Latest papers
We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and…
Accurate option prices do not imply accurate recovery of the latent risk-neutral density. We study this distinction with two complementary benchmarks. A controlled benchmark exposes simulator-truth densities for latent evaluation, while a…
LLM inference at scale faces a memory wall. The KV cache demands tens of terabytes at hundreds of gigabytes per second, yet no current memory tier delivers both at once. Characterization across multi-generation GPU systems with various…
The debris disk orbiting the M star AU Microscopii has a series of large-scale clumps that move away from the star at high velocities above the mid-plane on the southeast side. Two more bright features lie on the northwest side of the disk,…
We study the Sachdev-Ye-Kitaev (SYK) Hamiltonian $H_{\operatorname{SYK}}$ on $n$ Majorana modes with $k$-body interactions, and prove that $\mathbb{E}\|H_{\operatorname{SYK}}\|_{\operatorname{op}} = (1 - o(1))\cdot\sqrt{2n}/k$ for…
We show that nonadaptive single-qubit Pauli measurements suffice to test whether an unknown $n$-qubit state $\rho$ is $\varepsilon$-close to or $O(\varepsilon)$-far from an ideal target state $|\psi\rangle$, for all but a $2^{-\Omega(n)}$…
We present Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. We achieve an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. In addition to its increased…
Question-answer (QA) pairs are widely used in knowledge base construction, question-answering systems, and the post-training of large language models (LLMs). However, important knowledge in long documents is often distributed across…
Demonstrating a practical quantum advantage remains a central goal in quantum information science. While quantum computational supremacy is still technologically demanding, communication complexity offers a promising route to showcase…
Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice…
Conversational AI is increasingly positioned as a teammate rather than a tool, yet we know little about how its presence reshapes communication among the humans on the team. We examined sociocognitive communication dynamics in team…
State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for training retrieval models and study how English supervision transfers to multilingual…
Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents. Most current ad-hoc teamwork (AHT) approaches assume that agents will collaborate on a single, fixed task and that the partner's capabilities,…
It is known that cooperative systems, and more generally systems monotone with respect to cones, behave under appropriate irreducibility conditions like one-dimensional systems, as evidenced by results such as Hirsch's generic convergence…
We investigate the cosmological imprints of massive fields during inflation through primordial non-Gaussianity (PNG). When these fields are sufficiently light, they produce a signal in galaxy clustering, $\propto f_{\rm…
The superradiant instability of rotating black holes can generate a significant overdensity of bosonic matter around them, together forming a gravitational atom. This mechanism allows one to probe a large part of the parameter space of…
Spin is the hidden engine behind the zoo of MacWilliams transforms in weight enumerator theories - not only for qubits and qudits, but even for classical codes. From nothing more than a split into trivial and nontrivial errors, we…
Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall. In e-commerce marketplaces and particularly grocery, this paradigm is limiting, as user satisfaction and…
Quantum query is a basic subroutine in many quantum algorithms, and Quantum Random Access Memory (QRAM) provides a natural way to realize such coherent query access. In delegated settings, however, a standard QRAM query interface can expose…
Jacobs comprehension categories subsume a large class of categorical models of type dependency, supporting also the description of morphisms between types. We study the relationship between comprehension categories and a particular…