338 citations · 1.4k across the 188 of their papers we have counts for
200 papers
InfoVis: Unified Slide Image Generation and Editing
Jiahao Wang, Xiyan Jiang, Chenyuan Wu +7
Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within…
Self-improving data synthesis enables scalable adaptation of embedding models
Zucan Lyu, Rui Tang, Jianlyu Chen +3
AI agents require specialised retrieval across domains and tasks, but adapting embedding models is constrained by costly manual training-data design. Here we introduce SYNTRA, a se…
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Hongjin Qian, Chaofan Li, Kun Luo +11
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rest…
IGSD: Environment-Verified Hindsight Self-Distillation for Search Agents
Angqing Jiang, Gaoming Zhang, Chaoqun Zhang +5
On-policy self-distillation densifies agent training without external teachers: a policy conditioned on privileged hindsight provides step-level guidance for its own unprivileged r…
Efficient Linear Bandits via Cluster-Aware Sketching
Hantao Yang, Hong Xie, Defu Lian
We study the problem of computational efficiency for linear bandits in high-dimensional settings with a finite arm set. In linear bandits, the increase in the dimension of the…
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and ve…
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
Gaoming Zhang, Angqing Jiang, Jianchun Song +4
Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabilities for candidate items. Howe…
Support Selection Beyond Smooth DAG Exactness: Completion Geometry,Score Margins, and Selective Certificates
Rui Wu, Zongyuan Chen, Hong Xie +2
Smooth acyclicity constraints answer whether a weighted support is a DAG, whereas structure learning asks which support change should be made. Existing analyses establish degenerac…
SWIM: Step-Wise Integrated Measure for Session-supervised List Evaluation in Generative Re-ranking
Yuanhao Pu, Chenghao Zhang, Chao Feng +6
Modern industrial recommender systems have increasingly adopted the Generator-Evaluator (G-E) framework for the re-ranking stage. Within this paradigm, the generator produces candi…
Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval
Angqing Jiang, Gaoming Zhang, Jianchun Song +4
Dense retrieval has become a cornerstone of modern local-lifestyle e-commerce search by encoding queries and items into semantic embedding spaces. While recent advancements have tr…
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
Zhaoyi Li, Deyang Kong, Yuan Wei +13
On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly unders…
DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval
Yuanhao Pu, Chenghao Zhang, Chao Feng +2
Reranking is a combinatorial decision problem that aims to select and order a high-utility slate from a request-specific candidate set. A major line of generative rerankers adopts…
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective
Jiahe Fan, Yinghao Hou, Si Chen +3
Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment? Existing heterogeneous fusio…
CR: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Haoran Jin, Xiting Wang, Shijie Ren +2
Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionari…
RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
Cheng He, Zhenyu Guan, Xijie Liang +6
Financial time series forecasting presents structural challenges absent from standard benchmarks. Log-returns are non-stationary, exhibit exceptionally low signal-to-noise (SNR) ra…
OneReason Technical Report
OneRec Team, Biao Yang, Boyang Ding +81
Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. Howev…
Learning Generated Controls under Fractured Geometry: Projective Residualization and Variation-Allocation Frontiers
Rui Wu, Zongyuan Chen, Hong Xie +2
Many two-stage estimators assess the first-stage learner by prediction error, even when the next stage uses its residual. In control-function instrumental variables, that residual…
Representation-Guided Discrete Molecular Graph Retrosynthesis
Jiahai Huang, Anjie Qiao, Zhen Wang +2
Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models are typically trained only…
Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement
Chenwang Wu, Yiu-ming Cheung, Bo Han +1
Machine-generated texts (MGTs) produced by large language models (LLMs) are increasingly prevalent across various applications, while their potential misuse in fake news propagatio…
Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection
Chenwang Wu, Yiuming Cheung, Bo Han +2
Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection. Metric-based methods, which extract statistically disti…
CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting
Bokai Pan, Mingyue Cheng, Zhiding Liu +6
Time series forecasting is a fundamental task in temporal data analytics, and large language model (LLM)-based agents offer a promising paradigm through autonomous tool interaction…
Scaling Federated Linear Contextual Bandits via Sketching
Hantao Yang, Hong Xie, Xutong Liu +1
In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform -time determinant computation…
Similar Users-Augmented Interest Network
Xiaolong Chen, Haoyi Zhao, Xu Huang +1
Click-through rate (CTR) prediction is one of the core tasks in recommender systems. User behavior sequences, as one of the most effective features, can accurately reflect user pre…
Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders
Angqing Jiang, Jianlyu Chen, Zhe Fang +4
Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency an…