Related papers: Task Expansion and Cross Refinement for Open-World…

World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and offline evaluation. In text-based environments, world models are typically evaluated and…

Text-Based Person Search (TBPS) aims to retrieve pedestrian images from large galleries using natural language descriptions. This task, essential for public safety applications, is hindered by cross-modal discrepancies and ambiguous user…

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…

Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions. Besides flexibility and accuracy, a key benefit of…

Language model alignment (or, reinforcement learning) techniques that leverage active exploration -- deliberately encouraging the model to produce diverse, informative responses -- offer the promise of super-human capabilities. However,…

Performative prediction is a framework accounting for the shift in the data distribution induced by the prediction of a model deployed in the real world. Ensuring rapid convergence to a stable solution where the data distribution remains…

Most current sampling algorithms for high-dimensional distributions are based on MCMC techniques and are approximate in the sense that they are valid only asymptotically. Rejection sampling, on the other hand, produces valid samples, but is…

Virtual Cell Modeling (VCM) requires models that not only predict perturbation responses, but also support targeted revision when predictions fail. Current LLM-assisted modeling workflows face a refinement-routing problem: prediction…

Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks to expand LLM…

Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. Recent LLM-based refinements improve…

Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such…

We classify and re-examine some of the current approaches to improve the performance-computes trade-off of language models, including (1) non-causal models (such as masked language models), (2) extension of batch length with efficient…

Query expansion aims to mitigate the mismatch between the language used in a query and in a document. However, query expansion methods can suffer from introducing non-relevant information when expanding the query. To bridge this gap,…

Conformal Prediction methods have finite-sample distribution-free marginal coverage guarantees. However, they generally do not offer conditional coverage guarantees, which can be important for high-stakes decisions. In this paper, we…

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while…

Text-to-SQL systems have become crucial for translating natural language into SQL queries in various industries, enabling non-technical users to perform complex data operations. The need for accurate evaluation methods has increased as…

Efficient exploration remains a central challenge in reinforcement learning (RL), particularly in sparse-reward environments. We introduce Optimistic World Models (OWMs), a principled and scalable framework for optimistic exploration that…

The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in advance by domain experts and assumed to capture all necessary…

We consider single and multiobjective simulation-based optimization problems. Simulation-based optimization has traditionally used both model-based and search-based methods, often in isolation. Model-based methods include trust region…

Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…