MLINFO COLLECTION
Foundation models trained on longitudinal electronic health records (EHRs) can predict clinical diagnoses years in the future, making them a potential tool for disease screening. We developed TRACER…
Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for…
How effectively can vision-language-action (VLA) models learn diverse language-conditioned behaviors as training data scales? Investigating this question requires large and varied robot datasets,…
We introduce NEOPIC, a framework for learning the field operator in particle-based methods applied to kinetic plasma simulations. Its key novelty is a neural operator that acts directly on the…
Cross-modal scene and instance retrieval aims to retrieve a corresponding 3D environment or object given query 2D images, serving as a foundational mechanism for spatial reasoning in robotics and…
We study high-dimensional integration on bounded convex domains. Given a non-negative integrand $r$, the goal is to estimate $Z=\int_{D}r(x)\,\mathrm dx$ on $D\subset\mathbb R^d$.
Do research agents have taste, the judgment of which experiments are worth running before their outcomes are known? We give six frontier models seven recent NLP papers.
Sampling-based reachability estimates reachable sets from finitely many simulated trajectory endpoints. Existing guarantees often control missed probability mass or approximation error relative to…
Predictive models trained at well-resourced data-rich institutions often fail when deployed in new populations. Motivated by the goal of building clinical diagnosis and decision-making algorithms for…
Aerial imagery provides complementary spatial context for autonomous driving by exposing road structure beyond the immediate perception range of onboard sensors. Yet map construction from aerial…
We present PhysInsert, a framework for physically plausible reference-based object insertion that jointly adapts objects and their surrounding scenes. Existing methods often rely on masked inputs,…
Tool-use benchmarks often score agents by final task success, but terminal outcomes can obscure whether the intermediate tool-call trajectory was executable. We propose prefix executability as a…
Fine-grained manipulation requires a robot policy to follow instructions, remain robust to visual variations, and translate predicted actions into precise robot control. We present Demonstration…
In this article, we present socx, a GPU-accelerated solver for lifted convex reformulations of linear stochastic optimal control under chance constraints, implemented in JAX. We demonstrate that by…
We introduce Continuous-Action World Models (CoAWM), a framework for learning cross-embodiment spatiotemporal dynamics priors that support robot action generation across embodiments and execution…
We consider the problem of finite-sample identification of an unknown LTI system from a finite hypothesis class. In contrast to existing results that assume the hypothesis class contains the true…
Vision-Language-Action (VLA) models have demonstrated promising capabilities in robotic manipulation by integrating visual perception, language understanding, and action generation. Recent advances…
Unsupervised environment design (UED) methods such as PLR, ACCEL, SFL and PAIRED are compared mostly on 2D mazes, grid worlds and BipedalWalker, while terrain curricula for legged robots are…
We study high-dimensional nonparametric regression under multisource covariate shift, where $\mathrm J$ sources of training data share a common regression function but differ in their covariate…
As the effects of climate change become increasingly apparent, the demand for renewable energy sources such as wind power continues to grow. However, renewables' variable and intermittent nature…
Language models often need to maintain multiple contextual variables that evolve independently within a document. Prior work has identified structured representations of individual temporal or…
We present Vampire-Hammer, a hammer for the Lean interactive theorem prover that discharges goals using the Vampire automated theorem prover and reconstructs proofs checked by the Lean kernel.…
We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-level baselining} step that…
Bimanual dexterous manipulation requires continuous coordination of wrist motion, finger contact, and object motion. Human videos provide rich manipulation experience.