84 citations · 100 across the 33 of their papers we have counts for
34 papers
VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning
Haoze Li, Peng Zhou, Peiyuan Wu +2
Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every trajectory in a group fails w…
A Versioned Unified Graph Index for Dynamic Timestamp-Aware Nearest Neighbor Search
Jun Woo Chung, Weijie Zhao
We present TiGER (Time-Integrated Graph for Efficient Retrieval), a novel approach for performing fast time-aware approximate nearest neighbor searches on dynamic vector datasets w…
DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation
Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6
Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from train…
HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models
Guoshenghui Zhao, Tan Yu, Weijie Zhao
Diffusion large language models generate text through iterative denoising, exposing hidden trajectories that may contain reliability signals beyond the final output. We propose HIV…
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling
Weijie Zhao, Mingquan Liu, Bolun Wang +4
Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identif…
Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
Ziwen Liu, Huawei Lin, Yide Ran +5
Large language models (LLMs) sometimes memorize undesirable knowledge, which must be removed after deployment. Prior work on machine unlearning has focused largely on optimization…
RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning
Guoshenghui Zhao, Huawei Lin, Weijie Zhao
Machine unlearning for large language models (LLMs) remains challenging because full retraining is costly, while approximate methods often struggle to remove targeted behaviors wit…
Robust Watermarking on Gradient Boosting Decision Trees
Jun Woo Chung, Yingjie Lao, Weijie Zhao
Gradient Boosting Decision Trees (GBDTs) are widely used in industry and academia for their high accuracy and efficiency, particularly on structured data. However, watermarking GBD…
Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything
Huawei Lin, Yunzhi Shi, Tong Geng +3
Multimodal large language models (MLLMs) have shown strong capabilities but remain limited to fixed modality pairs and require costly fine-tuning with large aligned datasets. Build…
Automating Financial Statement Audits with Large Language Models
Rushi Wang, Jiateng Liu, Weijie Zhao +2
Financial statement auditing is essential for stakeholders to understand a company's financial health, yet current manual processes are inefficient and error-prone. Even with exten…
VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
Huawei Lin, Tong Geng, Tony Geng +2
Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to…
ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation
Yanzhou Pan, Huawei Lin, Yide Ran +5
Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited bu…
UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
Huawei Lin, Yingjie Lao, Tong Geng +3
Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outp…
Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data
Huawei Lin, Jun Woo Chung, Yingjie Lao +1
Gradient Boosting Decision Tree (GBDT) is one of the most popular machine learning models in various applications. However, in the traditional settings, all data should be simultan…
DMin: Scalable Training Data Influence Estimation for Diffusion Models
Huawei Lin, Yingjie Lao, Weijie Zhao
Identifying the training data samples that most influence a generated image is a critical task in understanding diffusion models (DMs), yet existing influence estimation methods ar…
Measuring Copyright Risks of Large Language Model via Partial Information Probing
Weijie Zhao, Huajie Shao, Zhaozhuo Xu +2
Exploring the data sources used to train Large Language Models (LLMs) is a crucial direction in investigating potential copyright infringement by these models. While this approach…
Token-wise Influential Training Data Retrieval for Large Language Models
Huawei Lin, Jikai Long, Zhaozhuo Xu +1
Given a Large Language Model (LLM) generation, how can we identify which training data led to this generation? In this paper, we proposed RapidIn, a scalable framework adapting to…
GUITAR: Gradient Pruning toward Fast Neural Ranking
Weijie Zhao, Shulong Tan, Ping Li
With the continuous popularity of deep learning and representation learning, fast vector search becomes a vital task in various ranking/retrieval based applications, say recommenda…
Pb-Hash: Partitioned b-bit Hashing
Ping Li, Weijie Zhao
Many hashing algorithms including minwise hashing (MinHash), one permutation hashing (OPH), and consistent weighted sampling (CWS) generate integers of bits. With hashes fo…
Blockwise Feature Interaction in Recommendation Systems
Weijie Zhao, Ping Li
Feature interactions can play a crucial role in recommendation systems as they capture complex relationships between user preferences and item characteristics. Existing methods suc…
Practice with Graph-based ANN Algorithms on Sparse Data: Chi-square Two-tower model, HNSW, Sign Cauchy Projections
Ping Li, Weijie Zhao, Chao Wang +3
Sparse data are common. The traditional ``handcrafted'' features are often sparse. Embedding vectors from trained models can also be very sparse, for example, embeddings trained vi…
Building K-Anonymous User Cohorts with\\ Consecutive Consistent Weighted Sampling (CCWS)
Xinyi Zheng, Weijie Zhao, Xiaoyun Li +1
To retrieve personalized campaigns and creatives while protecting user privacy, digital advertising is shifting from member-based identity to cohort-based identity. Under such iden…
Constrained Approximate Similarity Search on Proximity Graph
Weijie Zhao, Shulong Tan, Ping Li
Search engines and recommendation systems are built to efficiently display relevant information from those massive amounts of candidates. Typically a three-stage mechanism is emplo…
Asymmetric Hashing for Fast Ranking via Neural Network Measures
Khoa Doan, Shulong Tan, Weijie Zhao +1
Fast item ranking is an important task in recommender systems. In previous works, graph-based Approximate Nearest Neighbor (ANN) approaches have demonstrated good performance on it…