papers

Publications (33)

cs.DC2026

QoSFlow: Ensuring Service Quality of Distributed Workflows Using Interpretable Sensitivity Models

Md Hasanur Rashid, Jesun Firoz, Nathan R. Tallent +3

With the increasing importance of distributed scientific workflows, there is a critical need to ensure Quality of Service (QoS) constraints, such as minimizing time or limiting exe…

cs.CV2018

Normalized Cut Loss for Weakly-supervised CNN Segmentation

Meng Tang, Abdelaziz Djelouah, Federico Perazzi +2

Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supe…

cs.LG2019

Beyond Gradient Descent for Regularized Segmentation Losses

Dmitrii Marin, Meng Tang, Ismail Ben Ayed +1

The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly…

physics.app-ph2026

Ultralong Octupole Moment Switching Driven by Twin Topological Spin

Shijie Xu, Zhizhong Zhang, Yan Huang +10

Spintronics has emerged as a revolutionary frontier in the pursuit of faster, more energy-efficient, and technologically advanced electronics.

cs.LG2021

Deep-learning-based coupled flow-geomechanics surrogate model for CO sequestration

Meng Tang, Xin Ju, Louis J. Durlofsky

A deep-learning-based surrogate model capable of predicting flow and geomechanical responses in CO2 storage operations is presented and applied. The 3D recurrent R-U-Net model comb…

cs.CV2023

Latent Space Editing in Transformer-Based Flow Matching

Vincent Tao Hu, David W Zhang, Pascal Mettes +3

This paper strives for image editing via generative models. Flow Matching is an emerging generative modeling technique that offers the advantage of simple and efficient training. S…

cs.LG2019

Multiphase flow prediction with deep neural networks

Gege Wen, Meng Tang, Sally M. Benson

This paper proposes a deep neural network approach for predicting multiphase flow in heterogeneous domains with high computational efficiency. The deep neural network model is able…

physics.app-ph2025

Field Free Spin-Orbit Torque Controlled Synapse and Stochastic Neuron Devices for Spintronic Boltzmann Neural Networks

Aijaz H. Lone, Meng Tang, Camelia Florica +4

Spintronics offers a promising approach to energy efficient neuromorphic computing by integrating the functionalities of synapses and neurons within a single platform. A major chal…

cond-mat.mtrl-sci2026

A ferroelectric junction transistor memory made from switchable van der Waals p-n heterojunctions

Baoyu Wang, Lingrui Zou, Tao Wang +18

Van der Waals (vdW) p-n heterojunctions are important building blocks for advanced electronics and optoelectronics, in which high-quality heterojunctions essentially determine devi…

cs.LG2019

A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems

Meng Tang, Yimin Liu, Louis J. Durlofsky

A deep-learning-based surrogate model is developed and applied for predicting dynamic subsurface flow in channelized geological models. The surrogate model is based on deep convolu…

cs.CV2026

Pursuing Minimal Sufficiency in Spatial Reasoning

Yejie Guo, Yunzhong Hou, Wufei Ma +2

Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: in…

cond-mat.mtrl-sci2019

Angular characterization of spin-orbit torque and thermoelectric effects

Huanglin Yang, Huanjian Chen, Meng Tang +2

Arising from the interplay between charge, spin and orbital of electrons, spin-orbit torque (SOT) has attracted immense interest in the past decade. Despite vast progress, the exis…

stat.ML2017

Kernel clustering: density biases and solutions

Dmitrii Marin, Meng Tang, Ismail Ben Ayed +1

Kernel methods are popular in clustering due to their generality and discriminating power. However, we show that many kernel clustering criteria have density biases theoretically e…

physics.comp-ph2020

Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow

Meng Tang, Yimin Liu, Louis J. Durlofsky

Data assimilation in subsurface flow systems is challenging due to the large number of flow simulations often required, and by the need to preserve geological realism in the calibr…

cs.CV2026

Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

Shuaishuai Cao, Shuwei Peng, Meng Tang +5

Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misaligned; high overlap scores ma…

cs.CV2020

FroDO: From Detections to 3D Objects

Kejie Li, Martin Rünz, Meng Tang +8

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects.…

physics.app-ph2024

Magnetic Field Gated and Current Controlled Spintronic Mem-transistor Neuron -based Spiking Neural Networks

Aijaz H. Lone, Meng Tang, Daniel N. Rahimi +5

Spintronic devices, such as the domain walls and skyrmions, have shown significant potential for applications in energy-efficient data storage and beyond CMOS computing architectur…

cs.CV2025

ReDistill: Residual Encoded Distillation for Peak Memory Reduction of CNNs

Fang Chen, Gourav Datta, Mujahid Al Rafi +2

The expansion of neural network sizes and the enhanced resolution of modern image sensors result in heightened memory and power demands to process modern computer vision models. In…

cs.CV2024

Training Class-Imbalanced Diffusion Model Via Overlap Optimization

Divin Yan, Lu Qi, Vincent Tao Hu +2

Diffusion models have made significant advances recently in high-quality image synthesis and related tasks. However, diffusion models trained on real-world datasets, which often fo…

cs.AI2026

Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference

Nenad Banfic, David Fan, Kunal Vaishnavi +5

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on…

cs.CV2024

ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation

Jacob Schnell, Jieke Wang, Lu Qi +2

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthe…

cond-mat.mtrl-sci2025

Manipulating magnetization by orbital current from a light metal Ti

Dongxing Zheng, Jingkai Xu, Fatimah Alsayafi +16

The orbital Hall effect, which does not rely on the spin-orbit coupling, has recently emerged as a promising mechanism for electrically manipulating magnetization in thin-film ferr…

cs.CV2018

On Regularized Losses for Weakly-supervised CNN Segmentation

Meng Tang, Federico Perazzi, Abdelaziz Djelouah +3

Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segment…

cs.CV2019

Constrained-CNN losses for weakly supervised segmentation

Hoel Kervadec, Jose Dolz, Meng Tang +3

Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need fo…

cs.CL2019

Learning Compressed Sentence Representations for On-Device Text Processing

Dinghan Shen, Pengyu Cheng, Dhanasekar Sundararaman +5

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations a…

eess.IV2020

Scannerless non-line-of-sight three dimensional imaging with a 32x32 SPAD array

Chenfei Jin, Meng Tang, Legeng Jia +4

We develop a scannerless non-line-of-sight three dimensional imaging system based on a commercial 32x32 SPAD camera combined with a 70 ps pulsed laser. In our experiment, 1024 time…

cs.CV2025

Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects

Weimin Qiu, Jieke Wang, Meng Tang

Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based ima…

cs.CV2026

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

Fang Chen, Alex Villa, Gongbo Liang +3

Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse…

cond-mat.mtrl-sci2021

Efficient field-free perpendicular magnetization switching by a magnetic spin Hall effect

Shuai Hu, Ding-Fu Shao, Huanglin Yang +6

Current induced spin-orbit torques driven by the conventional spin Hall effect are widely used to manipulate the magnetization. This approach, however, is nondeterministic and inef…

cs.CL2022

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents

Yicheng Zou, Hongwei Liu, Tao Gui +5

Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most s…

cond-mat.mtrl-sci2025

Orbital Current-Driven Magnetization Switching in a Magnetic Tunnel Junction

Jingkai Xu, Dongxing Zheng, Meng Tang +9

Spin-orbitronics, based on both spin and orbital angular momentum, presents a promising pathway for energy-efficient memory and logic devices. Recent studies have demonstrated the…

cs.CV2016

Kernel Cuts: MRF meets Kernel & Spectral Clustering

Meng Tang, Dmitrii Marin, Ismail Ben Ayed +1

We propose a new segmentation model combining common regularization energies, e.g. Markov Random Field (MRF) potentials, and standard pairwise clustering criteria like Normalized C…

cs.CL2025

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

Huyu Wu, Meng Tang, Xinhan Zheng +1

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a diverse range of multimodal tasks. However, these models suffer from a core problem know…