4 citations · 11 across the 19 of their papers we have counts for
20 papers
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Haoqiang Kang, Yinpeng Chen, Luyang Liu +5
Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a…
Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models
Xilun Chen, Shao-Chuan Wang, Baykal Cakici +6
Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these…
Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in recommendation systems
Baolei Li, Yiping Yuan, Yilin Zheng +6
Large-scale recommendation systems face "Memory Wall" bottlenecks due to massive, dense embedding tables. While generative retrieval uses discrete tokens for IDs, high-dimensional…
LLM-Based User Personas for Recommendations at Scale
Haoting Wang, Haokai Lu, Zheyun Feng +14
Large Language Models (LLMs) offer unprecedented potential for enhancing recommendation systems through their world knowledge and reasoning capabilities. However, existing approach…
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
Qingyun Liu, Bo Yan, Yang Liu +15
User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors. An emergi…
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
Neha Verma, Nikhil Mehta, Shao-Chuan Wang +7
Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetting of their general, languag…
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
Zhengyang Su, Isay Katsman, Yueqi Wang +10
Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a c…
Selecting User Histories to Generate LLM Users for Cold-Start Item Recommendation
Nachiket Subbaraman, Jaskinder Sarai, Aniruddh Nath +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning, generalization, and simulating human-like behavior across a wide range of tasks. These strength…
Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates
Changping Meng, Hongyi Ling, Jianling Wang +9
Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities. However, the dynamic nature of user interests and content po…
PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
Ruining He, Lukasz Heldt, Lichan Hong +20
Large Language Models (LLMs) pose a new paradigm of modeling and computation for information tasks. Recommendation systems are a critical application domain poised to benefit signi…
ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation
Chengyu Dong, Huan Gui, Noveen Sachdeva +6
Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of su…
Serendipitous Recommendation with Multimodal LLM
Haoting Wang, Jianling Wang, Hao Li +9
Conventional recommendation systems succeed in identifying relevant content but often fail to provide users with surprising or novel items. Multimodal Large Language Models (MLLMs)…
User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems
Jianling Wang, Yifan Liu, Yinghao Sun +11
Exploration, the act of broadening user experiences beyond their established preferences, is challenging in large-scale recommendation systems due to feedback loops and limited sig…
STAR: A Simple Training-free Approach for Recommendations using Large Language Models
Dong-Ho Lee, Adam Kraft, Long Jin +5
Recent progress in large language models (LLMs) offers promising new approaches for recommendation system tasks. While the current state-of-the-art methods rely on fine-tuning LLMs…
Leveraging LLM Reasoning Enhances Personalized Recommender Systems
Alicia Y. Tsai, Adam Kraft, Long Jin +7
Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While t…
Aligning Large Language Models with Recommendation Knowledge
Yuwei Cao, Nikhil Mehta, Xinyang Yi +5
Large language models (LLMs) have recently been used as backbones for recommender systems. However, their performance often lags behind conventional methods in standard tasks like…
How to Train Data-Efficient LLMs
Noveen Sachdeva, Benjamin Coleman, Wang-Cheng Kang +6
The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto…
Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts
Zichang Liu, Qingyun Liu, Yuening Li +6
Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality. For example, in our experimen…
LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views
Yuji Roh, Qingyun Liu, Huan Gui +8
Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various task…
Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems
Huan Gui, Ruoxi Wang, Ke Yin +5
Learning feature interaction is the critical backbone to building recommender systems. In web-scale applications, learning feature interaction is extremely challenging due to the s…