A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
[Submitted on 6 Jun 2025 (v1), last revised 5 Mar 2026 (this version, v3)] Authors:Eugenie Lai, Gerardo Vitagliano, Ziyu Zhang, Om Chabra, Sivaprasad Sudhir, Anna Zeng, Anton A. Zabreyko, Chenning…
Low-input deep learning platform for citrullinated peptide identification, autoantigen discovery and rheumatoid arthritis treatment stratification
Kacen, A. et al. Post-translational modifications reshape the antigenic landscape of the MHC I immunopeptidome in tumors. Nat. Biotechnol. 41, 239–251 (2023).Article CAS PubMed Google Scholar Kelly, S. D., Allas,…
How everyday foam reveals the secret logic of artificial intelligence
Foams appear in everyday life as soap suds, shaving cream, whipped toppings and food emulsions like mayonnaise. For many years, scientists believed foams behaved much like glass, with their tiny…
Golden Retriever genes linked to anxiety, aggression, and intelligence in humans
Researchers at the University of Cambridge have uncovered new insights into the emotional lives of dogs, helping explain why some golden retrievers are more anxious, energetic, or aggressive than others.…
AI turns x-rays into time machines for arthritis care
A new artificial intelligence system developed by researchers at the University of Surrey can forecast what a patient's knee X-ray might look like one year in the future. This breakthrough…
A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
Large Language Models (LLMs) have rapidly evolved from text-only assistants into complex agentic systems capable of performing multi-step reasoning, calling external tools, retrieving memory, and executing code. With this evolution…
Accelerating Diffusion Models with an Open, Plug-and-Play Offering
Recent advances in large-scale diffusion models have revolutionized generative AI across multiple domains, from image synthesis to audio generation, 3D asset creation, molecular design, and beyond. These models have demonstrated…
Why You Should Stop Writing Loops in Pandas
: when I first started using Pandas, I wrote loops like this all the time: for i in range(len(df)): if df.loc > 1000: df.loc = "high" else: df.loc = "low"…
Near-term Improvements and Long-term Convergence
[Submitted on 18 Oct 2025 (v1), last revised 5 Mar 2026 (this version, v2)] View a PDF of the paper titled Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements…
[2602.23008] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
[Submitted on 26 Feb 2026 (v1), last revised 6 Mar 2026 (this version, v2)] View a PDF of the paper titled Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy…