wovepaper — the arXiv observatory

The paper introduces DIRECTOR, a parallel reranking framework that uses dynamic retrieval indices and entropy‑regularized optimal transport to generate duplicate‑free recommendatio…

#recommender systems#reranking#optimal transport#non‑autoregressive models

cs.CL2024

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing

Weichuan Wang, Zhaoyi Li, Defu Lian +3

cs.CL2026

SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation

Hang Lv, Sheng Liang, Hao Wang +6

cs.CL2025

Reinforced Information Retrieval

Chaofan Li, Zheng Liu, Jianlyv Chen +2

cs.LG2025

Efficient Machine Unlearning via Influence Approximation

Jiawei Liu, Chenwang Wu, Defu Lian +1

cs.IR2025

Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction

Xiang Xu, Hao Wang, Wei Guo +6

cs.CL2025

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

Xu Huang, Weiwen Liu, Xingshan Zeng +8

cs.IR2025

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Jianlyu Chen, Nan Wang, Chaofan Li +6

cs.LG2025

How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control

Hao Yu, Chu Xin Cheng, Runlong Yu +4

cs.CL2024

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

Yuqing Huang, Rongyang Zhang, Xuesong He +15

cs.LG2023

Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors

Moritz Neun, Christian Eichenberger, Henry Martin +27

cs.CL2026

Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection

Chenwang Wu, Yiuming Cheung, Bo Han +2

cs.AI2026

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility

Xuyang Zhi, Peilun zhou, Chengqiang Lu +10

cs.LG2026

C $^{2}$ R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

Haoran Jin, Xiting Wang, Shijie Ren +2

cs.CL2024

Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation

Zheng Liu, Chenyuan Wu, Ninglu Shao +3

cs.CV2024

Invariant Representation via Decoupling Style and Spurious Features from Images

Ruimeng Li, Yuanhao Pu, Zhaoyi Li +2

cs.LG2026

A DeepLearning Framework for Dynamic Estimation of Origin-Destination Sequence

Zheli Xiong, Defu Lian, Enhong Chen +2

cs.LG2026

CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting

Bokai Pan, Mingyue Cheng, Zhiding Liu +6

cs.IR2021

Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation

Yongji Wu, Defu Lian, Neil Zhenqiang Gong +4

cs.CL2026

Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection

Chenwang Wu, Yiu-ming Cheung, Shuhai Zhang +2

cs.AI2023

Deep Task-specific Bottom Representation Network for Multi-Task Recommendation

Qi Liu, Zhilong Zhou, Gangwei Jiang +2

cs.AI2025

Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing

Hong Xie, Haoran Gu, Yanying Huang +2

cs.AI2026

Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance

Wei Yang, Hong Xie, Tao Tan +3

cs.IR2025

HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks

Hongjin Qian, Zheng Liu, Chao Gao +3

cs.CL2023

GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph

Junhan Yang, Zheng Liu, Shitao Xiao +6

cs.LG2023

Toward Robust Recommendation via Real-time Vicinal Defense

Yichang Xu, Chenwang Wu, Defu Lian

cs.IR2019

A Novel User Representation Paradigm for Making Personalized Candidate Retrieval

Zheng Liu, Yu Xing, Jianxun Lian +3

cs.CL2026

IE as Cache: Information Extraction Enhanced Agentic Reasoning

Hang Lv, Sheng Liang, Hongchao Gu +5

cs.IR2023

Interactive Graph Convolutional Filtering

Jin Zhang, Defu Lian, Hong Xie +2

cs.CL2026

Position: The Real Barrier to LLM Agent Usability is Agentic ROI

Weiwen Liu, Jiarui Qin, Xu Huang +10

cs.IR2022

Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings

Shitao Xiao, Zheng Liu, Weihao Han +10

Publications (192)

ACEBench: Who Wins the Match Point in Tool Usage?

Making Text Embedders Few-Shot Learners

AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning

MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network

RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting

Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective

Deep Pairwise Hashing for Cold-start Recommendation

Representation-Guided Discrete Molecular Graph Retrosynthesis

Dataset Regeneration for Sequential Recommendation

Model Stealing Attack against Recommender System

Self-Supervised Text Erasing with Controllable Image Synthesis

Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

UniDM: A Unified Framework for Data Manipulation with Large Language Models

Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure

Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control

Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement

RecExplainer: Aligning Large Language Models for Explaining Recommendation Models

OpenOneRec Technical Report

Indigenization of Urban Mobility

Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation

Visualizing the Relationship Between Encoded Linguistic Information and Task Performance

GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data

FilterNet: Harnessing Frequency Filters for Time Series Forecasting

BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction

Orderness Predicts Academic Performance: Behavioral Analysis on Campus Lifestyle

Cooperative Retriever and Ranker in Deep Recommenders

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

MDAP: A Multi-view Disentangled and Adaptive Preference Learning Framework for Cross-Domain Recommendation

A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation

Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval

M2-MFP: A Multi-Scale and Multi-Level Memory Failure Prediction Framework for Reliable Cloud Infrastructure

DeepXiv-SDK: An Agentic Data Interface for Scientific Literature

Understanding Privacy Risks of Embeddings Induced by Large Language Models

C-Pack: Packed Resources For General Chinese Embeddings

Boosting Factorization Machines via Saliency-Guided Mixup

AgentCAT: An LLM Agent for Extracting and Analyzing Catalytic Reaction Data from Chemical Engineering Literature

Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering

Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction

Sampling-Decomposable Generative Adversarial Recommender

A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting

Understanding and Patching Compositional Reasoning in LLMs

KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification

Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendation

END4Rec: Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation

Towards Robust Recommender Systems via Triple Cooperative Defense

Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective

Foundations and Frontiers of Graph Learning Theory

DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction

Learning Partially Aligned Item Representation for Cross-Domain Sequential Recommendation

Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors

MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval

NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning

FuXi-I^±: Scaling Recommendation Model with Feature Interaction Enhanced Transformer

A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems

Hybrid Encoder: Towards Efficient and Precise Native AdsRecommendation via Hybrid Transformer Encoding Networks

On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning

Aligning Language Models for Versatile Text-based Item Retrieval

Scaling Federated Linear Contextual Bandits via Sketching

RecFlow: An Industrial Full Flow Recommendation Dataset

Assessing Dialogue Systems with Distribution Distances

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

WESE: Weak Exploration to Strong Exploitation for LLM Agents

Securing Recommender System via Cooperative Training

Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective

DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models

Analytical and Empirical Study of Herding Effects in Recommendation Systems

DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing

SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation

Reinforced Information Retrieval

Efficient Machine Unlearning via Influence Approximation

Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

M $^{2}$ -MFP: A Multi-Scale and Multi-Level Memory Failure Prediction Framework for Reliable Cloud Infrastructure

MR $^{2}$ -Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval

FuXi- $I^\pm$ : Scaling Recommendation Model with Feature Interaction Enhanced Transformer

C $^{2}$ R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders