5 citations · 9 across the 13 of their papers we have counts for
14 papers
Deformations of Holomorphic -Contact Structures
Dan Popovici
We investigate the notion of holomorphic -contact structure, that we introduced recently in the scalar case with H. Kasuya and L. Ugarte and in the line-bundle case with K. Brod…
What Makes a Good Semantic ID for Generative Recommendation? A Reproducibility Study
Yufei Chen, Junchen Fu, Jujia Zhao +2
Generative recommendation has emerged as an active research direction, where items are commonly represented by semantic IDs (SIDs): discrete codes generated token by token. Despite…
Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG
Shuyu Guo, Shuo Zhang, Zhaochun Ren
Retrieval-Augmented Generation (RAG) improves knowledge-intensive generation by conditioning language models on retrieved documents, but processing these documents becomes increasi…
ReportLogic: Evaluating Logical Quality in Deep Research Reports
Jujia Zhao, Zhaoxin Huan, Zihan Wang +4
Users increasingly rely on Large Language Models (LLMs) for Deep Research, using them to synthesize diverse sources into structured reports that support understanding and action. I…
Differentiable Semantic ID for Generative Recommendation
Junchen Fu, Xuri Ge, Alexandros Karatzoglou +4
Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content. Most existing methods treat SIDs as…
Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace Tuning
Jujia Zhao, Zihan Wang, Shuaiqun Pan +2
Search and recommendation (S&R) are core to online platforms, addressing explicit intent through queries and modeling implicit intent from behaviors, respectively. Their complement…
ReleaseEval: A Benchmark for Evaluating Language Models in Automated Release Note Generation
Qianru Meng, Zhaochun Ren, Joost Visser
Automated release note generation addresses the challenge of documenting frequent software updates, where manual efforts are time-consuming and prone to human error. Although recen…
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Jinyuan Fang, Yanwen Peng, Xi Zhang +12
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manua…
DeltaLLM: Delta-Key Sparse Attention for Edge LLMs
Jiawen Qi, Chang Gao, Jiayu Liu +2
On-device LLM inference is increasingly important for edge platforms but remains challenging due to high computational and memory demands and tight resource constraints. Modern app…
Enhancing RAG Efficiency with Adaptive Context Compression
Shuyu Guo, Shuo Zhang, Zhaochun Ren
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While c…
LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants
Haochen Huang, Yue Su, Xin Sun +11
Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precis…
Unifying Search and Recommendation with Dual-View Representation Learning in a Generative Paradigm
Jujia Zhao, Wenjie Wang, Chen Xu +3
Recommender systems and search engines serve as foundational elements of online platforms, with the former delivering information proactively and the latter enabling users to seek…
What are the limits of cross-lingual dense passage retrieval for low-resource languages?
Jie Wu, Zhaochun Ren, Suzan Verberne
In this paper, we analyze the capabilities of the multi-lingual Dense Passage Retriever (mDPR) for extremely low-resource languages. In the Cross-lingual Open-Retrieval Answer Gene…
Generative Retrieval with Few-shot Indexing
Arian Askari, Chuan Meng, Mohammad Aliannejadi +3
Existing generative retrieval (GR) methods rely on training-based indexing, which fine-tunes a model to memorise associations between queries and the document identifiers (docids)…