28 citations · 43 across the 22 of their papers we have counts for
24 papers
Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Weilun Xu, Zipeng Sun
Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it…
ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions
Peixian Zhou, Yuxu Chen, Chaorui Zhang +3
Large language models perform increasingly well on standardized logical reasoning benchmarks, but whether this ability remains robust beyond English is unclear. We introduce ChLogi…
Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL
Zerui Yang, Weichuan Wang, Yanwei Xu +4
Existing NL2SQL systems face two critical limitations: (1) they rely on in-context learning with only correct examples, overlooking the rich signal in historical error-fix pairs th…
On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
Xueyan Niu, Bo Bai, Wei Han +1
Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimiz…
DB3 Team's Solution For Meta KDD Cup' 25
Yikuan Xia, Jiazun Chen, Yirui Zhan +6
This paper presents the db3 team's winning solution for the Meta CRAG-MM Challenge 2025 at KDD Cup'25. Addressing the challenge's unique multi-modal, multi-turn question answering…
NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
Weizhi Fei, Hao Shi, Jing Xu +7
Efficiently editing knowledge stored in large language models (LLMs) enables model updates without large-scale training. One possible solution is Locate-and-Edit (L\&E), allowing s…
ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources
Yikuan Xia, Jiazun Chen, Yirui Zhan +6
Large language models (LLMs) excel in question-answering (QA) tasks, and retrieval-augmented generation (RAG) enhances their precision by incorporating external evidence from diver…
Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference
Weizhi Fei, Xueyan Niu, Guoqing Xie +3
Although applications involving long-context inputs are crucial for the effective utilization of large language models (LLMs), they also result in increased computational costs and…
Towards Faster Graph Partitioning via Pre-training and Inductive Inference
Meng Qin, Chaorui Zhang, Yu Gao +5
Graph partitioning (GP) is a classic problem that divides the node set of a graph into densely-connected blocks. Following the IEEE HPEC Graph Challenge and recent advances in pre-…
A Mean Field Ansatz for Zero-Shot Weight Transfer
Xingyuan Chen, Wenwei Kuang, Lei Deng +3
The pre-training cost of large language models (LLMs) is prohibitive. One cutting-edge approach to reduce the cost is zero-shot weight transfer, also known as model growth for some…
Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding
Weizhi Fei, Xueyan Niu, Guoqing Xie +4
Current Large Language Models (LLMs) face inherent limitations due to their pre-defined context lengths, which impede their capacity for multi-hop reasoning within extensive textua…
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory
Xueyan Niu, Bo Bai, Lei Deng +1
Increasing the size of a Transformer does not always lead to enhanced performance. This phenomenon cannot be explained by the empirical scaling laws. Furthermore, the model's enhan…
Localization and Discrete Beamforming with a Large Reconfigurable Intelligent Surface
Baojia Luo, Yili Deng, Miaomiao Dong +4
In millimeter-wave (mmWave) cellular systems, reconfigurable intelligent surfaces (RISs) are foreseeably deployed with a large number of reflecting elements to achieve high beamfor…
Extending Context Window of Large Language Models via Semantic Compression
Weizhi Fei, Xueyan Niu, Pingyi Zhou +4
Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint r…
RaftGP: Random Fast Graph Partitioning
Yu Gao, Meng Qin, Yibin Ding +6
Graph partitioning (GP), a.k.a. community detection, is a classic problem that divides the node set of a graph into densely-connected blocks. Following prior work on the IEEE HPEC…
High Perceptual Quality Wireless Image Delivery with Denoising Diffusion Models
Selim F. Yilmaz, Xueyan Niu, Bo Bai +3
We consider the image transmission problem over a noisy wireless channel via deep learning-based joint source-channel coding (DeepJSCC) along with a denoising diffusion probabilist…
Conditional Rate-Distortion-Perception Trade-Off
Xueyan Niu, Deniz Gündüz, Bo Bai +1
Recent advances in machine learning-aided lossy compression are incorporating perceptual fidelity into the rate-distortion theory. In this paper, we study the rate-distortion-perce…
Semantic Compression with Side Information: A Rate-Distortion Perspective
Tao Guo, Yizhu Wang, Jie Han +3
We consider the semantic rate-distortion problem motivated by task-oriented video compression. The semantic information corresponding to the task, which is not observable to the en…
Lossy Computing with Side Information via Multi-Hypergraphs
Deheng Yuan, Tao Guo, Bo Bai +1
We consider a problem of coding for computing, where the decoder wishes to estimate a function of its local message and the source message at the encoder within a given distortion.…
TOSE: A Fast Capacity Determination Algorithm Based on Random Matrix Theory
Dandan Jiang, Han Hao, Lu Yang +3
Wireless network capacity is one of the most important performance metrics for wireless communication networks. Future wireless networks will be composed of extremely large number…
An Efficient Two-Stage SPARC Decoder for Massive MIMO Unsourced Random Access
Juntao You, Wenjie Wang, Shansuo Liang +2
In this paper, we study a concatenate coding scheme based on sparse regression code (SPARC) and tree code for unsourced random access in massive multiple-input and multiple-output…
A Tensor-BTD-based Modulation for Massive Unsourced Random Access
Zhenting Luan, Yuchi Wu, Shansuo Liang +3
In this letter, we propose a novel tensor-based modulation scheme for massive unsourced random access. The proposed modulation can be deemed as a summation of third-order tensors,…
Harmonic Retrieval with -Tucker Tensor Decomposition
Zhenting Luan, Zhenyu Ming, Yuchi Wu +4
Harmonic retrieval (HR) has a wide range of applications in the scenes where signals are modelled as a summation of sinusoids. Past works have developed a number of approaches to r…
Structural Entropy of the Stochastic Block Models
Jie Han, Tao Guo, Qiaoqiao Zhou +3
With the rapid expansion of graphs and networks and the growing magnitude of data from all areas of science, effective treatment and compression schemes of context-dependent data i…