Publications (32)
Perturbation Theory-Aided Learned Digital Back-Propagation Scheme for Optical Fiber Nonlinearity Compensation
Xiang Lin, Shenghang Luo, Sunish Kumar Orappanpara Soman +4
Derived from the regular perturbation treatment of the nonlinear Schrodinger equation, a machine learning-based scheme to mitigate the intra-channel optical fiber nonlinearity is p…
SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes
Zhenglun Kong, Mufan Qiu, John Boesen +5
Understanding how cellular morphology, gene expression, and spatial context jointly shape tissue function is a central challenge in biology. Image-based spatial transcriptomics tec…
Modulation Classification Using Received Signal's Amplitude Distribution for Coherent Receivers
Xiang Lin, Yahia A. Eldemerdash, Octavia A. Dobre +2
In this letter, we propose a modulation classification algorithm which is based on the received signal's amplitude for coherent optical receivers. The proposed algorithm classifies…
Argus: Evidence Assembly for Scalable Deep Research Agents
Zhen Zhang, Liangcai Su, Zhuo Chen +7
Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of…
Advanced pure tilt actuator for testing tilt-to-length coupling in space-based gravitational wave detection
Xiang Lin, Qi Xia, Peng Qiu +2
Tilt-to-length (TTL) coupling, caused by the jitter of test masses or satellites, is a significant noise source in space-based gravitational wave detection. Calibrating and suppres…
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroMind Team, Song Bai, Lidong Bing +52
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale…
A Machine Learning-Based Detection Technique for Optical Fiber Nonlinearity Mitigation
Abdelkerim Amari, Xiang Lin, Octavia A. Dobre +2
We investigate the performance of a machine learning classification technique, called the Parzen window, to mitigate the fiber nonlinearity in the context of dispersion managed and…
Quasi-monolithic Compact Interferometric Sensor Head Design with Laser Auto-alignment
Xiang Lin, Peng Qiu, Yurong Liang +3
Interferometers play a crucial role in high-precision displacement measurement such as gravitational-wave detection. Conventional interferometer designs require accurate laser alig…
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks
Tasnim Mohiuddin, Prathyusha Jwalapuram, Xiang Lin +1
Although coherence modeling has come a long way in developing novel models, their evaluation on downstream applications for which they are purportedly developed has largely been ne…
A construction method of the quasi-monolithic compact interferometer based on UV-adhesives bonding
Xiang Lin, Hao Yan, Yiqiu Ma +1
Quasi-monolithic interferometers play a crucial role in high-precision measurement experiments, including gravitational wave detection, inertial sensing, vibrometry, and seismology…
Experiment demonstration of tilt-to-length coupling suppression by beam-alignment-mechanism
Peng Qiu, Xiang Lin, Yurong Liang +3
Tilt-to-length (TTL) noise, caused by angular jitter and misalignment, is a major noise source in the inter-satellite interferometer for gravitational wave detection. However, the…
Hierarchical Pointer Net Parsing
Linlin Liu, Xiang Lin, Shafiq Joty +2
Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity. However, the decoder…
Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling
Prathyusha Jwalapuram, Shafiq Joty, Xiang Lin
Given the claims of improved text generation quality across various pre-trained neural models, we consider the coherence evaluation of machine generated text to be one of the princ…
100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
Chong Zhang, Yue Deng, Xiang Lin +8
The recent development of reasoning language models (RLMs) represents a novel evolution in large language models. In particular, the recent release of DeepSeek-R1 has generated wid…
Resurrecting Submodularity for Neural Text Generation
Simeng Han, Xiang Lin, Shafiq Joty
Submodularity is desirable for a variety of objectives in content selection where the current neural encoder-decoder framework is inadequate. However, it has so far not been explor…
Towards More Expressive Spoken LLMs: Fine-Grained Intent Benchmarking and Acoustic-Lexical Decoupled Policy Optimization
Xiang Lin, Tian-Hao Zhang, Chunfeng Wang +3
Spoken emotional dialogue requires a model to understand a user's spoken input and generate a response that is both semantically appropriate and emotionally expressive. This is cha…
Dynamic Scheduled Sampling with Imitation Loss for Neural Text Generation
Xiang Lin, Prathyusha Jwalapuram, Shafiq Joty
State-of-the-art neural text generation models are typically trained to maximize the likelihood of each token in the ground-truth sequence conditioned on the previous target tokens…
RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models
Xiang Lin, Weixin Li, Shu Guo +2
Pre-trained Vision-Language Models (VLMs), \textit{e.g.} CLIP, have become essential tools in multimodal transfer learning. However, fine-tuning VLMs in few-shot scenarios poses si…
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing
Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram +1
We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse segmenter t…
Can Adversarial Network Attack be Defended?
Jinyin Chen, Yangyang Wu, Xiang Lin +1
Machine learning has been successfully applied to complex network analysis in various areas, and graph neural networks (GNNs) based methods outperform others. Recently, adversarial…
STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations
Boyang Fu, George Dasoulas, Sameer Gabbita +5
Predicting how genetic perturbations change cellular state is a core problem for building controllable models of gene regulation. Perturbations targeting the same gene can produce…
Graphfool: Targeted Label Adversarial Attack on Graph Embedding
Jinyin Chen, Xiang Lin, Dunjie Zhang +4
Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classificatio…
Attention-based graph neural networks: a survey
Chengcheng Sun, Chenhao Li, Xiang Lin +4
Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topological structures. In recent years,…
MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization
Xingxuan Li, Yao Xiao, Dianwen Ng +15
Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains,…
Picometer-level quadrangle optical bonding bench for testing interferometric technologies in TianQin
Hao Yan, Xiang Lin, Siyuan Xie
Interferometric techniques are crucial for space-based gravitational wave detection, requiring a picometer-level stable optical bench, precise phasemeter, interstellar transponder…
On the Role of Discreteness in Diffusion LLMs
Ziqi Jin, Bin Wang, Xiang Lin +2
Diffusion models offer appealing properties for language generation, such as parallel decoding and iterative refinement, but the discrete and highly structured nature of text chall…
Fiber Nonlinearity Mitigation via the Parzen Window Classifier for Dispersion Managed and Unmanaged Links
Abdelkerim Amari, Xiang Lin, Octavia A. Dobre +2
Machine learning techniques have recently received significant attention as promising approaches to deal with the optical channel impairments, and in particular, the nonlinear effe…
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
Xiang Lin, Simeng Han, Shafiq Joty
Advanced large-scale neural language models have led to significant success in many language generation tasks. However, the most commonly used training objective, Maximum Likelihoo…
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Shankar Kantharaj, Rixie Tiffany Ko Leong, Xiang Lin +4
Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights t…
N2VSCDNNR: A Local Recommender System Based on Node2vec and Rich Information Network
Jinyin Chen, Yangyang Wu, Lu Fan +4
Recommender systems are becoming more and more important in our daily lives. However, traditional recommendation methods are challenged by data sparsity and efficiency, as the numb…
EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks
Yaguan Qian, Qiqi Shao, Jiamin Wang +5
With the boom of edge intelligence, its vulnerability to adversarial attacks becomes an urgent problem. The so-called adversarial example can fool a deep learning model on the edge…
Robust Faster-than-Nyquist PDM-mQAM Systems with Tomlinson-Harashima Precoding
Deyuan Chang, Oluyemi Omomukuyo, Xiang Lin +3
A training-based channel estimation algorithm is proposed for the faster-than-Nyquist PDM-mQAM (m = 4, 16, 64) systems with Tomlinson-Harashima precoding (THP). This is robust to t…