GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation
arXiv:2605.20188v1 Announce Type: new
Abstract: Recommending safe and effective medication combinations from electronic health records (EHRs) is a core clinical AI problem, yet it remains difficult because patient trajectories are long, noisy, and clinically heterogeneous. Existing methods typicall...
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
arXiv:2605.20234v1 Announce Type: new
Abstract: Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for single-task inference, meaning that predicting several target values within a context requires repeat...
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
arXiv:2605.20235v1 Announce Type: new
Abstract: Diffusion models generate high-dimensional data with remarkable quality, yet how their training efficiently learns the score function, bypassing the curse of dimensionality when data is supported on low-dimensional manifolds, remains theoretically une...
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
arXiv:2605.20189v1 Announce Type: new
Abstract: Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation. Traditional fine-tu...
Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration
arXiv:2605.20190v1 Announce Type: new
Abstract: Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optim...
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
arXiv:2605.20425v1 Announce Type: new
Abstract: Designing multi-agent workflows is especially difficult in open-ended scientific settings where tasks lack curated training sets, reliable scalar evaluation metrics, and standardized interfaces between existing tools and agents. We propose AgentCo-op,...
New Approach to Scaling Laws Could Change How AI Models Are Trained
Leveraging statistical concepts from measurement science and education, AI researchers have greatly reduced the computational demand of predicting how the largest of large language models will scale up in the future. It could save millions of dollars in training costs.
AI Weekly Issue #494: SpaceX wants $80 billion. OpenAI wants a trillion.
For nine years the AI boom has been a private bet, priced by a small circle of venture funds and sovereign wealth in rounds most people could never touch. This week it started going public. SpaceX filed an $80 billion IPO prospectus on Wednesday, the largest in history, with a chatbot company and $6...
Meet Turbovec: A Rust Vector Index with Python Bindings, and Built on Google’s TurboQuant Algorithm
turbovec brings Google Research's TurboQuant algorithm to vector search, offering 16x compression and zero codebook training for RAG pipelines.
The post Meet Turbovec: A Rust Vector Index with Python Bindings, and Built on Google’s TurboQuant Algorithm appeared first on MarkTechPost.
OpenAI claims it solved an 80-year-old math problem — for real this time
OpenAI claims its reasoning model disproved a geometry conjecture unsolved since 1946 — and this time, the mathematicians who exposed its last embarrassing claim are backing it up.
Optimizing AI Agent Planning with Operations Research and Data Science
AI agents can quickly become expensive without a clear strategy for planning, skill coverage, and budgets. This article shows how to use operations research and data science to optimize AI agent cost and resource allocation. You will learn how to frame common agent problems—skill coverage, project a...
OpenAI barrels toward IPO that may happen in September
A day after Elon Musk lost his lawsuit that threatened OpenAI's structure, leadership, and finances, OpenAI is reportedly back to prepping for its IPO.