Story2Board: Training-Free Storyboards With Cinematic Consistency A new paper from researchers at Hebrew University, OriginAI , and Bar-Ilan University introduces Story2Board , a training-free framework for generating multi-panel storyboards that keep character...
PH-LLM Turns Wearable Data into Practical Sleep and Fitness Coaching Wearables now collect rich sleep and activity data, but most users still struggle to translate those numbers into helpful actions. A new study in Nature Medicine presents the Personal Health Lar... AI healthcare Artificial Intelligence Large Language Models
SmallThinker: Bringing Powerful Language Models to Local Devices Researchers from Shanghai Jiao Tong University’s Institute of Parallel and Distributed Systems, the School of Artificial Intelligence, and Zenergize AI introduced SmallThinker : a family of large lang... AI Models AI training reinforcement learning
Teaching AI to Teach: Sakana AI's New Approach to Training Reasoning Models Introduction: The High Cost of AI Reasoning Training large language models (LMs) to reason like humans is one of the biggest challenges in AI today. The current state-of-the-art method, reinforcement ...
Introducing LiveMCPBench: Evaluating Models on Large Tool Set Usage A new arXiv preprint, LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools , from the Chinese Academy of Sciences and UCAS, introduces a benchmark to test AI agents in realistic tool-rich environme... AI benchmarking AI tools Artificial Intelligence MCP MCP Server
SensorLM: Translating Wearable Sensor Data Into Meaningful Language What if your smartwatch not only monitored your heart rate, but also explained the reasons behind every spike and dip? This is what SensorLM brings to life, transforming streams of raw sensor data fro... activity recognition generative AI health tech multimodal learning natural language sensor data wearables
AI Powered CRISPR: The Next Generation of Gene Editing Tools Gene editing has relied on tools discovered in nature, but a new wave of innovation is changing how we create proteins by harnessing artificial intelligence. Scientists can now design custom CRISPR sy... artificial intelligence CRISPR gene editing genome engineering immunogenicity precision medicine protein design synthetic biology
Photoinduced Copper Catalysis For Chiral Synthesis Achieving the precise construction of chiral molecules is essential for progress in pharmaceuticals, materials science, and biochemistry. Recent research has introduced a groundbreaking approach: phot... asymmetric synthesis catalysis chiral molecules copper catalysis deracemization organic chemistry pharmaceuticals photochemistry
WhoFi: Person Identification with Wi-Fi Signals and Deep Learning In the pervasive landscape of modern surveillance and smart environments, the ability to accurately identify and track individuals across different locations and times, a task known as Person Re-Ident... biometrics CSI data deep learning person identification privacy transformers Wi-Fi sensing
TextArena Uses Competitive Gameplay to Advance AI As language models quickly catch up with and surpass traditional benchmarks, the need for more effective measurement tools becomes urgent. TextArena steps in as an innovative, open-source platf... agentic AI AI benchmarking LLM evaluation open source reinforcement learning soft skills text-based games TrueSkill
Test-Time Diffusion Deep Researcher: Ushering in a Human-Like AI Research Paradigm Introducing Test-Time Diffusion Deep Researcher (TTD-DR) framework an AI assistant that doesn't just gather information, but actively thinks, revises, and refines its work, much like a skilled human r... AI research draft refinement large language models multihop reasoning research automation retrieval augmentation self-evolution test-time diffusion
GenSeg For Medical Image Segmentation in Low-Data Environments Medical image semantic segmentation is a fundamental process in modern healthcare, crucial for applications such as diagnosing diseases, tracking disease progression, planning treatments, and assistin... AI segmentation data efficiency deep learning generative models healthcare AI medical imaging synthetic data