: huggingface.co/papers/2605.22…

4. PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects 🔑 Keywords: 3D generation, geometry representation, simulation-ready, PhysX-Omni, Vision-Language Models 💡 Category: Generative Models 🌟 Research Objective: - PhysX-Omni is introduced as a unified framework to generate simulation-ready physical 3D assets across diverse asset categories, addressing limitations in existing methods. 🛠️ Research Methods: - Development of a novel geometry representation tailored for Vision-Language Models, which enhances generation performance without compression. - Construction of PhysXVerse, a comprehensive 3D dataset, and PhysX-Bench, an evaluation benchmark covering multiple attributes. 💬 Research Conclusions: - PhysX-Omni demonstrates strong performance in both generation and understanding capabilities, with significant potential for applications in simulation-ready scene generation and robotic policy learning. - The framework aids in advancing embodied AI and physics-based simulation applications. 👉 Paper link: huggingface.co/papers/2605.21…

3. Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps 🔑 Keywords: RTPurbo, Long-context inference, Full-attention LLMs, Intrinsic sparsity, Sparse attention 💡 Category: Natural Language Processing 🌟 Research Objective: - The study aims to leverage intrinsic sparsity in full-attention LLMs to enhance the efficiency of long-context inference with minimal training overhead, achieving significant speedups while maintaining near-lossless accuracy. 🛠️ Research Methods: - The approach is based on three key observations: a small subset of attention heads requires full long-context processing, long-range retrieval is managed by a low-dimensional subspace allowing efficient token retrieval, and dynamic top-p selection is more optimal than fixed top-k sparsification. RTPurbo retains the full KV cache for retrieval heads and uses a lightweight token indexer for sparse attention. 💬 Research Conclusions: - RTPurbo demonstrates that strong sparse inference can be achieved without expensive native sparse pretraining. It shows substantial efficiency gains, including up to a 9.36x speedup in prefill and a 2.01x speedup in decode, while preserving near-lossless accuracy in long-context benchmarks and reasoning tasks. 👉 Paper link: huggingface.co/papers/2605.16…

2. DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards 🔑 Keywords: Reinforcement Learning, Verifiable Rewards, Discriminative Token Credit Assignment, Token-Gradient Vectors, AI-Generated Summary 💡 Category: Reinforcement Learning 🌟 Research Objective: - To improve reinforcement learning from verifiable rewards by introducing a discriminative token credit assignment method. 🛠️ Research Methods: - Developed a perspective of RLVR updates as a linear discriminator over token-gradient vectors to determine token probability adjustments during learning. - Proposed DelTA method to enhance token-gradient direction distinction by adjusting token coefficients for more effective side-wise centroids. 💬 Research Conclusions: - DelTA significantly outperforms the previous baselines on mathematical benchmarks and demonstrates strong generalization abilities in various domains, including code generation and out-of-domain evaluations. 👉 Paper link: huggingface.co/papers/2605.21…

1. TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation 🔑 Keywords: TransitLM, Large Language Models, Transit Route Planning, GPS Coordinates, Data-Driven 💡 Category: Natural Language Processing 🌟 Research Objective: - The main objective is to enable end-to-end transit route planning using large language models trained on structured transit data, bypassing traditional map-based approaches. 🛠️ Research Methods: - Development and utilization of the TransitLM dataset, comprising over 13 million transit route planning records from four Chinese cities, with continual pre-training and benchmark data for evaluation tasks. 💬 Research Conclusions: - Experiments indicate that models trained on TransitLM can generate structurally valid routes with high accuracy, implicitly grounding arbitrary GPS coordinates to stations without explicit mapping, thus demonstrating the feasibility of map-free route generation from origin-destination information. 👉 Paper link: huggingface.co/papers/2605.22…

If you found this helpful, follow us @AINativeF for more insights. A like or share on the first tweet would mean a lot—thank you for your support!

Figma launches AI design agent directly inside the design canvas Figma launched an AI design agent that works directly inside Figma Design, helping users generate design layers, explore multiple directions, automate bulk edits, apply design systems, and act on feedback without switching tools. The agent can start from design layers, use components, libraries, tokens, variables, and team context, and support tasks such as updating typography, replacing copy and imagery, converting screens to dark mode, and organizing comments into next steps. It is rolling out gradually in beta via early-access requests, with no AI credit usage during beta and availability for Full seat users on Professional, Organization, and Enterprise plans. Read more: figma.com/blog/the-figma… @figma 🎥 Credit: @figma on X

🌟 Today’s Global AI Native Industry Insights include: 1. OpenAI releases Appshots feature for Codex on Mac, allowing Command-Command app window capture 2. xAI enables Grok and X Premium subscribers to access Grok Build model in OpenCode terminal coding environment 3. Figma launches AI design agent directly inside the design canvas 🔍 Dive into the in-depth insights in the thread below. Here’s what’s shaping the future of AI: 👇