We analyzed a dataset of repeat founders who have gone through Y Combinator’s cohorts and found some very interesting insights. The dataset, shared with us directly from YC, consisted of 454 repeat founders through the...
Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a...
Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate. While existing programmatic benchmarks offer...
Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is identified only up to equivalence, and every...
A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis. The learner sees a uniform shuffle of...
From natural-language query interfaces to automated report generation, data analysis tools need a description of the data: the real-world entities it contains, which columns function as measures or identifiers, and how...
Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor benchmarks may contain inconsistent tasks, simplistic scenarios, or...
Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize...
Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an...
The use of e-commerce mobile applications is expanding in Nigeria, creating both opportunities and risks, including fraud and reduced user control over digital technologies, raising concerns about digital sovereignty....
Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$. Writing $L$ for the binary risk and $L^*=\min_{h\in H}L(h)$, we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\...
Deciding which of two agents is stronger means playing games until skill outweighs luck, and every game costs money, model inference, or expert time. Since the number of games needed is unknown, fixed-budget evaluations...
We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation...
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task...
This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through the DetoxAI image recognition system for bias detection and concept...
Multilingual reasoning transfer is crucial for extending reasoning capabilities of large language models (LLMs) beyond high-resource languages. On-policy self-distillation (OPSD) and its variants have emerged as a...
LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to locate the earliest error step in a...
Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficiently evaluated. National standard documents, such as China GB/T...
White matter hyperintensities (WMH), bright regions on Fluid-attenuated Inversion Recovery (FLAIR) scans are associated with cerebrovascular pathology and neurodegeneration. FLAIR is usually acquired with thick slices...
Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranking, generative reward models have not...
Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents...