Related papers: Certified Error Control of Candidate Set Pruning f…

Large-scale retrieval systems are often implemented as a cascading sequence of phases -- a first filtering step, in which a large set of candidate documents are extracted using a simple technique such as Boolean matching and/or static…

Current methods for pruning neural network weights iteratively apply magnitude-based pruning on the model weights and re-train the resulting model to recover lost accuracy. In this work, we show that such strategies do not allow for the…

Quality Estimation (QE) metrics are vital in machine translation for reference-free evaluation and increasingly serve as selection criteria in data filtering and candidate reranking. However, the prevalence and impact of length bias in QE…

Learned sparse retrieval (LSR) is a popular method for first-stage retrieval because it combines the semantic matching of language models with efficient CPU-friendly algorithms. Previous work aggregates blocks into "superblocks" to quickly…

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval…

Generate-then-rank is the dominant test-time scaling (TTS) paradigm for code generation, but scaling accuracy by sampling and executing more candidates makes comprehensive verification a major computational bottleneck. This creates an…

We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized network. Our algorithm uses a small batch of input data…

Conducting pairwise comparisons is a widely used approach in curating human perceptual preference data. Typically raters are instructed to make their choices according to a specific set of rules that address certain dimensions of image…

Model pruning is an effective approach for compressing large language models (LLMs). However, this process often leads to significant degradation of model capabilities. While post-training techniques such as instruction tuning are commonly…

Automated resume screening systems are now a central part of hiring at scale, yet there is growing evidence that rigid screening logic can exclude qualified candidates before human review. In prior work, we introduced the concept of…

In many real-world settings, the critical class is rare and a missed detection carries a disproportionately high cost. For example, tumors are rare and a false negative diagnosis could have severe consequences on treatment outcomes;…

In response to the rising interest in large multimodal models, we introduce Cross-Attention Token Pruning (CATP), a precision-focused token pruning method. Our approach leverages cross-attention layers in multimodal models, exemplified by…

Modern computational models in supervised machine learning are often highly parameterized universal approximators. As such, the value of the parameters is unimportant, and only the out of sample performance is considered. On the other hand…

Most machine learning classifiers are designed to output posterior probabilities for the classes given the input sample. These probabilities may be used to make the categorical decision on the class of the sample; provided as input to a…

We study online aggregation of the predictions of experts, and first show new second-order regret bounds in the standard setting, which are obtained via a version of the Prod algorithm (and also a version of the polynomially weighted…

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept…

This paper presents a comprehensive study on resume classification to reduce the time and labor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates. A total of 6,492…

Estimating the ratio of two probability densities from finitely many samples, is a central task in machine learning and statistics. In this work, we show that a large class of kernel methods for density ratio estimation suffers from error…

In cancer biomarker development, a key objective is to evaluate whether a new biomarker, when combined with an established one, improves early cancer detection compared to using the established biomarker alone. Incremental value is often…