arXiv subjects

Yiran Chen

Publications and source records attributed to Yiran Chen.

At least 91 records · Page 5Linked to original sources

arXiv2025

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models

Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Logits Evolution Decoding (SLED), a novel decoding framework that enhances the truthfulness of LLMs without relying on external knowledge bases or requiring further fine-tuning. From an optimization perspective, our SLED framework leverages the latent knowledge embedded within the LLM by contrasting the output logits from the final layer with those from early layers. It then utilizes an approximate gradient approach to enable latent knowledge to guide the self-refinement of outputs, thereby effectively improving factual accuracy. Extensive experiments have been conducted on established benchmarks across a diverse range of model families (Gemma, Qwen, Mixtral, gpt-oss) and scales (from 1B to 45B), including more advanced architectural configurations such as the mixture of experts (MoE). Our evaluation spans a wide variety of tasks and the results demonstrate that SLED consistently improves factual accuracy compared to existing decoding methods while maintaining natural language fluency and negligible latency overhead. Furthermore, it can be flexibly combined with other decoding methods to further enhance their performance.

cs.CL↗

arXiv2025

FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal accuracy loss. Previous SVD-based approaches have focused primarily on reducing the memory footprint of model weights, largely overlooking the additional activation memory overhead incurred during inference when applying truncated factors via standard dense CUDA kernels. Our experiments demonstrate that this activation overhead, scaling with sequence length and hidden dimension, prevents current SVD compression techniques from achieving any reduction in peak inference memory, thereby limiting their viability for real-world, on-device deployments. We introduce FlashSVD, a novel, end-to-end rank-aware streaming inference framework specifically designed for SVD-compressed large language models. FlashSVD can be seamlessly integrated with any model that employs SVD-based methods for parameter reduction. By fusing low-rank projection kernels directly into both the self-attention and feed-forward network (FFN) pipelines, FlashSVD avoid materializing full-size activation buffers. Instead, small tiles of the truncated factors are loaded into on-chip SRAM, multiplied and reduced on the fly, and immediately evicted, preserving high GPU occupancy and adding no extra latency. On standard encoder benchmarks (e.g., BERT-Base), FlashSVD cuts peak activation memory by up to 70.2% and intermediate transient memory by 75%, all while incur no accuracy loss with upstreaming compression methods, offering a practical path toward memory-constrained deployment of low-rank LLMs.

cs.LG↗

arXiv2025

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation

Automation of analog topology design is crucial due to customized requirements of modern applications with heavily manual engineering efforts. The state-of-the-art work applies a sequence-to-sequence approach and supervised finetuning on language models to generate topologies given user specifications. However, its circuit formulation is inefficient due to O(|V |2) token length and suffers from low precision sensitivity to numeric inputs. In this work, we introduce LaMAGIC2, a succinct float-input canonical formulation with identifier (SFCI) for language model-based analog topology generation. SFCI addresses these challenges by improving component-type recognition through identifier-based representations, reducing token length complexity to O(|V |), and enhancing numeric precision sensitivity for better performance under tight tolerances. Our experiments demonstrate that LaMAGIC2 achieves 34% higher success rates under a tight tolerance of 0.01 and 10X lower MSEs compared to a prior method. LaMAGIC2 also exhibits better transferability for circuits with more vertices with up to 58.5% improvement. These advancements establish LaMAGIC2 as a robust framework for analog topology generation.

cs.LG↗

arXiv2025

MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization

This paper presents MCP4EDA, the first Model Context Protocol server that enables Large Language Models (LLMs) to control and optimize the complete open-source RTL-to-GDSII design flow through natural language interaction. The system integrates Yosys synthesis, Icarus Verilog simulation, OpenLane place-and-route, GTKWave analysis, and KLayout visualization into a unified LLM-accessible interface, enabling designers to execute complex multi-tool EDA workflows conversationally via AI assistants such as Claude Desktop and Cursor IDE. The principal contribution is a backend-aware synthesis optimization methodology wherein LLMs analyze actual post-layout timing, power, and area metrics from OpenLane results to iteratively refine synthesis TCL scripts, establishing a closed-loop optimization system that bridges the traditional gap between synthesis estimates and physical implementation reality. In contrast to conventional flows that rely on wire-load models, this methodology leverages real backend performance data to guide synthesis parameter tuning, optimization sequence selection, and constraint refinement, with the LLM functioning as an intelligent design space exploration agent. Experimental evaluation on representative digital designs demonstrates 15-30% improvements in timing closure and 10-20% area reduction compared to default synthesis flows, establishing MCP4EDA as the first practical LLM-controlled end-to-end open-source EDA automation system. The code and demo are avaiable at: http://www.agent4eda.com/

cs.AR↗

arXiv2025

SADA: Stability-guided Adaptive Diffusion Acceleration

Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce per-step computation cost, while effectively reducing sampling time, demonstrate low faithfulness compared to the original baseline. We hypothesize that this fidelity gap arises because (a) different prompts correspond to varying denoising trajectory, and (b) such methods do not consider the underlying ODE formulation and its numerical solution. In this paper, we propose Stability-guided Adaptive Diffusion Acceleration (SADA), a novel paradigm that unifies step-wise and token-wise sparsity decisions via a single stability criterion to accelerate sampling of ODE-based generative models (Diffusion and Flow-matching). For (a), SADA adaptively allocates sparsity based on the sampling trajectory. For (b), SADA introduces principled approximation schemes that leverage the precise gradient information from the numerical ODE solver. Comprehensive evaluations on SD-2, SDXL, and Flux using both EDM and DPM++ solvers reveal consistent $\ge 1.8\times$ speedups with minimal fidelity degradation (LPIPS $\leq 0.10$ and FID $\leq 4.5$) compared to unmodified baselines, significantly outperforming prior methods. Moreover, SADA adapts seamlessly to other pipelines and modalities: It accelerates ControlNet without any modifications and speeds up MusicLDM by $1.8\times$ with $\sim 0.01$ spectrogram LPIPS.

cs.LG↗

arXiv2025

EDALearn: A Comprehensive RTL-to-Signoff EDA Benchmark for Democratized and Reproducible ML for EDA Research

The application of Machine Learning (ML) in Electronic Design Automation (EDA) for Very Large-Scale Integration (VLSI) design has garnered significant research attention. Despite the requirement for extensive datasets to build effective ML models, most studies are limited to smaller, internally generated datasets due to the lack of comprehensive public resources. In response, we introduce EDALearn, the first holistic, open-source benchmark suite specifically for ML tasks in EDA. This benchmark suite presents an end-to-end flow from synthesis to physical implementation, enriching data collection across various stages. It fosters reproducibility and promotes research into ML transferability across different technology nodes. Accommodating a wide range of VLSI design instances and sizes, our benchmark aptly represents the complexity of contemporary VLSI designs. Additionally, we provide an in-depth data analysis, enabling users to fully comprehend the attributes and distribution of our data, which is essential for creating efficient ML models. Our contributions aim to encourage further advances in the ML-EDA domain.

cs.LG↗

arXiv2025

Federated Unsupervised Visual Representation Learning via Exploiting General Content and Personal Style

Discriminative unsupervised learning methods such as contrastive learning have demonstrated the ability to learn generalized visual representations on centralized data. It is nonetheless challenging to adapt such methods to a distributed system with unlabeled, private, and heterogeneous client data due to user styles and preferences. Federated learning enables multiple clients to collectively learn a global model without provoking any privacy breach between local clients. On the other hand, another direction of federated learning studies personalized methods to address the local heterogeneity. However, work on solving both generalization and personalization without labels in a decentralized setting remains unfamiliar. In this work, we propose a novel method, FedStyle, to learn a more generalized global model by infusing local style information with local content information for contrastive learning, and to learn more personalized local models by inducing local style information for downstream tasks. The style information is extracted by contrasting original local data with strongly augmented local data (Sobel filtered images). Through extensive experiments with linear evaluations in both IID and non-IID settings, we demonstrate that FedStyle outperforms both the generalization baseline methods and personalization baseline methods in a stylized decentralized setting. Through comprehensive ablations, we demonstrate our design of style infusion and stylized personalization improve performance significantly.

cs.CV↗

arXiv2025

MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing

In multi-GPU Mixture-of-Experts (MoE) network, experts are distributed across different GPUs, which creates load imbalance as each expert processes different number of tokens. Recent works improve MoE inference load balance by dynamically duplicating popular experts to more GPUs to process excessive tokens, which requires predicting the distribution before routing. In this paper, we discuss the tradeoff of prediction strategies, accuracies, overhead, and end-to-end system performance. We propose MoE-GPS, a framework that guides the selection of the optimal predictor design under various system configurations, by quantifying the performance impact to system-level model runtime. Specifically, we advocate for Distribution-Only Prediction, a prediction strategy that only predicts overall token distribution which significantly reduces overhead compared to the traditional Token-to-Expert Prediction. On Mixtral 8x7B MMLU dataset, MoE-GPS suggests Distribution-Only Prediction which improves end-to-end inference performance by more than 23% compared with Token-to-Expert Prediction.

cs.LG↗

arXiv2025

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity

Federated Learning enables collaborative fine-tuning of Large Language Models (LLMs) across decentralized Non-Independent and Identically Distributed (Non-IID) clients, but such models' massive parameter sizes lead to significant memory and communication challenges. This work introduces Meerkat, a sparse zeroth-order optimization (ZO) method designed for federated LLM fine-tuning. By limiting fine-tuning to a transferable, static, extremely sparse subset of parameters, Meerkat achieves remarkable communication efficiency, enabling cost-effective high-frequency synchronization. With theoretical analysis and experiments, we show that this high-frequency communication effectively mitigates Non-IID data challenges and leads to superior performance compared to full-parameter ZO. Furthermore, experiment results show that Meerkat outperforms existing sparsity baselines with better performance at the same communication frequency. To further handle Non-IID drift, Meerkat leverages traceable local updates and forms a virtual path for each client. This virtual path mechanism reveals the GradIP phenomenon: the inner products between LLM pre-training gradients maintained by server and client gradients estimated via ZO converges for extreme Non-IID clients but oscillates for IID ones. This distinct behavior provides a signal for identifying clients with extreme data heterogeneity. Using this signal, Meerkat-vp is proposed to analyze GradIP trajectories to identify extreme Non-IID clients and applies early stopping to enhance aggregated model quality. Experiments confirm that Meerkat and Meerkat-vp significantly improve the efficiency and effectiveness of ZO federated LLM fine-tuning.

cs.LG↗

arXiv2025

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate a new research area: automated failure attribution for LLM multi-agent systems. To support this initiative, we introduce the Who&When dataset, comprising extensive failure logs from 127 LLM multi-agent systems with fine-grained annotations linking failures to specific agents and decisive error steps. Using the Who&When, we develop and evaluate three automated failure attribution methods, summarizing their corresponding pros and cons. The best method achieves 53.5% accuracy in identifying failure-responsible agents but only 14.2% in pinpointing failure steps, with some methods performing below random. Even SOTA reasoning models, such as OpenAI o1 and DeepSeek R1, fail to achieve practical usability. These results highlight the task's complexity and the need for further research in this area. Code and dataset are available at https://github.com/mingyin1/Agents_Failure_Attribution

cs.MA↗

arXiv2025

SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues

Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To address this challenge, we propose a novel defense mechanism: SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues (STREAM). STREAM defends LLMs against multi-turn attacks while preserving their functional capabilities. Our approach involves constructing a human-annotated dataset, the Safety Reasoning Multi-turn Dialogues dataset, which is used to fine-tune a plug-and-play safety reasoning moderator. This model is designed to identify malicious intent hidden within multi-turn conversations and alert the target LLM of potential risks. We evaluate STREAM across multiple LLMs against prevalent multi-turn attack strategies. Experimental results demonstrate that our method significantly outperforms existing defense techniques, reducing the Attack Success Rate (ASR) by 51.2%, all while maintaining comparable LLM capability.

cs.CL↗

arXiv2025

LoBAM: LoRA-Based Backdoor Attack on Model Merging

Model merging is an emerging technique that integrates multiple models fine-tuned on different tasks to create a versatile model that excels in multiple domains. This scheme, in the meantime, may open up backdoor attack opportunities where one single malicious model can jeopardize the integrity of the merged model. Existing works try to demonstrate the risk of such attacks by assuming substantial computational resources, focusing on cases where the attacker can fully fine-tune the pre-trained model. Such an assumption, however, may not be feasible given the increasing size of machine learning models. In practice where resources are limited and the attacker can only employ techniques like Low-Rank Adaptation (LoRA) to produce the malicious model, it remains unclear whether the attack can still work and pose threats. In this work, we first identify that the attack efficacy is significantly diminished when using LoRA for fine-tuning. Then, we propose LoBAM, a method that yields high attack success rate with minimal training resources. The key idea of LoBAM is to amplify the malicious weights in an intelligent way that effectively enhances the attack efficacy. We demonstrate that our design can lead to improved attack success rate through extensive empirical experiments across various model merging scenarios. Moreover, we show that our method is highly stealthy and is difficult to detect and defend against.

cs.CR↗

arXiv2025

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neuron sparsity reduces high-dimensional computations, both offering promising solutions to enhance efficiency. Recently, these two sparsity paradigms have evolved largely in parallel, fostering the prevailing assumption that they function independently. However, a fundamental yet underexplored question remains: Do they truly operate in isolation, or is there a deeper underlying interplay that has yet to be uncovered? In this paper, we conduct the first comprehensive investigation into this question. By introducing and analyzing the matching mechanism between Core Neurons and Core Tokens, we found that key neurons and tokens for inference mutually influence and reinforce each other. Building on this insight, we propose CoreMatching, a co-adaptive sparse inference framework, which leverages the synergy between token and neuron sparsity to enhance inference efficiency. Through theoretical analysis and efficiency evaluations, we demonstrate that the proposed method surpasses state-of-the-art baselines on ten image understanding tasks and three hardware devices. Notably, on the NVIDIA Titan Xp, it achieved 5x FLOPs reduction and a 10x overall speedup. Code is released at https://github.com/wangqinsi1/2025-ICML-CoreMatching/tree/main.

cs.LG↗

arXiv2025

CONCORD: Concept-Informed Diffusion for Dataset Distillation

Dataset distillation (DD) has witnessed significant progress in creating small datasets that encapsulate rich information from large original ones. Particularly, methods based on generative priors show promising performance, while maintaining computational efficiency and cross-architecture generalization. However, the generation process lacks explicit controllability for each sample. Previous distillation methods primarily match the real distribution from the perspective of the entire dataset, whereas overlooking concept completeness at the instance level. The missing or incorrectly represented object details cannot be efficiently compensated due to the constrained sample amount typical in DD settings. To this end, we propose incorporating the concept understanding of large language models (LLMs) to perform Concept-Informed Diffusion (CONCORD) for dataset distillation. Specifically, distinguishable and fine-grained concepts are retrieved based on category labels to inform the denoising process and refine essential object details. By integrating these concepts, the proposed method significantly enhances both the controllability and interpretability of the distilled image generation, without relying on pre-trained classifiers. We demonstrate the efficacy of CONCORD by achieving state-of-the-art performance on ImageNet-1K and its subsets. The code implementation is released in https://github.com/vimar-gu/CONCORD.

cs.CV↗

arXiv2025

Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks

Spiking Neural Networks (SNNs) are gaining attention for their energy efficiency and biological plausibility, utilizing 0-1 activation sparsity through spike-driven computation. While existing SNN accelerators exploit this sparsity to skip zero computations, they often overlook the unique distribution patterns inherent in binary activations. In this work, we observe that particular patterns exist in spike activations, which we can utilize to reduce the substantial computation of SNN models. Based on these findings, we propose a novel \textbf{pattern-based hierarchical sparsity} framework, termed \textbf{\textit{Phi}}, to optimize computation. \textit{Phi} introduces a two-level sparsity hierarchy: Level 1 exhibits vector-wise sparsity by representing activations with pre-defined patterns, allowing for offline pre-computation with weights and significantly reducing most runtime computation. Level 2 features element-wise sparsity by complementing the Level 1 matrix, using a highly sparse matrix to further reduce computation while maintaining accuracy. We present an algorithm-hardware co-design approach. Algorithmically, we employ a k-means-based pattern selection method to identify representative patterns and introduce a pattern-aware fine-tuning technique to enhance Level 2 sparsity. Architecturally, we design \textbf{\textit{Phi}}, a dedicated hardware architecture that efficiently processes the two levels of \textit{Phi} sparsity on the fly. Extensive experiments demonstrate that \textit{Phi} achieves a $3.45\times$ speedup and a $4.93\times$ improvement in energy efficiency compared to state-of-the-art SNN accelerators, showcasing the effectiveness of our framework in optimizing SNN computation.

cs.AR↗

arXiv2025

AutoRAC: Automated Processing-in-Memory Accelerator Design for Recommender Systems

The performance bottleneck of deep-learning-based recommender systems resides in their backbone Deep Neural Networks. By integrating Processing-In-Memory~(PIM) architectures, researchers can reduce data movement and enhance energy efficiency, paving the way for next-generation recommender models. Nevertheless, achieving performance and efficiency gains is challenging due to the complexity of the PIM design space and the intricate mapping of operators. In this paper, we demonstrate that automated PIM design is feasible even within the most demanding recommender model design space, spanning over $10^{54}$ possible architectures. We propose \methodname, which formulates the co-optimization of recommender models and PIM design as a combinatorial search over mixed-precision interaction operations, and parameterizes the search with a one-shot supernet encompassing all mixed-precision options. We comprehensively evaluate our approach on three Click-Through Rate benchmarks, showcasing the superiority of our automated design methodology over manual approaches. Our results indicate up to a 3.36$\times$ speedup, 1.68$\times$ area reduction, and 12.48$\times$ higher power efficiency compared to naively mapped searched designs and state-of-the-art handcrafted designs.

cs.AR↗

arXiv2025

Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression

Large language models (LLMs) have demonstrated transformative capabilities across diverse artificial intelligence applications, yet their deployment is hindered by substantial memory and computational demands, especially in resource-constrained environments. Quantization techniques have emerged as a critical solution, reducing data precision to enhance memory and computational efficiency. However, existing methods often suffer from high runtime overheads and potential accuracy degradation. To address these challenges, we propose Ecco, an entropy-based cache compression technique tailored for LLMs. Ecco combines group-wise and non-uniform quantization with pre-defined shared k-means patterns and Huffman coding to exploit the inherent entropy characteristics of LLM cache data. Recognizing the inefficiencies of traditional Huffman coding in terms of parallelism and latency, we introduce a novel parallel Huffman-based decoding process with a multi-stage pipeline design, reducing latency by two orders of magnitude and achieving throughput comparable to GPU L2 caches. Comprehensive evaluations demonstrate that Ecco achieves an up to 2.9$\times$ and 1.9$\times$ speedup over the state-of-the-art AWQ and SmoothQuant framework, 2.4$\times$ over the Olive accelerator, all while increasing memory capacity by nearly 4$\times$ and maintaining state-of-the-art LLM accuracy. These results underscore the effectiveness of our entropy-based cache compression in enhancing LLM performance and efficiency, paving the way for more deployable large-scale AI models.

cs.AR↗

arXiv2025

PatternPaint: Practical Layout Pattern Generation Using Diffusion-Based Inpainting

Generating diverse VLSI layout patterns is essential for various downstream tasks in design for manufacturing, as design rules continually evolve during the development of new technology nodes. However, existing training-based methods for layout pattern generation rely on large datasets. In practical scenarios, especially when developing a new technology node, obtaining such extensive layout data is challenging. Consequently, training models with large datasets becomes impractical, limiting the scalability and adaptability of prior approaches. To this end, we propose PatternPaint, a diffusion-based framework capable of generating legal patterns with limited design-rule-compliant training samples. PatternPaint simplifies complex layout pattern generation into a series of inpainting processes with a template-based denoising scheme. Furthermore, we perform few-shot finetuning on a pretrained image foundation model with only 20 design-rule-compliant samples. Experimental results show that using a sub-3nm technology node (Intel 18A), our model is the only one that can generate legal patterns in complex 2D metal interconnect design rule settings among all previous works and achieves a high diversity score. Additionally, our few-shot finetuning can boost the legality rate with 1.87X improvement compared to the original pretrained model. As a result, we demonstrate a production-ready approach for layout pattern generation in developing new technology nodes.

cs.CV↗