2. MiniMax Sparse Attention 🔑 Keywords: MiniMax Sparse Attention, Ultra-long-context capability, Blockwise sparsity, GPU execution, Grouped Query Attention 💡 Category: Natural Language Processing 🌟 Research Objective: - The study aims to enable efficient processing of ultra-long contexts in large language models while maintaining performance and achieving significant speedups. 🛠️ Research Methods: - Introduction of MiniMax Sparse Attention (MSA), employing blockwise sparsity based on Grouped Query Attention, with an optimized GPU execution path via exp-free Top-k selection and KV-outer sparse attention. 💬 Research Conclusions: - The implementation of MSA achieves major reductions in per-token attention computation and significant wall-clock speedups for both prefill and decoding, maintaining performance on par with existing methods. 👉 Paper link: huggingface.co/papers/2606.1…

13. EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge 🔑 Keywords: EvoBrowseComp, contamination-free, temporal freshness, automated synthesis, reasoning graphs 💡 Category: Natural Language Processing 🌟 Research Objective: - The paper introduces EvoBrowseComp, an evolving benchmark designed to provide contamination-free evaluation of search agents, maintaining temporal freshness and preventing parametric memorization. 🛠️ Research Methods: - A collaborative framework involving three agents: a QA synthesis agent, an information filtering agent, and a high-level guidance agent generates complex questions via live-web traversal to ensure up-to-date content and block reasoning shortcuts. 💬 Research Conclusions: - EvoBrowseComp demonstrates a high difficulty level, requiring broad horizontal search, and establishes a scalable paradigm for continuously updatable benchmarks aligned with evolving world knowledge and agent capabilities. 👉 Paper link: huggingface.co/papers/2606.1…

📚 AI Native Daily Paper Digest - 2026-06-12🌟 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. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments 2. MiniMax Sparse Attention 3. Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? 4. MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling 5. LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories 6. N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization 7. Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning 8. Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback 9. MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold 10. TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search 11. Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models 12. SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling 13. EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge

0. Xiaomi releases and open-sources MiMo Code V0.1.0, an AI programming assistant with persistent memory system 1. MNN inference engine adds Arm SME2 support achieving 80% speedup for Qwen3-VL on-device deployment 2. Tencent Hunyuan open-sources HPC-Ops inference operator library with major system-level upgrade

📚 AI Native Daily Paper Digest - 2026-06-11🌟 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. Redesign Mixture-of-Experts Routers with Manifold Power Iteration 2. Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application 3. Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions 4. Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning 5. World Pilot: Steering Vision-Language-Action Models with World-Action Priors 6. ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics 7. InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning 8. TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning 9. ICA Lens: Interpreting Language Models Without Training Another Dictionary 10. Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models 11. World Model Self-Distillation: Training World Models to Solve General Tasks 12. ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction 13. i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models

13. i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models 🔑 Keywords: text-to-image diffusion, diffusion models, open models, i1 model 💡 Category: Generative Models 🌟 Research Objective: - This study aims to investigate the design choices in text-to-image diffusion models and develop i1, a new 3B-parameter model that maintains transparency and matches leading performance. 🛠️ Research Methods: - Conducted over 300 controlled experiments consuming 700K TPU v6e hours to analyze and identify effective modeling and data design choices for text-to-image diffusion models. 💬 Research Conclusions: - The i1 model is created utilizing publicly available datasets and achieves competitive results across five representative benchmarks, outperforming existing fully open models by an average of 29.5 percentage points. The study offers the i1 model checkpoints, training and inference code, and a data processing pipeline to facilitate open research. 👉 Paper link: huggingface.co/papers/2606.1…