arXiv subjects

Wei Hu

Publications and source records attributed to Wei Hu.

At least 109 records · Page 6Linked to original sources

arXiv2025

TIM: A Large-Scale Dataset and large Timeline Intelligence Model for Open-domain Timeline Summarization

Open-domain Timeline Summarization (TLS) is crucial for monitoring the evolution of news topics. To identify changes in news topics, existing methods typically employ general Large Language Models (LLMs) to summarize relevant timestamps from retrieved news. While general LLMs demonstrate capabilities in zero-shot news summarization and timestamp localization, they struggle with assessing topic relevance and understanding topic evolution. Consequently, the summarized information often includes irrelevant details or inaccurate timestamps. To address these issues, we propose the first large Timeline Intelligence Model (TIM) for open-domain TLS, which is capable of effectively summarizing open-domain timelines. Specifically, we begin by presenting a large-scale TLS dataset, comprising over 1,000 news topics and more than 3,000 annotated TLS instances. Furthermore, we propose a progressive optimization strategy, which gradually enhance summarization performance. It employs instruction tuning to enhance summarization and topic-irrelevant information filtering capabilities. Following this, it exploits a novel dual-alignment reward learning method that incorporates both semantic and temporal perspectives, thereby improving the understanding of topic evolution principles. Through this progressive optimization strategy, TIM demonstrates a robust ability to summarize open-domain timelines. Extensive experiments in open-domain demonstrate the effectiveness of our TIM.

cs.CL↗

arXiv2025

Hamiltonian transformation for accurate and efficient band structure interpolation

Electronic band structure is a cornerstone of condensed matter physics and materials science. Conventional methods like Wannier interpolation (WI), which are commonly used to interpolate band structures onto dense k-point grids, often encounter difficulties with complex systems, such as those involving entangled bands or topological obstructions. We introduce the Hamiltonian transformation (HT) method, a novel framework that enhances interpolation accuracy by localizing the Hamiltonian. Using a pre-optimized transformation, HT produces a far more localized Hamiltonian than WI-SCDM (where Wannier functions are generated via the selected columns of the density matrix projection), achieving up to two orders of magnitude greater accuracy for entangled bands. Although HT utilizes a slightly larger, nonlocal numerical basis set, its construction is rapid and requires no optimization, resulting in significant computational speedups. These features make HT a more precise, efficient, and robust alternative to WI-SCDM for band structure interpolation, as verified by high-throughput calculations.

cond-mat.mtrl-sci↗

arXiv2025

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering

In this paper, we identify a critical problem, "lost-in-retrieval", in retrieval-augmented multi-hop question answering (QA): the key entities are missed in LLMs' sub-question decomposition. "Lost-in-retrieval" significantly degrades the retrieval performance, which disrupts the reasoning chain and leads to the incorrect answers. To resolve this problem, we propose a progressive retrieval and rewriting method, namely ChainRAG, which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation. Each step in our retrieval and rewriting process builds upon the previous one, creating a seamless chain that leads to accurate retrieval and answers. Finally, all retrieved sentences and sub-question answers are integrated to generate a comprehensive answer to the original question. We evaluate ChainRAG on three multi-hop QA datasets - MuSiQue, 2Wiki, and HotpotQA - using three large language models: GPT4o-mini, Qwen2.5-72B, and GLM-4-Plus. Empirical results demonstrate that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.

cs.CL↗

arXiv2025

Pseudo-Likelihood Ratio Screening based on Network Data with Applications

Social network platforms today generate vast amounts of data, including network structures and a large number of user-defined tags, which reflect users' interests. The dimensionality of these personalized tags can be ultra-high, posing challenges for model analysis in targeted preference analysis. Traditional categorical feature screening methods overlook the network structure, which can lead to incorrect feature set and suboptimal prediction accuracy. This study focuses on feature screening for network-involved preference analysis based on ultra-high-dimensional categorical tags. We introduce the concepts of self-related features and network-related features, defined as those directly related to the response and those related to the network structure, respectively. We then propose a pseudo-likelihood ratio feature screening procedure that identifies both types of features. Theoretical properties of this procedure under different scenarios are thoroughly investigated. Extensive simulations and real data analysis on Sina Weibo validate our findings.

stat.ME↗

arXiv2025

Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates

Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, requiring many bits for compression. This paper proposes a "Denoising Diffusion Probabilistic Model" (DDPM) architecture for point cloud compression (DDPM-PCC) at low bit-rates. A PointNet encoder produces the condition vector for the generation, which is then quantized via a learnable vector quantizer. This configuration allows to achieve a low bitrates while preserving quality. Experiments on ShapeNet and ModelNet40 show improved rate-distortion at low rates compared to standardized and state-of-the-art approaches. We publicly released the code at https://github.com/EIDOSLAB/DDPM-PCC.

cs.CV↗

arXiv2025

Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage their complementary strengths that potentially arise from diverse training data and paradigms. By using consistency as a signal, our strategy dynamically switches between models. Theoretical analysis highlights the efficiency and performance advantages of our strategy. Extensive experiments on six datasets demonstrate that our strategy not only outperforms self-consistency and state-of-the-art multi-agent debate approaches, but also significantly reduces inference costs. Additionally, ModelSwitch requires only a few comparable LLMs to achieve optimal performance and can be extended with verification methods, demonstrating the potential of leveraging multiple LLMs in the generation-verification paradigm.

cs.AI↗

arXiv2025

Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model

''Grokking'' is a phenomenon where a neural network first memorizes training data and generalizes poorly, but then suddenly transitions to near-perfect generalization after prolonged training. While intriguing, this delayed generalization phenomenon compromises predictability and efficiency. Ideally, models should generalize directly without delay. To this end, this paper proposes GrokTransfer, a simple and principled method for accelerating grokking in training neural networks, based on the key observation that data embedding plays a crucial role in determining whether generalization is delayed. GrokTransfer first trains a smaller, weaker model to reach a nontrivial (but far from optimal) test performance. Then, the learned input embedding from this weaker model is extracted and used to initialize the embedding in the target, stronger model. We rigorously prove that, on a synthetic XOR task where delayed generalization always occurs in normal training, GrokTransfer enables the target model to generalize directly without delay. Moreover, we demonstrate that, across empirical studies of different tasks, GrokTransfer effectively reshapes the training dynamics and eliminates delayed generalization, for both fully-connected neural networks and Transformers.

cs.LG↗

arXiv2025

PWDFT-SW: Extending the Limit of Plane-Wave DFT Calculations to 16K Atoms on the New Sunway Supercomputer

First-principles density functional theory (DFT) with plane wave (PW) basis set is the most widely used method in quantum mechanical material simulations due to its advantages in accuracy and universality. However, a perceived drawback of PW-based DFT calculations is their substantial computational cost and memory usage, which currently limits their ability to simulate large-scale complex systems containing thousands of atoms. This situation is exacerbated in the new Sunway supercomputer, where each process is limited to a mere 16 GB of memory. Herein, we present a novel parallel implementation of plane wave density functional theory on the new Sunway supercomputer (PWDFT-SW). PWDFT-SW fully extracts the benefits of Sunway supercomputer by extensively refactoring and calibrating our algorithms to align with the system characteristics of the Sunway system. Through extensive numerical experiments, we demonstrate that our methods can substantially decrease both computational costs and memory usage. Our optimizations translate to a speedup of 64.8x for a physical system containing 4,096 silicon atoms, enabling us to push the limit of PW-based DFT calculations to large-scale systems containing 16,384 carbon atoms.

cs.DC↗

arXiv2025

Building Machine Learning Challenges for Anomaly Detection in Science

Scientific discoveries are often made by finding a pattern or object that was not predicted by the known rules of science. Oftentimes, these anomalous events or objects that do not conform to the norms are an indication that the rules of science governing the data are incomplete, and something new needs to be present to explain these unexpected outliers. The challenge of finding anomalies can be confounding since it requires codifying a complete knowledge of the known scientific behaviors and then projecting these known behaviors on the data to look for deviations. When utilizing machine learning, this presents a particular challenge since we require that the model not only understands scientific data perfectly but also recognizes when the data is inconsistent and out of the scope of its trained behavior. In this paper, we present three datasets aimed at developing machine learning-based anomaly detection for disparate scientific domains covering astrophysics, genomics, and polar science. We present the different datasets along with a scheme to make machine learning challenges around the three datasets findable, accessible, interoperable, and reusable (FAIR). Furthermore, we present an approach that generalizes to future machine learning challenges, enabling the possibility of large, more compute-intensive challenges that can ultimately lead to scientific discovery.

cs.LG↗

arXiv2025

Benign Overfitting in Single-Head Attention

The phenomenon of benign overfitting, where a trained neural network perfectly fits noisy training data but still achieves near-optimal test performance, has been extensively studied in recent years for linear models and fully-connected/convolutional networks. In this work, we study benign overfitting in a single-head softmax attention model, which is the fundamental building block of Transformers. We prove that under appropriate conditions, the model exhibits benign overfitting in a classification setting already after two steps of gradient descent. Moreover, we show conditions where a minimum-norm/maximum-margin interpolator exhibits benign overfitting. We study how the overfitting behavior depends on the signal-to-noise ratio (SNR) of the data distribution, namely, the ratio between norms of signal and noise tokens, and prove that a sufficiently large SNR is both necessary and sufficient for benign overfitting.

cs.LG↗

arXiv2025

Knowledge Graph-Guided Retrieval Augmented Generation

Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based approaches to retrieve isolated relevant chunks, which ignore their intrinsic relationships. In this paper, we propose a novel Knowledge Graph-Guided Retrieval Augmented Generation (KG$^2$RAG) framework that utilizes knowledge graphs (KGs) to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. Specifically, after performing a semantic-based retrieval to provide seed chunks, KG$^2$RAG employs a KG-guided chunk expansion process and a KG-based chunk organization process to deliver relevant and important knowledge in well-organized paragraphs. Extensive experiments conducted on the HotpotQA dataset and its variants demonstrate the advantages of KG$^2$RAG compared to existing RAG-based approaches, in terms of both response quality and retrieval quality.

cs.CL↗

arXiv2025

QMe14S, A Comprehensive and Efficient Spectral Dataset for Small Organic Molecules

Developing machine learning protocols for molecular simulations requires comprehensive and efficient datasets. Here we introduce the QMe14S dataset, comprising 186,102 small organic molecules featuring 14 elements (H, B, C, N, O, F, Al, Si, P, S, Cl, As, Se, Br) and 47 functional groups. Using density functional theory at the B3LYP/TZVP level, we optimized the geometries and calculated properties including energy, atomic charge, atomic force, dipole moment, quadrupole moment, polarizability, octupole moment, first hyperpolarizability, and Hessian. At the same level, we obtained the harmonic IR, Raman and NMR spectra. Furthermore, we conducted ab initio molecular dynamics simulations to generate dynamic configurations and extract nonequilibrium properties, including energy, forces, and Hessians. By leveraging our E(3)-equivariant message-passing neural network (DetaNet), we demonstrated that models trained on QMe14S outperform those trained on the previously developed QM9S dataset in simulating molecular spectra. The QMe14S dataset thus serves as a comprehensive benchmark for molecular simulations, offering valuable insights into structure-property relationships.

physics.chem-ph↗

arXiv2025

Controllable Protein Sequence Generation with LLM Preference Optimization

Designing proteins with specific attributes offers an important solution to address biomedical challenges. Pre-trained protein large language models (LLMs) have shown promising results on protein sequence generation. However, to control sequence generation for specific attributes, existing work still exhibits poor functionality and structural stability. In this paper, we propose a novel controllable protein design method called CtrlProt. We finetune a protein LLM with a new multi-listwise preference optimization strategy to improve generation quality and support multi-attribute controllable generation. Experiments demonstrate that CtrlProt can meet functionality and structural stability requirements effectively, achieving state-of-the-art performance in both single-attribute and multi-attribute protein sequence generation.

cs.AI↗

arXiv2025

Solving Optimal Control Problems of Rigid-Body Dynamics with Collisions Using the Hybrid Minimum Principle

Collisions are common in many dynamical systems with real applications. They can be formulated as hybrid dynamical systems with discontinuities automatically triggered when states transverse certain manifolds. We present an algorithm for the optimal control problem of such hybrid dynamical systems based on solving the equations derived from the hybrid minimum principle (HMP). The algorithm is an iterative scheme following the spirit of the method of successive approximations (MSA), and it is robust to undesired collisions observed in the initial guesses. We propose several techniques to address the additional numerical challenges introduced by the presence of discontinuities. The algorithm is tested on disc collision problems whose optimal solutions exhibit one or multiple collisions. Linear convergence in terms of iteration steps and asymptotic first-order accuracy in terms of time discretization are observed when the algorithm is implemented with the forward-Euler scheme. The numerical results demonstrate that the proposed algorithm has better accuracy and convergence than direct methods based on gradient descent. Furthermore, the algorithm is also simpler, more accurate, and more stable than a deep reinforcement learning method.

math.OC↗

arXiv2025

Deep Learning and Foundation Models for Weather Prediction: A Survey

Physics-based numerical models have been the bedrock of atmospheric sciences for decades, offering robust solutions but often at the cost of significant computational resources. Deep learning (DL) models have emerged as powerful tools in meteorology, capable of analyzing complex weather and climate data by learning intricate dependencies and providing rapid predictions once trained. While these models demonstrate promising performance in weather prediction, often surpassing traditional physics-based methods, they still face critical challenges. This paper presents a comprehensive survey of recent deep learning and foundation models for weather prediction. We propose a taxonomy to classify existing models based on their training paradigms: deterministic predictive learning, probabilistic generative learning, and pre-training and fine-tuning. For each paradigm, we delve into the underlying model architectures, address major challenges, offer key insights, and propose targeted directions for future research. Furthermore, we explore real-world applications of these methods and provide a curated summary of open-source code repositories and widely used datasets, aiming to bridge research advancements with practical implementations while fostering open and trustworthy scientific practices in adopting cutting-edge artificial intelligence for weather prediction. The related sources are available at https://github.com/JimengShi/ DL-Foundation-Models-Weather.

cs.LG↗

arXiv2025

EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed

Non-autoregressive (NAR) automatic speech recognition (ASR) models predict tokens independently and simultaneously, bringing high inference speed. However, there is still a gap in the accuracy of the NAR models compared to the autoregressive (AR) models. In this paper, we propose a single-step NAR ASR architecture with high accuracy and inference speed, called EffectiveASR. It uses an Index Mapping Vector (IMV) based alignment generator to generate alignments during training, and an alignment predictor to learn the alignments for inference. It can be trained end-to-end (E2E) with cross-entropy loss combined with alignment loss. The proposed EffectiveASR achieves competitive results on the AISHELL-1 and AISHELL-2 Mandarin benchmarks compared to the leading models. Specifically, it achieves character error rates (CER) of 4.26%/4.62% on the AISHELL-1 dev/test dataset, which outperforms the AR Conformer with about 30x inference speedup.

cs.SD↗

arXiv2025

Large Scale Finite-Temperature Real-time Time Dependent Density Functional Theory Calculation with Hybrid Functional on ARM and GPU Systems

Ultra-fast electronic phenomena originating from finite temperature, such as nonlinear optical excitation, can be simulated with high fidelity via real-time time dependent density functional theory (rt-TDDFT) calculations with hybrid functional. However, previous rt-TDDFT simulations of real materials using the optimal gauge--known as the parallel transport gauge--have been limited to low-temperature systems with band gaps. In this paper, we introduce the parallel transport-implicit midpoint (PT-IM) method, which significantly accelerates finite-temperature rt-TDDFT calculations of real materials with hybrid function. We first implement PT-IM with hybrid functional in our plane wave code PWDFT, and optimized it on both GPU and ARM platforms to build a solid baseline code. Next, we propose a diagonalization method to reduce computation and communication complexity, and then, we employ adaptively compressed exchange (ACE) method to reduce the frequency of the most expensive Fock exchange operator. Finally, we adopt the ring\_based method and the shared memory mechanism to overlap computation and communication and alleviate memory consumption respectively. Numerical results show that our optimized code can reach 3072 atoms for rt-TDDFT simulation with hybrid functional at finite temperature on 192 computing nodes, the time-to-solution for one time step is 429.3s, which is 41.4 times faster compared to the baseline.

cond-mat.mtrl-sci↗

arXiv2024

AugGS: Self-augmented Gaussians with Structural Masks for Sparse-view 3D Reconstruction

Sparse-view 3D reconstruction is a major challenge in computer vision, aiming to create complete three-dimensional models from limited viewing angles. Key obstacles include: 1) a small number of input images with inconsistent information; 2) dependence on input image quality; and 3) large model parameter sizes. To tackle these issues, we propose a self-augmented two-stage Gaussian splatting framework enhanced with structural masks for sparse-view 3D reconstruction. Initially, our method generates a basic 3D Gaussian representation from sparse inputs and renders multi-view images. We then fine-tune a pre-trained 2D diffusion model to enhance these images, using them as augmented data to further optimize the 3D Gaussians. Additionally, a structural masking strategy during training enhances the model's robustness to sparse inputs and noise. Experiments on benchmarks like MipNeRF360, OmniObject3D, and OpenIllumination demonstrate that our approach achieves state-of-the-art performance in perceptual quality and multi-view consistency with sparse inputs.

cs.CV↗