Related papers: R Melts Brains -- An IR for First-Class Environmen…
Optimizing compilers are essential for the efficient and correct execution of software across various scientific fields. Domain-specific languages (DSL) typically use higher level intermediate representations (IR) in their compiler…
Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…
Effectful programs interact in ways that go beyond simple input-output, making compositional reasoning challenging. Existing work has shown that when such programs are ``separate'', i.e., when programs do not interfere with each other, it…
Reinforcement learning (RL) has proven highly effective in eliciting the reasoning capabilities of large language models (LLMs). Inspired by this success, recent studies have explored applying similar techniques to vision-language models…
I describe an approach to compiling common idioms in R code directly to native machine code and illustrate it with several examples. Not only can this yield significant performance gains, but it allows us to use new approaches to computing…
Programming languages are expected to support programmer's effort to structure program code. The ML module system, object systems and mixins are good examples of language constructs promoting modular programming. Among the three, mixins can…
In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned…
A key feature of inductive logic programming (ILP) is its ability to learn first-order programs, which are intrinsically more expressive than propositional programs. In this paper, we introduce techniques to learn higher-order programs.…
Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting evidence, rather than semantic similarity. Motivated by the emergent reasoning abilities…
The R programming language is widely used in large-scale data analyses. It contains especially rich built-in support for dealing with vectors, arrays, and matrices. These operations feature prominently in the applications that form R's…
Optimization modeling and solving are fundamental to the application of Operations Research (OR) in real-world decision making, yet the process of translating natural language problem descriptions into formal models and solver code remains…
Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges,…
Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of…
Integer programming (IP) is a general optimization framework widely applicable to a variety of unstructured and structured problems arising in, e.g., scheduling, production planning, and graph optimization. As IP models many provably hard…
Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…
User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods…
Real world programming languages crucially depend on the availability of computational effects to achieve programming convenience and expressive power as well as program efficiency. Logical frameworks rely on predicates, or dependent types,…
This paper is an introduction to Lambdix, a lazy Lisp interpreter implemented at the Research Laboratory of Paris XI University (Laboratoire de Recherche en Informatique, Orsay). Lambdix was devised in the course of an investigation into…
Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…
While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effectiveness in accurately adhering to instructions remains…