arXiv subjects

Yingying Sun

Publications and source records attributed to Yingying Sun.

11 recordsLinked to original sources

arXiv2026

MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

Multi-hop question answering is a fundamental challenge in retrieval-augmented generation (RAG), because deriving an answer requires integrating dispersed evidence. Iterative RAG (iRAG) is widely used for this challenge, but existing methods have two limitations. First, most methods still support each reasoning step with single-granularity evidence, making it difficult to balance information density and contextual noise. Second, existing methods often answer the original question only after aggregating evidence retrieved across intermediate steps, so redundant evidence and intermediate retrieval errors may accumulate and degrade the final answer. To address these limitations, we propose MEGRAG, an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph. Offline, MEGRAG links passages to their sentences and extracted triples through a cross-granularity index. Online, it retrieves passages for the current query and selects aligned evidence, starting with compact triples and adding sentence or passage context as needed. MEGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved. If not, it identifies the missing information and formulates a focused next query; otherwise, it stops retrieval and returns the answer. Extensive experiments demonstrate consistent gains over a diverse set of RAG baselines.

cs.AI↗

arXiv2026

Communication-Aware Placement and Pruning for Efficient Mixture-of-Experts Inference

As MoE models scale to hundreds of experts, placement and pruning decisions increasingly dictate communication volume, affecting the performance of distributed inference across GPUs and nodes. We propose CAP (Communication-Aware Assignment and Pruning), a framework that considers computation, communication and accuracy together for efficient MoE inference through expert placement and pruning. It consists of three components: (1) Co-activation driven expert placement, which groups frequently co-activated experts to reduce inter-device and inter-node communication; (2) Communicationcomputation trade-off adjustment, which generates placements with different computational load and communication volume; and (3) Communication-aware expert pruning, which selectively removes routing destinations to reduce communication with limited accuracy degradation. By combining these components, CAP selects an efficient operating strategy for different hardware configurations. Across our single-node and multi-node experiments, it achieves 1.23x - 1.86 x throughput improvement over DeepSeek EPLB and sequential placement in vLLM, and preserves better model accuracy at the same target speedup under lossy acceleration.

cs.DC↗

arXiv2025

FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning

Federated learning (FL) enables multiple clients to collaboratively train a shared global model while preserving the privacy of their local data. Within this paradigm, the intellectual property rights (IPR) of client models are critical assets that must be protected. In practice, the central server responsible for maintaining the global model may maliciously manipulate the global model to erase client contributions or falsely claim sole ownership, thereby infringing on clients' IPR. Watermarking has emerged as a promising technique for asserting model ownership and protecting intellectual property. However, existing FL watermarking approaches remain limited, suffering from potential watermark collisions among clients, insufficient watermark security, and non-intuitive verification mechanisms. In this paper, we propose FLClear, a novel framework that simultaneously achieves collision-free watermark aggregation, enhanced watermark security, and visually interpretable ownership verification. Specifically, FLClear introduces a transposed model jointly optimized with contrastive learning to integrate the watermarking and main task objectives. During verification, the watermark is reconstructed from the transposed model and evaluated through both visual inspection and structural similarity metrics, enabling intuitive and quantitative ownership verification. Comprehensive experiments conducted over various datasets, aggregation schemes, and attack scenarios demonstrate the effectiveness of FLClear and confirm that it consistently outperforms state-of-the-art FL watermarking methods.

cs.LG↗

arXiv2025

The FM Agent

Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic combination of LLM-based reasoning and large-scale evolutionary search to address complex real-world challenges. The core of FM Agent integrates several key innovations: 1) a cold-start initialization phase incorporating expert guidance, 2) a novel evolutionary sampling strategy for iterative optimization, 3) domain-specific evaluators that combine correctness, effectiveness, and LLM-supervised feedback, and 4) a distributed, asynchronous execution infrastructure built on Ray. Demonstrating broad applicability, our system has been evaluated across diverse domains, including operations research, machine learning, GPU kernel optimization, and classical mathematical problems. FM Agent reaches state-of-the-art results autonomously, without human interpretation or tuning -- 1976.3 on ALE-Bench (+5.2\%), 43.56\% on MLE-Bench (+4.0pp), up to 20x speedups on KernelBench, and establishes new state-of-the-art(SOTA) results on several classical mathematical problems. Beyond academic benchmarks, FM Agent shows considerable promise for both large-scale enterprise R\&D workflows and fundamental scientific research, where it can accelerate innovation, automate complex discovery processes, and deliver substantial engineering and scientific advances with broader societal impact.

cs.AI↗

arXiv2025

InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba

Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which often face challenges related to scalability and efficiency. To address these issues, we propose a novel, efficient human-human interaction generation method based on the Mamba framework, designed to meet the demands of effectively capturing long-sequence dependencies while providing real-time feedback. Specifically, we introduce an adaptive spatio-temporal Mamba framework that utilizes two parallel SSM branches with an adaptive mechanism to integrate the spatial and temporal features of motion sequences. To further enhance the model's ability to capture dependencies within individual motion sequences and the interactions between different individual sequences, we develop two key modules: the self-adaptive spatio-temporal Mamba module and the cross-adaptive spatio-temporal Mamba module, enabling efficient feature learning. Extensive experiments demonstrate that our method achieves state-of-the-art results on two interaction datasets with remarkable quality and efficiency. Compared to the baseline method InterGen, our approach not only improves accuracy but also requires a minimal parameter size of just 66M ,only 36% of InterGen's, while achieving an average inference speed of 0.57 seconds, which is 46% of InterGen's execution time.

cs.CV↗

arXiv2025

Strategic priorities for transformative progress in advancing biology with proteomics and artificial intelligence

Artificial intelligence (AI) is transforming scientific research, including proteomics. Advances in mass spectrometry (MS)-based proteomics data quality, diversity, and scale, combined with groundbreaking AI techniques, are unlocking new challenges and opportunities in biological discovery. Here, we highlight key areas where AI is driving innovation, from data analysis to new biological insights. These include developing an AI-friendly ecosystem for proteomics data generation, sharing, and analysis; improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and ultimately enabling AI-empowered virtual cells.

q-bio.OT↗

arXiv2024

MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control

Reinforcement learning methods have proposed promising traffic signal control policy that can be trained on large road networks. Current SOTA methods model road networks as topological graph structures, incorporate graph attention into deep Q-learning, and merge local and global embeddings to improve policy. However, graph-based methods are difficult to parallelize, resulting in huge time overhead. Moreover, none of the current peer studies have deployed dynamic traffic systems for experiments, which is far from the actual situation. In this context, we propose Multi-Scene Aggregation Convolutional Learning for traffic signal control (MacLight), which offers faster training speeds and more stable performance. Our approach consists of two main components. The first is the global representation, where we utilize variational autoencoders to compactly compress and extract the global representation. The second component employs the proximal policy optimization algorithm as the backbone, allowing value evaluation to consider both local features and global embedding representations. This backbone model significantly reduces time overhead and ensures stability in policy updates. We validated our method across multiple traffic scenarios under both static and dynamic traffic systems. Experimental results demonstrate that, compared to general and domian SOTA methods, our approach achieves superior stability, optimized convergence levels and the highest time efficiency. The code is under https://github.com/Aegis1863/MacLight.

cs.MA↗

arXiv2024

Hot electron lifetime exceeds 300 nanoseconds in quantum dots with high quantum efficiency

Hot electrons are theoretically predicted to be long-lived in strongly confined quantum dots, which could play vital roles in quantum dot-based optoelectronics; however, existing photoexcitation transient spectroscopy investigations reveal that their lifetime is less than 1 ps in well-passivated quantum dots because of the ultrafast electron-hole Auger-assisted cooling. Therefore, they are generally considered absent in quantum dot optoelectronic devices. Here, by using our newly developed electrically excited transient absorption spectroscopy, we surprisingly observed abundant hot electrons in both II-VI and III-VI compound quantum dot light-emitting diodes at elevated bias (>4 V), of which the lifetimes reach 59 to 371 ns, lengthened by more than 5 orders of magnitude compared with the photoexcited hot electrons. These results experimentally prove the presence of a strong phonon bottleneck effect, refreshing our understanding of the role of hot electrons in quantum dot optoelectronics.

cond-mat.mes-hall↗

arXiv2019

Rational solutions for three semi-discrete modified Korteweg-de Vries type equations

In this paper, we consider three semi-discrete modified Korteweg-de Vries type equations which are the nonlinear lumped self-dual network equation,the semi-discrete lattice potential modified Korteweg-de Vries equation and a semi-discrete modified Korteweg-de Vries equation. We derive several kinds of exact solutions, in particular rational solutions, in terms of the Casorati determinant for these three equations respectively. For some rational solutions, we present the related asymptotic analysis to understand their dynamics better.

nlin.SI↗

arXiv2018

End to End Performance Analysis of Relay Cooperative Communication Based on Parked Cars

Parking lots (PLs) are usually full with cars. If these cars are formed into a self-organizing vehicular network, they can be new kind of road side units (RSUs) in urban area to provide communication data forwarding between mobile terminals nearby and a base station. However cars in PLs can leave at any time, which is neglected in the existing studies. In this paper, we investigate relay cooperative communication based on parked cars in PLs. Taking the impact of the car's leaving behavior into consideration, we derive the expressions of outage probability in a two-hop cooperative communication and its link capacity. Finally, the numerical results show that the impact of a car's arriving time is greater than the impact of the duration the car has parked on outage probability.

cs.IT↗

arXiv2018

Study on Energy Consumption and Coverage of Hierarchical Cooperation of Small Cell Base Stations in Heterogeneous Networks

The demand for communication services in the era of intelligent terminals is unprecedented and huge. To meet such development, modern wireless communications must provide higher quality services with higher energy efficiency in terms of system capacity and quality of service (QoS), which could be achieved by the high-speed data rate, the wider coverage and the higher band utilization. In this paper, we propose a way to offload users from a macro base station(MBS) with a hierarchical distribution of small cell base stations(SBS). The connection probability is the key indicator of the implementation of the unload operation. Furthermore, we measure the service performance of the system by finding the conditional probability-coverage probability with the certain SNR threshold as the condition, that is, the probability of obtaining the minimum communication quality when the different base stations are connected to the user. Then, user-centered total energy consumption of the system is respectively obtained when the macro base station(MBS) and the small cell base stations(SBS) serve each of the users. The simulation results show that the hierarchical SBS cooperation in heterogeneous networks can provide a higher system total coverage probability for the system with a lower overall system energy consumption than MBS.

cs.IT↗