2 citations · 4 across the 15 of their papers we have counts for
16 papers
When Does Generating More Help? Disentangling Fixed-Source Synthesis from Source Expansion in Synthetic Data Scaling
Xu Guo, Jian Tong, Zhihui Lu +1
Synthetic data can be scaled along two routes: Source Expansion (SE), which enlarges the source by adding seed materials or generators, and Fixed-Source Synthesis (FSS), which hold…
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
Yao Guan, Lin Wang, Zhihu Lu +3
Despite the remarkable progress of Large Language Model (LLM) based Multi-Agent Systems, most research focuses on optimizing coordination topology while largely underexploring the…
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
Xu Guo, Runyu Peng, Jian Tong +4
Large language models (LLMs) rely on web-scale corpora for pre-training. The noise inherent in these datasets tends to obscure meaningful patterns and ultimately degrade model perf…
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
Xu Guo, Qiming Ge, Jian Tong +8
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (M…
LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries
Xuancheng Ren, Shijing Hu, Zhihui Lu +2
In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs that yield misleading results or vi…
Prefix Probing: Lightweight Harmful Content Detection for Large Language Models
Jirui Yang, Hengqi Guo, Zhihui Lu +6
Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This…
InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inference
Ruijun Deng, Zhihui Lu, Qiang Duan
Split inference (SI) enables users to access deep learning (DL) services without directly transmitting raw data. However, recent studies reveal that data reconstruction attacks (DR…
Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
Shijing Hu, Jingyang Li, Zhihui Lu +1
Speculative decoding accelerates large language model (LLM) inference by letting a lightweight draft model propose multiple tokens that the target model verifies in parallel. Yet e…
Agent Communications toward Agentic AI at Edge -- A Case Study of the Agent2Agent Protocol
Qiang Duan, Zhihui Lu
The current evolution of artificial intelligence introduces a paradigm shift toward agentic AI built upon multi-agent systems (MAS). Agent communications serve as a key to effectiv…
IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
Xu Guo, Tianyi Liang, Tong Jian +6
Reinforcement Learning with Verifiable Rewards (RLVR) improves instruction following capabilities of large language models (LLMs), but suffers from training inefficiency due to ina…
CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation
Jirui Yang, Zheyu Lin, Zhihui Lu +6
Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerabil…
Quantifying Privacy Leakage in Split Inference via Fisher-Approximated Shannon Information Analysis
Ruijun Deng, Zhihui Lu, Qiang Duan +1
Split inference (SI) partitions deep neural networks into distributed sub-models, enabling collaborative learning without directly sharing raw data. However, SI remains vulnerable…
GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
Shijing Hu, Jingyang Li, Xingyu Xie +3
Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token m…
Backdoor Attack on Vertical Federated Graph Neural Network Learning
Jirui Yang, Peng Chen, Zhihui Lu +3
Federated Graph Neural Network (FedGNN) integrate federated learning (FL) with graph neural networks (GNNs) to enable privacy-preserving training on distributed graph data. Vertica…
UIFV: Data Reconstruction Attack in Vertical Federated Learning
Jirui Yang, Peng Chen, Zhihui Lu +2
Vertical Federated Learning (VFL) facilitates collaborative machine learning without the need for participants to share raw private data. However, recent studies have revealed priv…
LAECIPS: Large Vision Model Assisted Adaptive Edge-Cloud Collaboration for IoT-based Embodied Intelligence System
Shijing Hu, Zhihui Lu, Xin Xu +3
Embodied intelligence (EI) enables manufacturing systems to flexibly perceive, reason, adapt, and operate within dynamic shop floor environments. In smart manufacturing, a represen…