Related papers: Declarative Experimentation in Information Retriev…
High-performance tensor programs are crucial to guarantee efficient execution of deep neural networks. However, obtaining performant tensor programs for different operators on various hardware platforms is notoriously challenging.…
Speech-based open-domain question answering (QA over a large corpus of text passages with spoken questions) has emerged as an important task due to the increasing number of users interacting with QA systems via speech interfaces. Passage…
Dense embedding models have become critical for modern information retrieval, particularly in RAG pipelines, but their performance often degrades when applied to specialized corpora outside their pre-training distribution. To address thi we…
While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling…
As the complexity of state-of-the-art deep learning models increases by the month, implementation, interpretation, and traceability become ever-more-burdensome challenges for AI practitioners around the world. Several AI frameworks have…
Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical…
Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools. However, models employing TIR often display suboptimal behaviors, such as insufficient or…
Generative information retrieval (IR) has experienced substantial growth across multiple research communities (e.g., information retrieval, computer vision, natural language processing, and machine learning), and has been highly visible in…
Modern information retrieval is transitioning from simple document filtering to complex, neuro-symbolic reasoning workflows. However, current retrieval architectures face a fundamental efficiency dilemma when handling the rigorous logical…
Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and…
Deep learning has enabled major advances in the fields of computer vision, natural language processing, and multimedia among many others. Developing a deep learning system is arduous and complex, as it involves constructing neural network…
Information Retrieval (IR) evaluation involves far more complexity than merely presenting performance measures in a table. Researchers often need to compare multiple models across various dimensions, such as the Precision-Recall trade-off…
Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. Retrieval-augmented large language…
Tool calling has become increasingly popular for Large Language Models (LLMs). However, for large tool sets, the resulting tokens would exceed the LLM's context window limit, making it impossible to include every tool. Hence, an external…
Despite of achieving great success in real-world applications, Deep Reinforcement Learning (DRL) is still suffering from three critical issues, i.e., data efficiency, lack of the interpretability and transferability. Recent research shows…
GPUs have been favored for training deep learning models due to their highly parallelized architecture. As a result, most studies on training optimization focus on GPUs. There is often a trade-off, however, between cost and efficiency when…
Deep Learning (DL) has been successfully applied to a wide range of application domains, including safety-critical ones. Several DL testing approaches have been recently proposed in the literature but none of them aims to assess how…
The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While existing trajectory level exploration methods improve the…
Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is…
Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…