Publications (103)
From Horizontal Layering to Vertical Integration: A Comparative Study of the AI-Driven Software Development Paradigm
Chi Zhang, Zehan Li, Ziqian Zhong +4
This paper examines the organizational implications of Generative AI adoption in software engineering through a multiple-case comparative study. We contrast two development environ…
Damping dynamics of the centroid oscillation of a relativistic laser pulse in a plasma channel
Yuhui Xia, Zhenan Wang, Ziyao Tang +10
The centroid oscillation of an offset laser pulse propagating in a preformed plasma channel is investigated through theoretical analysis and three-dimensional particle-in-cell simu…
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Ronghao Guo, Chen Lin, Chuming Li +4
One-shot NAS method has attracted much interest from the research community due to its remarkable training efficiency and capacity to discover high performance models. However, the…
GENET: Unleashing the Power of Side Information for Recommendation via Hypergraph Pre-training
Yang Li, Qi'ao Zhao, Chen Lin +3
Recommendation with side information has drawn significant research interest due to its potential to mitigate user feedback sparsity. However, existing models struggle with general…
Observation of Arbitrarily Configurable Nonlinear Topological Modes
Kai Bai, Chen Lin, Jia-Zheng Li +3
Nonlinear topology is an emerging field that combines the intrinsic reconfigurability of nonlinear systems with the robustness of topological protection, offering fertile ground fo…
DeepThink: Aligning Language Models with Domain-Specific User Intents
Yang Li, Mingxuan Luo, Yeyun Gong +4
Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from re…
Local vaccination and systemic tumor suppression via irradiation and manganese adjuvant in mice
Chunyang Lu, Jing Qian, Jianfeng Lv +15
Presently 4T-1 luc cells were irradiated with proton under ultra-high dose rate FLASH or with gamma-ray with conventional dose rate, and then subcutaneous vaccination with or witho…
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Boyu Chen, Peixia Li, Baopu Li +6
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network pro…
Rho-1: Not All Tokens Are What You Need
Zhenghao Lin, Zhibin Gou, Yeyun Gong +8
Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that "9l training". Our ini…
Measuring Gender and Racial Biases in Large Language Models
Jiafu An, Difang Huang, Chen Lin +1
In traditional decision making processes, social biases of human decision makers can lead to unequal economic outcomes for underrepresented social groups, such as women, racial or…
Visual Encoding and Debiasing for CTR Prediction
Si Chen, Chen Lin, Wanxian Guan +7
Extracting expressive visual features is crucial for accurate Click-Through-Rate (CTR) prediction in visual search advertising systems. Current commercial systems use off-the-shelf…
Two-dimensional Dirac nodal-line semimetal protected by symmetry
Xingxia Cui, Yafei Li, Deping Guo +12
Dirac nodal line semimetals (DNLSs) host relativistic quasiparticles in their one-dimensional (1D) Dirac nodal line (DNL) bands that are protected by certain crystalline symmetries…
UWC: Unit-wise Calibration Towards Rapid Network Compression
Chen Lin, Zheyang Li, Bo Peng +4
This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ meth…
The -rationality of and
Chen Lin, Xuejun Guo
In this paper, we construct new families of imaginary and real quadratic fields that are -rational. In the imaginary case, we prove that for any positive integer and any int…
Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation
Yihang Zheng, Bo Li, Zhenghao Lin +6
The development of Large Language Models (LLMs) has revolutionized QA across various industries, including the database domain. However, there is still a lack of a comprehensive be…
Reduce proton energy spread by target ablation
Shuan Zhao, Chen Lin, Jiaer Chen +1
It's shown that, with strong target ablation monoenergetic protons along the laser direction is available during the laser aluminum foil interaction, which is different from the cl…
Dependence of the Radical Dynamics on the Beam Temporal Profile in FLASH Radiotherapy
Jianhan Sun, Xianghui Kong, Jianfeng Lv +6
Purpose: This study aims to investigate the impact of the beam temporal profile on the radical dynamics and inter-track interactions of FLASH radiotherapy, supporting parameter opt…
Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles
Chen Lin, Si Chen, Meifang Zeng +3
Due to the pivotal role of Recommender Systems (RS) in guiding customers towards the purchase, there is a natural motivation for unscrupulous parties to spoof RS for profits. In th…
Active Liquid-Liquid Phase-Separation in a Confining Environment
Chen Lin, Robijn Bruinsma
Active liquid-liquid phase separation (LLPS) in a confining environment is believed to play an important role in cell biology. Recently, it was shown that when active noise at the…
DFT Accuracy on Crystal Structure Prediction with Machine Learning Interatomic Potentials
Laurence I. Midgley, Chen Lin, J. Harry Moore +8
We present an evaluation of CSP-MACE-Ã , a machine learning interatomic potential intended to replace DFT in crystal structure prediction (CSP). We decompose the total energy into…
Positioning of Transparent Targets Using Defocusing Method in a Laser Proton Accelerator
Yinren Shou, Dahui Wang, Pengjie Wang +11
We report a positioning method for transparent targets with an accuracy of \SI{2}{μm} for a compact laser proton accelerator. The positioning system consists of two light-emitting…
Impact of noise on nonlinear-exceptional-point-based sensors
Kai Bai, Chen Lin, Meng Xiao
Nonlinear exceptional points (NEPs), a new type of spectral singularity in nonlinear non-Hermitian systems, are expected to address the noise divergence issue encountered at linear…
A Deep Reinforcement Learning Approach for Interactive Search with Sentence-level Feedback
Jianghong Zhou, Joyce C. Ho, Chen Lin +1
Interactive search can provide a better experience by incorporating interaction feedback from the users. This can significantly improve search accuracy as it helps avoid irrelevant…
Revealing Decurve Flows for Generalized Graph Propagation
Chen Lin, Liheng Ma, Yiyang Chen +3
This study addresses the limitations of the traditional analysis of message-passing, central to graph learning, by defining {\em \textbf{generalized propagation}} with directed and…
Unsupervised Extractive Summarization with Heterogeneous Graph Embeddings for Chinese Document
Chen Lin, Ye Liu, Siyu An +1
In the scenario of unsupervised extractive summarization, learning high-quality sentence representations is essential to select salient sentences from the input document. Previous…
Contrastive Graph Multimodal Model for Text Classification in Videos
Ye Liu, Changchong Lu, Chen Lin +2
The extraction of text information in videos serves as a critical step towards semantic understanding of videos. It usually involved in two steps: (1) text recognition and (2) text…
Improving One-shot NAS by Suppressing the Posterior Fading
Xiang Li, Chen Lin, Chuming Li +4
There is a growing interest in automated neural architecture search (NAS). To improve the efficiency of NAS, previous approaches adopt weight sharing method to force all models sha…
Empowering Chemical Structures with Biological Insights for Scalable Phenotypic Virtual Screening
Xiaoqing Lian, Pengsen Ma, Tengfeng Ma +9
Motivation: The scalable identification of bioactive compounds is essential for contemporary drug discovery. This process faces a key trade-off: structural screening offers scalabi…
Improve Power of Knockoffs with Annotation Information of Covariates
Xiangyu Zhang, Lijun Wang, Changjun Li +2
Genome-wide association studies (GWAS) often find association signals between many genetic variants and traits of interest in a genomic region. Functional annotations of these vari…
Efficient and Universal Neural-Network Decoder for Stabilizer-Based Quantum Error Correction
Gengyuan Hu, Wanli Ouyang, Chao-Yang Lu +2
Scaling quantum computing to practical applications necessitates reliable quantum error correction. Although numerous correction codes have been proposed, the overall correction ef…
Synaptic Strength For Convolutional Neural Network
Chen Lin, Zhao Zhong, Wei Wu +1
Convolutional Neural Networks(CNNs) are both computation and memory intensive which hindered their deployment in mobile devices. Inspired by the relevant concept in neural science…
On the distillablity conjecture in matrix theory
Saiqi Liu, Chen Lin
The distillability conjecture of two-copy 4 by 4 Werner states is one of the main open problems in quantum information. We prove two special cases of the conjecture. The first case…
DETR for Crowd Pedestrian Detection
Matthieu Lin, Chuming Li, Xingyuan Bu +5
Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…
Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning
Jueye Zhang, Chao Yang, Youfang Lai +9
Head-and-neck cancer (HNC) planning is difficult because multiple critical organs-at-risk (OARs) are close to complex targets. Intensity-modulated carbon-ion therapy (IMCT) offers…
First observation of shock waves induced by laser-accelerated proton beams
Yanlyu Fang, Xiaoyun Le, Yang Yan +5
We demonstrate, for the first time, that laser-accelerated protons can induce shock waves in materials. The ultra-short pulse width of laser-driven protons enables them to deposit…
AM-LFS: AutoML for Loss Function Search
Chuming Li, Yuan Xin, Chen Lin +4
Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to…
Adaptive Gradient Method with Resilience and Momentum
Jie Liu, Chen Lin, Chuming Li +4
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some r…
Enhancing Healthcare Search Intent Recognition with Query Representation Learning and Session Context
Harshita Jagdish Sahijwani, Madhav Sigdel, Song Aslan +4
Classifying the intent behind healthcare search queries is crucial for improving the delivery of online healthcare information. The intricate nature of medical search queries, coup…
Revisiting the Broken Symmetry Phase of Solid Hydrogen: A Neural Network Variational Monte Carlo Study
Shengdu Chai, Chen Lin, Xinyang Dong +4
The crystal structure of high-pressure solid hydrogen remains a fundamental open problem. Although the research frontier has mostly shifted toward ultra-high pressure phases above…
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
Mingzhu Shen, Feng Liang, Ruihao Gong +6
Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly focus on designing advan…
Inception Convolution with Efficient Dilation Search
Jie Liu, Chuming Li, Feng Liang +5
As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computa…
QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs
Shupeng Li, Weipeng Lu, Linyun Liu +16
Domain-specific enhancement of Large Language Models (LLMs) within the financial context has long been a focal point of industrial application. While previous models such as Bloomb…
LFQA-E: Carefully Benchmarking Long-form QA Evaluation
Yuchen Fan, Chen Lin, Xin Zhong +11
Long-Form Question Answering (LFQA) involves generating comprehensive, paragraph-level responses to open-ended questions, which poses a significant challenge for evaluation due to…
Efficient Token Pruning for LLaDA-V
Zhewen Wan, Tianchen Song, Chen Lin +2
Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional at…
Delayed Feedback Modeling for Post-Click Gross Merchandise Volume Prediction: Benchmark, Insights and Approaches
Xinyu Li, Sishuo Chen, Guipeng Xv +7
The prediction objectives of online advertisement ranking models are evolving from probabilistic metrics like conversion rate (CVR) to numerical business metrics like post-click gr…
The asymptotic estimation of prime ideals in imaginary quadratic fields and Chebyshev's bias
Chen Lin, Chenhao Tang, Xuejun Guo
We study the asymptotic estimation of prime ideals that satisfy certain congruence and argument conditions in imaginary quadratic fields. We also discuss the phenomenon of Chebyshe…
On the Fractional Parts of Polynomials Modulo
Xuejun Guo, Chen Lin, Zhefeng Xu
We study a half-interval distribution problem for polynomial residues modulo an odd prime : how often the fractional part of lies in the upper half of the unit interva…
From Intention To Implementation: Automating Biomedical Research via LLMs
Yi Luo, Linghang Shi, Yihao Li +4
Conventional biomedical research is increasingly labor-intensive due to the exponential growth of scientific literature and datasets. Artificial intelligence (AI), particularly Lar…
DocReLM: Mastering Document Retrieval with Language Model
Gengchen Wei, Xinle Pang, Tianning Zhang +5
With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information withi…
Online Hyper-parameter Learning for Auto-Augmentation Strategy
Chen Lin, Minghao Guo, Chuming Li +5
Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for Auto-Augmentation (OHL-Auto-Aug), an…
Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Zhenghao Lin, Zihao Tang, Xiao Liu +31
We introduce Sigma, an efficient large language model specialized for the system domain, empowered by a novel architecture including DiffQKV attention, and pre-trained on our metic…
PV-NAS: Practical Neural Architecture Search for Video Recognition
Zihao Wang, Chen Lin, Lu Sheng +2
Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability. Deep neural networks for video tasks is highly customized…
Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches
Yuanzheng Ci, Chen Lin, Lei Bai +1
Contrastive-based self-supervised learning methods achieved great success in recent years. However, self-supervision requires extremely long training epochs (e.g., 800 epochs for M…
HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modification
Yuntao Shi, Yi Luo, Yeyun Gong +1
Large Language Models (LLMs) have achieved remarkable success in various domains. However, when handling long-form text modification tasks, they still face two major problems: (1)…
Evolving Search Space for Neural Architecture Search
Yuanzheng Ci, Chen Lin, Ming Sun +3
The automation of neural architecture design has been a coveted alternative to human experts. Recent works have small search space, which is easier to optimize but has a limited up…
Computation Reallocation for Object Detection
Feng Liang, Chen Lin, Ronghao Guo +4
The allocation of computation resources in the backbone is a crucial issue in object detection. However, classification allocation pattern is usually adopted directly to object det…
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
Zhenghao Lin, Yeyun Gong, Yelong Shen +5
In this paper, we introduce a novel dIffusion language modEl pre-training framework for text generation, which we call GENIE. GENIE is a large-scale pretrained diffusion language m…
Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting
Chen Lin, Zhichao Ouyang, Junqing Zhuang +3
Automatic code summarization frees software developers from the heavy burden of manual commenting and benefits software development and maintenance. Abstract Syntax Tree (AST), whi…
Cross Learning between Electronic Structure Theories for Unifying Molecular, Surface, and Inorganic Crystal Foundation Force Fields
Ilyes Batatia, Chen Lin, Joseph Hart +5
Creating a single unified interatomic potential capable of attaining ab initio accuracy across all chemistry remains a long-standing challenge in computational chemistry and materi…
Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs
Yi Luo, Qiwen Wang, Junqi Yang +5
Generalized Category Discovery (GCD) aims to classify both known and novel categories using partially labeled data that contains only known classes. Despite achieving strong perfor…
PROD: Progressive Distillation for Dense Retrieval
Zhenghao Lin, Yeyun Gong, Xiao Liu +8
Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the s…
Low-overhead pieceable fault-tolerant construction of logical controlled-phase circuit for degenerate quantum code
Chen Lin, Guowu Yang
We designed an search algorithm in order to find a non-transversal but fault-tolerant construction of a logical controlled-phase gate for general [[n,1,d]] degenerate quantum code.…
Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation
Peng Ye, Baopu Li, Tao Chen +6
Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal n…
Ultra-short lifetime isomer studies from photonuclear reactions using laser-driven ultra-intense γ-ray
Di Wu, Haoyang Lan, Jiaxing Liu +29
Isomers, ubiquitous populations of relatively long-lived nuclear excited states, play a crucial role in nuclear physics. However, isomers with half-life times of several seconds or…
Improving Auto-Augment via Augmentation-Wise Weight Sharing
Keyu Tian, Chen Lin, Ming Sun +3
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search i…
Modeling Cascaded Delay Feedback for Online Net Conversion Rate Prediction: Benchmark, Insights and Solutions
Mingxuan Luo, Guipeng Xv, Sishuo Chen +8
In industrial recommender systems, conversion rate (CVR) is widely used for traffic allocation, but it fails to fully reflect recommendation effectiveness because it ignores refund…
SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image
Yan Hu, Zhongxi Qiu, Dan Zeng +3
Vascular segmentation extracts blood vessels from images and serves as the basis for diagnosing various diseases, like ophthalmic diseases. Ophthalmologists often require high-reso…
FLEN: Leveraging Field for Scalable CTR Prediction
Wenqiang Chen, Lizhang Zhan, Yuanlong Ci +3
Click-Through Rate (CTR) prediction has been an indispensable component for many industrial applications, such as recommendation systems and online advertising. CTR prediction syst…
A foundation model for atomistic materials chemistry
Ilyes Batatia, Philipp Benner, Yuan Chiang +85
Atomistic simulations of matter, especially those that leverage first-principles (ab initio) electronic structure theory, provide a microscopic view of the world, underpinning much…
Efficient light-emitting diodes based on oriented perovskite nanoplatelets
Jieyuan Cui, Yang Liu, Yunzhou Deng +15
Solution-processed planar perovskite light-emitting diodes (LEDs) promise high-performance and cost-effective electroluminescent (EL) devices ideal for large-area display and light…
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
Jiashuo Sun, Chengjin Xu, Lumingyuan Tang +6
Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep an…
HDTSA: An R package for high-dimensional time series analysis
Jinyuan Chang, Jing He, Chen Lin +1
High-dimensional time series analysis has become increasingly important in fields such as finance, economics, and biology. The two primary tasks for high-dimensional time series an…
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
Keyu Tian, Yi Jiang, Qishuai Diao +3
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution…
AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators
Xingwei He, Zhenghao Lin, Yeyun Gong +7
Many natural language processing (NLP) tasks rely on labeled data to train machine learning models with high performance. However, data annotation is time-consuming and expensive,…
Competition-Level Problems are Effective LLM Evaluators
Yiming Huang, Zhenghao Lin, Xiao Liu +8
Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about these abilities and the potential data contamination problem rec…
Counting Polynomial-type Exceptional Units on Algebraic Varieties over Number Fields
Chen Lin, Kaihan Tang
Previous research on exceptional units has primarily focused on the ring of rational integers or abstract finite rings, often restricted to linear or quadratic constraints. In this…
Impact of Residual Angular Chirp in a Petawatt-class Laser System on Laser-driven Proton Acceleration
Qingfan Wu, Minjian Wu, Jiarui Zhao +25
The paper shows that a small residual angular chirp caused by misaligned grating compressors in a petawatt laser degrades the focal spot and reduces proton energies, and that remov…
GLiT: Neural Architecture Search for Global and Local Image Transformer
Boyu Chen, Peixia Li, Chuming Li +6
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones a…
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
Yi Luo, Zhenghao Lin, Yuhao Zhang +7
Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques in…
LOCR: Location-Guided Transformer for Optical Character Recognition
Yu Sun, Dongzhan Zhou, Chen Lin +3
Academic documents are packed with texts, equations, tables, and figures, requiring comprehensive understanding for accurate Optical Character Recognition (OCR). While end-to-end O…
From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
Jiahao Wang, Weiyu Xie, Mingxing Zhang +10
Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to hi…
Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis
Shuai Fan, Chen Lin, Haonan Li +6
Most existing pre-trained language representation models (PLMs) are sub-optimal in sentiment analysis tasks, as they capture the sentiment information from word-level while under-c…
BN-NAS: Neural Architecture Search with Batch Normalization
Boyu Chen, Peixia Li, Baopu Li +5
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required b…
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
Ziyi Lin, Chris Liu, Renrui Zhang +13
We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings. First, for stronger vision-languag…
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
Jiashuo Sun, Hang Zhang, Chen Lin +3
Long-form numerical reasoning in financial analysis aims to generate a reasoning program to calculate the correct answer for a given question. Previous work followed a retriever-ge…
Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels
Si Chen, Yuqiu Qian, Hui Li +1
Online gaming is growing faster than ever before, with increasing challenges of providing better user experience. Recommender systems (RS) for online games face unique challenges s…
HotLoop Optimization of Petawatt Laser Focal Spot via a Twin-Focus Scheme
Qingfan Wu, Ying Gao, Minjian Wu +25
Achieving diffraction-limited focusing of high-power laser pulses to generate ultra-high intensities is crucial for developing compact laser-driven particle accelerators and explor…
Implicit Neural Representations for Chemical Reaction Paths
Kalyan Ramakrishnan, Lars L. Schaaf, Chen Lin +2
We show that neural networks can be optimized to represent minimum energy paths as continuous functions, offering a flexible alternative to discrete path-search methods such as Nud…
Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback
Guipeng Xv, Xinyu Li, Ruobing Xie +5
Multi-modal recommender systems (MRSs) are pivotal in diverse online web platforms and have garnered considerable attention in recent years. However, previous studies overlook the…
Matrix Kloosterman sums and product-trace estimates for semisimple algebras
Xuejun Guo, Chen Lin, Chenhao Tang
Let , and . For , and , let be the number of $r…
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models
Jiashuo Sun, Yi Luo, Yeyun Gong +4
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. H…
Group-Average and Convex Clustering for Partially Heterogeneous Linear Regression
Lu Lin, Jun Lu, Chen Lin
In this paper, a subgroup least squares and a convex clustering are introduced for inferring a partially heterogenous linear regression that has potential application in the areas…
An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework
Zeyu Wang, Frank P. -W. Lo, Qian Chen +7
Existing LLM-enabled multi-agent frameworks are predominantly limited to digital or simulated environments and confined to narrowly focused knowledge domain, constraining their app…
Self-consistent Validation for Machine Learning Electronic Structure
Gengyuan Hu, Gengchen Wei, Zekun Lou +4
Machine learning has emerged as a significant approach to efficiently tackle electronic structure problems. Despite its potential, there is less guarantee for the model to generali…
ThinkRec: Thinking-based recommendation via LLM
Qihang Yu, Kairui Fu, Zheqi Lv +6
Recent advances in large language models (LLMs) have enabled more semantic-aware recommendations through natural language generation. Existing LLM for recommendation (LLM4Rec) meth…
Scalable Equilibrium Sampling with Sequential Boltzmann Generators
Charlie B. Tan, Avishek Joey Bose, Chen Lin +3
Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann generators tackle this problem by pairing normaliz…
Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
Peng Gao, Le Zhuo, Dongyang Liu +17
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lac…
Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries: Deep Learning-Based Time Series Forecasting
Chen Lin, Safoora Yousefi, Elvis Kahoro +4
Real-time air pollution monitoring is a valuable tool for public health and environmental surveillance. In recent years, there has been a dramatic increase in air pollution forecas…
FAAR: Format-Aware Adaptive Rounding for NVFP4
Hanglin Li, Shuchang Tian, Chen Lin +2
Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing me…
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
Chen Lin, Kedi Chen, Wei Zhang
On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally r…