Related papers: MetaSynth: Multi-Agent Metadata Generation from Im…

We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes - over 50 times larger than the prior real dataset DL3DV -…

Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive volume of retrieved content, the possible dispersion of its…

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

We introduce Latent Meaning Cells, a deep latent variable model which learns contextualized representations of words by combining local lexical context and metadata. Metadata can refer to granular context, such as section type, or to more…

This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from…

Web-scale ranking systems at Meta serving billions of users is complex. Improving ranking models is essential but engineering heavy. Automated Machine Learning (AutoML) can release engineers from labor intensive work of tuning ranking…

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…

Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending on which few-shot examples are included, yet selection must remain cheap enough to run…

Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide…

Generating synthetic text addresses the challenge of data availability in privacy-sensitive domains such as healthcare. This study explores the applicability of synthetic data in real-world medical settings. We introduce MedSyn, a novel…

High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design. Existing works contribute heavy human efforts to manually labeling…

Question Generation (QG) is a task of Natural Language Processing (NLP) that aims at automatically generating questions from text. Many applications can benefit from automatically generated questions, but often it is necessary to curate…

Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content is noisy and unreliable, and many real-world tasks require…

Improved search quality enhances users' satisfaction, which directly impacts sales growth of an E-Commerce (E-Com) platform. Traditional Learning to Rank (LTR) algorithms require relevance judgments on products. In E-Com, getting such…

Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The…

With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications. However, many of them remain difficult to diagnose what aspects…

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

Click-through rate (CTR) estimation is a fundamental task in personalized advertising and recommender systems and it's important for ranking models to effectively capture complex high-order features.Inspired by the success of ELMO and Bert…

When developing new large language models (LLMs), a key step is evaluating their final performance, often by computing the win-rate against a reference model based on external feedback. Human feedback is the gold standard, particularly for…

Recommendation systems power engagement and monetization across feeds, ads, and short-video platforms, but translating the latest advances in Large Language Models into Recommendation Systems (RecSys) gains remains rare, particularly in…