Yihang Zhang

Qingyang Li, Yihang Zhang, Zhidong Jia et al.

It is an interesting question Can and How Large Language Models (LLMs) understand non-language network data, and help us detect unknown malicious flows. This paper takes Carpet Bombing as a case study and shows how to exploit LLMs' powerful capability in the networking area. Carpet Bombing is a new DDoS attack that has dramatically increased in recent years, significantly threatening network infrastructures. It targets multiple victim IPs within subnets, causing congestion on access links and disrupting network services for a vast number of users. Characterized by low-rates, multi-vectors, these attacks challenge traditional DDoS defenses. We propose DoLLM, a DDoS detection model utilizes open-source LLMs as backbone. By reorganizing non-contextual network flows into Flow-Sequences and projecting them into LLMs semantic space as token embeddings, DoLLM leverages LLMs' contextual understanding to extract flow representations in overall network context. The representations are used to improve the DDoS detection performance. We evaluate DoLLM with public datasets CIC-DDoS2019 and real NetFlow trace from Top-3 countrywide ISP. The tests have proven that DoLLM possesses strong detection capabilities. Its F1 score increased by up to 33.3% in zero-shot scenarios and by at least 20.6% in real ISP traces.

Xinyi Gao, Dongting Xie, Yihang Zhang et al.

With the expansion of data availability, machine learning (ML) has achieved remarkable breakthroughs in both academia and industry. However, imbalanced data distributions are prevalent in various types of raw data and severely hinder the performance of ML by biasing the decision-making processes. To deepen the understanding of imbalanced data and facilitate the related research and applications, this survey systematically analyzes various real-world data formats and concludes existing researches for different data formats into four distinct categories: data re-balancing, feature representation, training strategy, and ensemble learning. This structured analysis helps researchers comprehensively understand the pervasive nature of imbalance across diverse data formats, thereby paving a clearer path toward achieving specific research goals. We provide an overview of relevant open-source libraries, spotlight current challenges, and offer novel insights aimed at fostering future advancements in this critical area of study.

Yuxin Liu, Chaojie Gu, Yihang Zhang et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning tasks, yet they often struggle with problems involving missing information, exhibiting issues such as incomplete responses, factual errors, and hallucinations. While forward reasoning approaches like Chain-of-Thought (CoT) and Tree-of-Thought (ToT) have shown success in structured problem-solving, they frequently fail to systematically identify and recover omitted information. In this paper, we explore the potential of reverse thinking methodologies to enhance LLMs' performance on missing information detection tasks. Drawing inspiration from recent work on backward reasoning, we propose a novel framework that guides LLMs through reverse thinking to identify necessary conditions and pinpoint missing elements. Our approach transforms the challenging task of missing information identification into a more manageable backward reasoning problem, significantly improving model accuracy. Experimental results demonstrate that our reverse thinking approach achieves substantial performance gains compared to traditional forward reasoning methods, providing a promising direction for enhancing LLMs' logical completeness and reasoning robustness.

Zhibang Yang, Xinke Jiang, Rihong Qiu et al.

Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and relevant documents for ambiguous queries, especially in cross-domain scenarios, which significantly limits their effectiveness in supporting downstream generation tasks. Inspired by Dynamic Information Flow (DIF), we propose DFAMS, a novel framework that leverages DIF to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. Specifically, DFAMS probes the DIF in LLMs by leveraging gradient signals from a few annotated queries and employing Shapley value-based attribution to trace neuron activation paths associated with intent recognition and subdomain boundary detection. Then, DFAMS leverages DIF to train an alignment module via multi-prototype contrastive learning, enabling fine-grained intra-source modeling and inter-source semantic alignment across knowledge bases. Experimental results across five benchmarks show that DFAMS outperforms advanced FR methods by up to 14.37\% in knowledge classification accuracy, 5.38\% in retrieval recall, and 6.45\% in downstream QA accuracy, demonstrating its effectiveness in complex FR scenarios. Our code are anonymous available at https://anonymous.4open.science/r/DFAMS/

Jiayang Yu, Yihang Zhang, Bin Wang et al.

Fine-tuning is a key approach for adapting language models to specific downstream tasks, but updating all model parameters becomes impractical as model sizes increase. Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), address this challenge by introducing additional adaptation parameters into pre-trained weight matrices. However, LoRA's performance varies across different insertion points within the model, highlighting potential parameter inefficiency due to unnecessary insertions. To this end, we propose SSMLoRA (State Space Model Low-Rank Adaptation), an extension of LoRA that incorporates a State Space Model (SSM) to interconnect low-rank matrices. SSMLoRA ensures that performance is maintained even with sparser insertions. SSMLoRA allows the model to not only map inputs to a low-rank space for better feature extraction but also leverage the computations from the previous low-rank space. Our method achieves comparable performance to LoRA on the General Language Understanding Evaluation (GLUE) benchmark while using only half the parameters. Additionally, due to its structure, SSMLoRA shows promise in handling tasks with longer input sequences. .You can find our code here:https://github.com/yuhkalhic/SSMLoRA.

Yihang Zhang, Zimeng Huang, Ren Zhai et al.

Reconciling platform revenue with user experience in LLM advertising motivates a data-centric foundation. We introduce NaiAD, the first comprehensive dataset for LLM-native advertising comprising 58,999 carefully constructed ad-embedded responses paired with user queries. NaiAD is organized around theoretically grounded evaluation metrics that separately and comprehensively capture user and commercial utility. To mitigate the dimensional collinearity of aligned LLMs, we propose a decoupled generation pipeline that produces structurally diverse samples, ranging from responses that explicitly disentangle stakeholder utilities to responses that are uniformly strong or weak across dimensions. We further provide score labels calibrated by a Variance-Calibrated Prediction-Powered Inference (VC-PPI) framework, aligning automated scoring with human annotations. Mechanistic analyses reveal that successful ad integration relies on reasoning paths that cluster into four distinct semantic strategies. Models leveraging NaiAD internalize these strategies to simultaneously improve user and commercial utility, while enabling independent control over these distinct objectives via in-context learning. Together, these results position NaiAD as a foundational infrastructure for developing future LLM-native ad systems.

Peiran Yun, Wenxin Xu, Jiayuan Liu et al.

As Large Language Models (LLMs) transition into conversational agents, generative advertising emerges as a crucial monetization strategy. However, embedding advertisements within unstructured LLM outputs introduces a critical trilemma: balancing advertiser payoffs, platform revenue, and user experience. Existing methods, such as prompt injection or rigid position slots, disrupt semantic coherence and lack a parametric framework for independent control, rendering rigorous mechanism design intractable. To bridge this gap, we introduce Neuron Auctions, a novel paradigm that shifts the auction object from the surface text space to the LLM's internal representations. Leveraging mechanistic interpretability, we identify brand-specific feed-forward network (FFN) neurons and demonstrate that competing brands activate within approximately orthogonal subspaces. This near-perfect independence allows us to define continuous, disentangled intervention budgets (specifically, neuron counts and amplification factors) as auctionable commodities. Building on this computational carrier, we design a continuous menu-based auction mechanism that naturally guarantees strategy-proofness and optimizes revenue for the platform. By explicitly incorporating a user utility penalty into the platform's optimization objective, our framework dynamically prices out overly aggressive interventions. Extensive experiments demonstrate that Neuron Auctions effectively preserve natural discourse quality while achieving an optimal alignment between commercial incentives and user satisfaction.

Di Zhang, Yihang Zhang

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empirical evidence suggests potential performance limitations. In response, this paper proposes a stochastic conjugate subgradient method together with adaptive sampling tailored specifically for training LLMs. The method not only achieves faster convergence per iteration but also demonstrates improved scalability compared to traditional SGD techniques. It leverages sample complexity analysis to adaptively choose the sample size, employs a stochastic conjugate subgradient approach to determine search directions and utilizing an AdamW-like algorithm to adaptively adjust step sizes. This approach preserves the key advantages of first-order methods while effectively addressing the nonconvexity and non-smoothness inherent in LLMs training. Additionally, we provide a detailed analysis of the advantage of the algorithm. Experimental results show that the proposed method not only maintains, but in many cases surpasses, the scalability of traditional SGD techniques, significantly enhancing both the speed and accuracy of the optimization process.

Wenjie Qiu, Yi-Chen Li, Xuqin Zhang et al.

Learning reward models from human preference datasets and subsequently optimizing language models via reinforcement learning has emerged as a fundamental paradigm for aligning LLMs with human preferences. The performance of the reward model plays a crucial role in the effectiveness of alignment. Previous reward models operate at a coarse-grained level, requiring the generation of a complete response to obtain a reward value. The sparse reward may present challenges for downstream reinforcement learning. While recent efforts have attempted to learn token-level reward models, the lack of explicit semantic information makes it difficult to model the credit of every individual token. In this paper, we propose assigning scores to every sentence, introducing an intermediate-grained reward model. By segmenting the complete response into sentences and applying differential operations to reward output at the start and end positions of each sentence, we can effectively model the rewards of sentences. Moreover, a novel attention mechanism is introduced to aggregate the scores of all sentences into a response-level score, which allows it to be trained using the Bradley-Terry model. On common benchmarks, our method outperforms the response-level reward model by 2.7% on RewardBench (for reward modeling evaluation) and surpasses all baselines on AlpacaEval (for alignment evaluation).

Yun Liang, Hai Lin, Shaojian Qiu et al.

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality--It fine-tunes easily to downstream tasks and shows more robust performance. However, the predominant fine-tuning method currently used is still full fine-tuning, which involves updating all parameters during training. This not only incurs significant memory usage and time costs but also compromises the model's generality. Other fine-tuning methods either struggle to address this issue or fail to achieve matching performance. Therefore, we conducted a comprehensive analysis of existing fine-tuning methods and proposed an efficient fine-tuning approach based on Adapter tuning, namely AAT. The core idea is to freeze the audio Transformer model and insert extra learnable Adapters, efficiently acquiring downstream task knowledge without compromising the model's original generality. Extensive experiments have shown that our method achieves performance comparable to or even superior to full fine-tuning while optimizing only 7.118% of the parameters. It also demonstrates superiority over other fine-tuning methods.

Yihang Zhang, Aristotelis-Angelos Papadopoulos, Pengfei Chen et al.

Transportation networks are highly complex and the design of efficient traffic management systems is difficult due to lack of adequate measured data and accurate predictions of the traffic states. Traffic simulation models can capture the complex dynamics of transportation networks by using limited available traffic data and can help central traffic authorities in their decision-making, if appropriate input is fed into the simulator. In this paper, we design an integrated simulation-prediction system which estimates the Origin-Destination (OD) matrix of a road network using only flow rate information and predicts the behavior of the road network in different simulation scenarios. The proposed system includes an optimization-based OD matrix generation method, a Neural Network (NN) model trained to predict OD matrices via the pattern of traffic flow and a microscopic traffic simulator with a Dynamic Traffic Assignment (DTA) scheme to predict the behavior of the transportation system. We test the proposed system on the road network of the central terminal area (CTA) of the Los Angeles International Airport (LAX), which demonstrates that the integrated traffic simulation-prediction system can be used to simulate the effects of several real world scenarios such as lane closures, curbside parking and other changes. The model is an effective tool for learning the impact and possible benefits of changes in the network and for analyzing scenarios at a very low cost without disrupting the network.

Tongyu Dai, Xinggong Zhang, Yihang Zhang et al.

With the increasing demands on interactive video applications, how to adapt video bit rate to avoid network congestion has become critical, since congestion results in self-inflicted delay and packet loss which deteriorate the quality of real-time video service. The existing congestion control is hard to simultaneously achieve low latency, high throughput, good adaptability and fair bandwidth allocation, mainly because of the hardwired control strategy and egocentric convergence objective. To address these issues, we propose an end-to-end statistical learning based congestion control, named Iris. By exploring the underlying principles of self-inflicted delay, we reveal that congestion delay is determined by sending rate, receiving rate and network status, which inspires us to control video bit rate using a statistical-learning congestion control model. The key idea of Iris is to force all flows to converge to the same queue load, and adjust the bit rate by the model. All flows keep a small and fixed number of packets queuing in the network, thus the fair bandwidth allocation and low latency are both achieved. Besides, the adjustment step size of sending rate is updated by online learning, to better adapt to dynamically changing networks. We carried out extensive experiments to evaluate the performance of Iris, with the implementations of transport layer (UDP) and application layer (QUIC) respectively. The testing environment includes emulated network, real-world Internet and commercial LTE networks. Compared against TCP flavors and state-of-the-art protocols, Iris is able to achieve high bandwidth utilization, low latency and good fairness concurrently. Especially over QUIC, Iris is able to increase the video bitrate up to 25%, and PSNR up to 1dB.