2 citations · 7 across the 16 of their papers we have counts for
20 papers
From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents
Shixuan Li, Wei Yang, Peiyu Zhang +7
Long-term memory enables LLM agents to reuse past experiences, yet retrieving relevant memories does not necessarily provide sufficient evidence for answering a query. Essential in…
Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems
Shixuan Li, Wei Yang, Peiyu Zhang +3
Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect effectiv…
HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling
Peiyu Zhang, Heng Ping, Nikos Kanakaris +5
Multi-label classification (MLC) requires predicting multiple relevant labels for each instance, where a central challenge is modeling complex label dependencies arising from co-oc…
Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction
Yu Chang, Anzhe Cheng, Jiahao Chen +8
Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and for identifying functional s…
ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling
Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +5
Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sust…
COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation
Heng Ping, Peiyu Zhang, Shixuan Li +5
LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches universally decouple the two objectives, optimizing P…
POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization
Heng Ping, Peiyu Zhang, Zhenkun Wang +5
Applying large language models (LLMs) to RTL code optimization for improved power, performance, and area (PPA) faces two key challenges: ensuring functional correctness of optimize…
OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization
Arijit Bhattacharjee, Heng Ping, Son Vu Le +3
Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedb…
Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
Wei Yang, Shixuan Li, Heng Ping +3
Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, d…
FITMM: Adaptive Frequency-Aware Multimodal Recommendation via Information-Theoretic Representation Learning
Wei Yang, Rui Zhong, Yiqun Chen +4
Multimodal recommendation aims to enhance user preference modeling by leveraging rich item content such as images and text. Yet dominant systems fuse modalities in the spatial doma…
ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
Anzhe Cheng, Shukai Duan, Shixuan Li +8
Mixture-of-Experts (MoE) architectures expand model capacity by sparsely activating experts but face two core challenges: misalignment between router logits and each expert's inter…
VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation
Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +8
Automation of Register Transfer Level (RTL) design can help developers meet increasing computational demands. Large Language Models (LLMs) show promise for Hardware Description Lan…
HGFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs
Trung-Kien Nguyen, Heng Ping, Shixuan Li +4
The growing interests and applications of graph learning in diverse domains have propelled the development of a unified model generalizing well across different graphs and tasks, k…
HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL
Heng Ping, Shixuan Li, Peiyu Zhang +8
Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, when applied to hardware description languages (HDL), t…
MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation
Anzhe Cheng, Chenzhong Yin, Yu Chang +4
Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is ofte…
Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance
Nikos Kanakaris, Heng Ping, Xiongye Xiao +4
Detecting organized political campaigns is of paramount importance in fighting against disinformation on social media. Existing approaches for the identification of such organized…
A Structure-Aware Framework for Learning Device Placements on Computation Graphs
Shukai Duan, Heng Ping, Nikos Kanakaris +9
Computation graphs are Directed Acyclic Graphs (DAGs) where the nodes correspond to mathematical operations and are used widely as abstractions in optimizations of neural networks.…
Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models
Xiongye Xiao, Heng Ping, Chenyu Zhou +6
In recent years, there has been increasing attention on the capabilities of large models, particularly in handling complex tasks that small-scale models are unable to perform. Nota…
Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks
Anzhe Cheng, Zhenkun Wang, Chenzhong Yin +5
Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological impla…
PerfRL: A Small Language Model Framework for Efficient Code Optimization
Shukai Duan, Nikos Kanakaris, Xiongye Xiao +8
Code optimization is a challenging task requiring a substantial level of expertise from developers. Nonetheless, this level of human capacity is not sufficient considering the rapi…