Related papers: FORGE: Forming Semantic Identifiers for Generative…
We present FORGE, a method for sim-to-real transfer of force-aware manipulation policies in the presence of significant pose uncertainty. During simulation-based policy learning, FORGE combines a force threshold mechanism with a dynamics…
Implementing Retrieval-Augmented Generation (RAG) systems is inherently complex, requiring deep understanding of data, use cases, and intricate design decisions. Additionally, evaluating these systems presents significant challenges,…
Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generation over a unified token space comprising language tokens and itemic identifiers, where each item…
Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a…
Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline, first…
Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-model approaches typically treat this task as prompt-conditioned sequence generation.…
Retrieval-Augmented Generation (RAG) is a well-established and rapidly evolving field within AI that enhances the outputs of large language models by integrating relevant information retrieved from external knowledge sources. While industry…
Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated…
Combinatorial optimization problems are ubiquitous in science and engineering. Still, learning-based approaches to accelerate combinatorial optimization often require solving a large number of difficult instances to collect training data,…
We introduce SAGE; a Generative LLM for inferring attribute values for products across world-wide e-Commerce catalogs. We introduce a novel formulation of the attribute-value prediction problem as a Seq2Seq summarization task, across…
Aiming to reduce the computational cost of Softmax in massive label space of Face Recognition (FR) benchmarks, recent studies estimate the output using a subset of identities. Although promising, the association between the computation cost…
Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems…
Generative Retrieval (GR) offers a promising paradigm for recommendation through next-token prediction (NTP). However, scaling it to large-scale industrial systems introduces three challenges: (i) within a single request, the identical…
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation Download PDF Neal Gregory Lawton, Alfy Samuel, Anoop Kumar, Daben Liu Published: 20 Aug 2025, Retrieval augmented generation (RAG) is a popular…
Embedding-based retrieval serves as a dominant approach to candidate item matching for industrial recommender systems. With the success of generative AI, generative retrieval has recently emerged as a new retrieval paradigm for…
Requirements engineering in Industry 4.0 faces critical challenges with heterogeneous, unstructured documentation spanning technical specifications, supplier lists, and compliance standards. While retrieval-augmented generation (RAG) shows…
Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, conflicting between internal and external retrieved contexts, or…
The Information Retrieval in Software Engineering (IRSE) track aims to develop solutions for automated evaluation of code comments in a machine learning framework based on human and large language model generated labels. In this track,…
Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…
Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the…