arXiv subjects

Yu Gu

Publications and source records attributed to Yu Gu.

At least 127 records · Page 7Linked to original sources

arXiv2025

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Retrieval-Augmented Generation (RAG) enhances the performance of Large Language Models (LLMs) by incorporating external knowledge. However, LLMs still encounter challenges in effectively utilizing the knowledge from retrieved documents, often being misled by irrelevant or noisy information. To address this issue, we introduce RankCoT, a knowledge refinement method that incorporates reranking signals in generating CoT-based summarization for knowledge refinement based on given query and all retrieval documents. During training, RankCoT prompts the LLM to generate Chain-of-Thought (CoT) candidates based on the query and individual documents. It then fine-tunes the LLM to directly reproduce the best CoT from these candidate outputs based on all retrieved documents, which requires LLM to filter out irrelevant documents during generating CoT-style summarization. Additionally, RankCoT incorporates a self-reflection mechanism that further refines the CoT outputs, resulting in higher-quality training data. Our experiments demonstrate the effectiveness of RankCoT, showing its superior performance over other knowledge refinement models. Further analysis reveals that RankCoT can provide shorter but effective refinement results, enabling the generator to produce more accurate answers. All code and data are available at https://github.com/NEUIR/RankCoT.

cs.CL↗

arXiv2025

Exploring the Effects of Traditional Chinese Medicine Scents on Mitigating Driving Fatigue

The rise of autonomous driving technology has led to concerns about inactivity-induced fatigue. This paper explores Traditional Chinese Medicine (TCM) scents for mitigating. Two human-involved studies have been conducted in a high-fidelity driving simulator. Study 1 maps six prevalent TCM scents onto the arousal/valence circumplex to select proper candidates, i.e., argy wormwood (with the highest arousal) and tangerine peel (with the highest valence). Study 2 tests both scents in an auto-driving course. Statistics show both scents can improve driver alertness and reaction-time, but should be used in different ways: argy wormwood is suitable for short-term use due to its higher intensity but poor acceptance, while tangerine peel is ideal for long-term use due to its higher likeness. These findings provide insights for in-car fatigue mitigation to enhance driver safety and well-being. However, issues such as scent longevity as for aromatherapy and automatic fatigue prediction remain unresolved.

cs.HC↗

arXiv2025

Magma: A Foundation Model for Multimodal AI Agents

We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to plan and act in the visual-spatial world (spatial-temporal intelligence) and complete agentic tasks ranging from UI navigation to robot manipulation. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data, where the actionable visual objects (e.g., clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and the object movements (e.g., the trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that SoM and ToM reach great synergy and facilitate the acquisition of spatial-temporal intelligence for our Magma model, which is fundamental to a wide range of tasks as shown in Fig.1. In particular, Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. On image and video-related multimodal tasks, Magma also compares favorably to popular large multimodal models that are trained on much larger datasets. We make our model and code public for reproducibility at https://microsoft.github.io/Magma.

cs.CV↗

arXiv2025

Density-dependent spin susceptibility and effective mass in monolayer MoSe2

Atomically thin MoSe2 is a promising platform for investigating quantum phenomena due to its large effective mass, high crystal quality, and strong spin-orbit coupling. In this work, we demonstrate a triple-gate device design with bismuth contacts, enabling reliable ohmic contact down to low electron densities, with a maximum Hall mobility of approximately 22,000 cm2/Vs. Low-temperature transport measurements illustrate metal-insulator transitions, and density-dependent quantum oscillation sequences. Enhanced spin susceptibility and density-dependent effective mass are observed, attributed to interaction effects and valley polarization. These findings establish monolayer MoSe2 as a versatile platform for further exploring interaction-driven quantum states.

cond-mat.mes-hall↗

arXiv2025

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human debugging typically follows a multi-stage process, which includes Bug Localization, Bug Identification, Code Repair, and Code Recognition. However, existing code debugging benchmarks predominantly focus on the Code Repair stage, which offers only a limited perspective on evaluating the debugging capabilities of LLMs. In this paper, we introduce DEBUGEVAL, a comprehensive benchmark for evaluating the debugging abilities of LLMs by emulating the multi-stage human debugging process. Through evaluating on DEBUGEVAL, we observe that 7B-scale models consistently underperform compared to their larger counterparts, highlighting their limitations in comprehending code semantics. In this case, we propose the COmmunicative Agent-based data SynThesis (COAST) framework, which employs a multi-agent system to generate high-quality training data for supervised fine-tuning (SFT). Experimental results demonstrate that COAST-generated data outperform human-curated and GPT-4-generated data, enabling 7B-scale LLMs to achieve debugging performance comparable to GPT-3.5. All data and codes are available at https://github.com/NEUIR/COAST.

cs.SE↗

arXiv2025

Beyond surveys: A High-Precision Wealth Inequality Mapping of China's Rural Households Derived from Satellite and Street View Imageries

Wide coverage and high-precision rural household wealth data is an important support for the effective connection between the national macro rural revitalization policy and micro rural entities, which helps to achieve precise allocation of national resources. However, due to the large number and wide distribution of rural areas, wealth data is difficult to collect and scarce in quantity. Therefore, this article attempts to integrate "sky" remote sensing images with "ground" village street view imageries to construct a fine-grained "computable" technical route for rural household wealth. With the intelligent interpretation of rural houses as the core, the relevant wealth elements of image data were extracted and identified, and regressed with the household wealth indicators of the benchmark questionnaire to form a high-precision township scale wealth prediction model (r=0.85); Furthermore, a national and township scale map of rural household wealth in China was promoted and drawn. Based on this, this article finds that there is a "bimodal" pattern in the distribution of wealth among rural households in China, which is reflected in a polarization feature of "high in the south and low in the north, and high in the east and low in the west" in space. This technological route may provide alternative solutions with wider spatial coverage and higher accuracy for high-cost manual surveys, promote the identification of shortcomings in rural construction, and promote the precise implementation of rural policies.

econ.GN↗

arXiv2025

The Benchmark Mode $Ω_c \to Ω^-π^+$ and Its Related Processes

The benchmark mode $Ω_c^0\to Ω^- π^+$, which receives purely factorization contribution, is of great importance among all the decay channels of $Ω_c^0$ decays. In this work, within the framework of non-relativistic quark model (NRQM), we calculate all the 6 baryon transition form factors involving $\frac12 ^+\to \frac32 ^+$ decays. The absolute branching fractions of non-leptonic decays $Ω_c^0\to Ω^- π^+$, $Ω_c^0\to Ω^- ρ^+$ and $Ω_c^0\to Ξ^- π^+$ as well as semi-leptonic decays $Ω_c^0\to Ω^- \ell^+ ν_{\ell} \; (\ell=e,μ)$ are calculated although they cannot be measured directly by current experiment. Based on the prediction $\mathcal{B}(Ω_c^0\toΩ^-π^+)=(3.43\pm0.48)\%$ in our work, we further predict the ratios between interested modes and the benchmark mode, giving $R(Ξ^-π^+)=0.16\pm0.06$, $R(Ω^-ρ^+)=5.33\pm0.94$, $R(Ω^- e^+ν_e)=1.18\pm0.22$ and $R(Ω^- μ^+ν_μ)=1.11\pm0.20$. The predictions on $Ω_c^0\to Ξ^-π^+$ and $Ω_c^0\to Ω^- e^+ν$ agree well with recent measured ratios reported by LHCb in 2023 and ALICE in 2024, respectively.

hep-ph↗

arXiv2025

Noise sensitivity for stochastic heat and Schrödinger equation

In this note, we consider the stochastic heat and Schrödinger equation, and show that, at time $t$, the onset of the chaos occurs on the scale of $1/t$, and the Fourier spectrum of the solution is asymptotically Gaussian after centering and rescaling.

math.PR↗

arXiv2025

Improving Accuracy and Generalization for Efficient Visual Tracking

Efficient visual trackers overfit to their training distributions and lack generalization abilities, resulting in them performing well on their respective in-distribution (ID) test sets and not as well on out-of-distribution (OOD) sequences, imposing limitations to their deployment in-the-wild under constrained resources. We introduce SiamABC, a highly efficient Siamese tracker that significantly improves tracking performance, even on OOD sequences. SiamABC takes advantage of new architectural designs in the way it bridges the dynamic variability of the target, and of new losses for training. Also, it directly addresses OOD tracking generalization by including a fast backward-free dynamic test-time adaptation method that continuously adapts the model according to the dynamic visual changes of the target. Our extensive experiments suggest that SiamABC shows remarkable performance gains in OOD sets while maintaining accurate performance on the ID benchmarks. SiamABC outperforms MixFormerV2-S by 7.6\% on the OOD AVisT benchmark while being 3x faster (100 FPS) on a CPU. Our code and models are available at https://wvuvl.github.io/SiamABC/.

cs.CV↗

arXiv2025

Some recent progress on the periodic KPZ equation

We review recent progress on the study of the Kardar-Parisi-Zhang (KPZ) equation in a periodic setting, which describes the random growth of an interface in a cylindrical geometry. The main results include central limit theorems for the height of the interface and the winding number of the directed polymer in a periodic random environment. We present two different approaches for each result, utilizing either a homogenization argument or tools from Malliavin calculus. A surprising finding in the case of a $1+1$ spacetime white noise is that the effective variances for both the height and the winding number can be expressed in terms of independent Brownian bridges. Additionally, we present two new results: (i) the explicit expression of the corrector used in the homogenization argument, and (ii) the law of the iterated logarithm for the height function.

math.PR↗

arXiv2025

HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the impressive accomplishments, large language models (LLMs), even with retrieval-augmented generation (RAG), still struggle to efficiently and effectively integrate a large amount of new experiences after pre-training. In this work, we introduce HippoRAG, a novel retrieval framework inspired by the hippocampal indexing theory of human long-term memory to enable deeper and more efficient knowledge integration over new experiences. HippoRAG synergistically orchestrates LLMs, knowledge graphs, and the Personalized PageRank algorithm to mimic the different roles of neocortex and hippocampus in human memory. We compare HippoRAG with existing RAG methods on multi-hop question answering and show that our method outperforms the state-of-the-art methods remarkably, by up to 20%. Single-step retrieval with HippoRAG achieves comparable or better performance than iterative retrieval like IRCoT while being 10-30 times cheaper and 6-13 times faster, and integrating HippoRAG into IRCoT brings further substantial gains. Finally, we show that our method can tackle new types of scenarios that are out of reach of existing methods. Code and data are available at https://github.com/OSU-NLP-Group/HippoRAG.

cs.CL↗

arXiv2024

NeutronTP: Load-Balanced Distributed Full-Graph GNN Training with Tensor Parallelism

Graph neural networks (GNNs) have emerged as a promising direction. Training large-scale graphs that relies on distributed computing power poses new challenges. Existing distributed GNN systems leverage data parallelism by partitioning the input graph and distributing it to multiple workers. However, due to the irregular nature of the graph structure, existing distributed approaches suffer from unbalanced workloads and high overhead in managing cross-worker vertex dependencies. In this paper, we leverage tensor parallelism for distributed GNN training. GNN tensor parallelism eliminates cross-worker vertex dependencies by partitioning features instead of graph structures. Different workers are assigned training tasks on different feature slices with the same dimensional size, leading to a complete load balance. We achieve efficient GNN tensor parallelism through two critical functions. Firstly, we employ a generalized decoupled training framework to decouple NN operations from graph aggregation operations, significantly reducing the communication overhead caused by NN operations which must be computed using complete features. Secondly, we employ a memory-efficient task scheduling strategy to support the training of large graphs exceeding single GPU memory, while further improving performance by overlapping communication and computation. By integrating the above techniques, we propose a distributed GNN training system NeutronTP. Our experimental results on a 16-node Aliyun cluster demonstrate that NeutronTP achieves 1.29X-8.72X speedup over state-of-the-art GNN systems including DistDGL, NeutronStar, and Sancus.

cs.DC↗

arXiv2024

CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder

Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness. Conventional SVS systems usually utilize an acoustic model to transform a music score into acoustic features, followed by a vocoder to reconstruct the singing voice. It was recently shown that end-to-end modeling is effective in the fields of SVS and Text to Speech (TTS). In this work, we thus present a fully end-to-end SVS method together with a chunkwise streaming inference to address the latency issue for practical usages. Note that this is the first attempt to fully implement end-to-end streaming audio synthesis using latent representations in VAE. We have made specific improvements to enhance the performance of streaming SVS using latent representations. Experimental results demonstrate that the proposed method achieves synthesized audio with high expressiveness and pitch accuracy in both streaming SVS and TTS tasks.

eess.AS↗

arXiv2024

Real-space study of zero-field correlation in tetralayer rhombohedral graphene

Rhombohedral graphene (RG) has emerged as a promising platform for exploring exotic quantum phenomena, such as quantum magnetism, unconventional superconductivity, and fractional quantum anomalous Hall effects. Despite its potential, atomic-scale investigations of RG remain limited, hindering a detailed microscopic understanding of the origins of these correlated states. In this study, we employ scanning probe microscopy and spectroscopy to probe the intrinsic electronic states in trilayer and tetralayer RG. We identify a correlated insulating state with a 17 meV gap at the charge neutrality point in tetralayer RG, which is absent in the trilayer configuration. This gap is suppressed by applying a perpendicular magnetic field or doping the charge carrier density and does not exhibit inter-valley coherence patterns. We attribute this phenomenon to a symmetry-broken layer antiferromagnetic state, characterized by ferrimagnetic ordering in the outermost layers and antiferromagnetic coupling between them. To further investigate this magnetic correlated state, we conduct local scattering experiments. Within the correlated regime, a bound state emerges around a non-magnetic impurity but is absent near magnetic impurities, suggesting that non-magnetic doping induces a spin texture in the ferrimagnetic surface layers. Outside the correlated regime, Friedel oscillations are observed, allowing precise determination of the band dispersion in tetralayer RG. These findings provide atomic-scale evidences of zero-field correlations in RG and may be extended to study other exotic phases in RG.

cond-mat.mes-hall↗

arXiv2024

XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache framework makes a compromise between time and space complexities. However, caching data generates the increasingly growing memory demand, that can quickly exhaust the limited memory capacity of the modern accelerator like GPUs, particularly in long-context inference tasks. Existing studies reduce memory consumption by evicting some of cached data that have less important impact on inference accuracy. But the benefit in practice is far from ideal due to the static cache allocation across different LLM network layers. This paper observes that the layer-specific cached data have very different impacts on accuracy. We quantify this difference, and give experimental and theoretical validation. We accordingly make a formal analysis and shows that customizing the cache size for each layer in a personalized manner can yield a significant memory reduction, while still providing comparable accuracy. We simulate the cache allocation as a combinatorial optimization problem and give a global optimal solution. In particular, we devise a mini- and sampling-based inference over a lightweight variant of the LLM model, so as to quickly capture the difference and then feed it into the personalized algorithms. Extensive experiments on real-world datasets demonstrate that our proposals can reduce KV cache memory consumption by 61.6% on average, improve computational efficiency by 2.1x and then increase the throughput by up to 5.5x.

cs.LG↗

arXiv2024

Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological Oscillations

Biological oscillations are periodic changes in various signaling processes crucial for the proper functioning of living organisms. These oscillations are modeled by ordinary differential equations, with coefficient variations leading to diverse periodic behaviors, typically measured by oscillatory frequencies. This paper explores sampling techniques for neural networks to model the relationship between system coefficients and oscillatory frequency. However, the scarcity of oscillations in the vast coefficient space results in many samples exhibiting non-periodic behaviors, and small coefficient changes near oscillation boundaries can significantly alter oscillatory properties. This leads to non-oscillatory bias and boundary sensitivity, making accurate predictions difficult. While existing importance and uncertainty sampling approaches partially mitigate these challenges, they either fail to resolve the sensitivity problem or result in redundant sampling. To address these limitations, we propose the Hierarchical Gradient-based Genetic Sampling (HGGS) framework, which improves the accuracy of neural network predictions for biological oscillations. The first layer, Gradient-based Filtering, extracts sensitive oscillation boundaries and removes redundant non-oscillatory samples, creating a balanced coarse dataset. The second layer, Multigrid Genetic Sampling, utilizes residual information to refine these boundaries and explore new high-residual regions, increasing data diversity for model training. Experimental results demonstrate that HGGS outperforms seven comparative sampling methods across four biological systems, highlighting its effectiveness in enhancing sampling and prediction accuracy.

cs.LG↗

arXiv2024

Building A Coding Assistant via the Retrieval-Augmented Language Model

Pretrained language models have shown strong effectiveness in code-related tasks, such as code retrieval, code generation, code summarization, and code completion tasks. In this paper, we propose COde assistaNt viA retrieval-augmeNted language model (CONAN), which aims to build a code assistant by mimicking the knowledge-seeking behaviors of humans during coding. Specifically, it consists of a code structure aware retriever (CONAN-R) and a dual-view code representation-based retrieval-augmented generation model (CONAN-G). CONAN-R pretrains CodeT5 using Code-Documentation Alignment and Masked Entity Prediction tasks to make language models code structure-aware and learn effective representations for code snippets and documentation. Then CONAN-G designs a dual-view code representation mechanism for implementing a retrieval-augmented code generation model. CONAN-G regards the code documentation descriptions as prompts, which help language models better understand the code semantics. Our experiments show that CONAN achieves convincing performance on different code generation tasks and significantly outperforms previous retrieval augmented code generation models. Our further analyses show that CONAN learns tailored representations for both code snippets and documentation by aligning code-documentation data pairs and capturing structural semantics by masking and predicting entities in the code data. Additionally, the retrieved code snippets and documentation provide necessary information from both program language and natural language to assist the code generation process. CONAN can also be used as an assistant for Large Language Models (LLMs), providing LLMs with external knowledge in shorter code document lengths to improve their effectiveness on various code tasks. It shows the ability of CONAN to extract necessary information and help filter out the noise from retrieved code documents.

cs.CL↗

arXiv2024

DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis

This paper proposes an improved version of DurIAN-E (DurIAN-E 2), which is also a duration informed attention neural network for expressive and high-fidelity text-to-speech (TTS) synthesis. Similar with the DurIAN-E model, multiple stacked SwishRNN-based Transformer blocks are utilized as linguistic encoders and Style-Adaptive Instance Normalization (SAIN) layers are also exploited into frame-level encoders to improve the modeling ability of expressiveness in the proposed the DurIAN-E 2. Meanwhile, motivated by other TTS models using generative models such as VITS, the proposed DurIAN-E 2 utilizes variational autoencoders (VAEs) augmented with normalizing flows and a BigVGAN waveform generator with adversarial training strategy, which further improve the synthesized speech quality and expressiveness. Both objective test and subjective evaluation results prove that the proposed expressive TTS model DurIAN-E 2 can achieve better performance than several state-of-the-art approaches besides DurIAN-E.

eess.AS↗