Tootfinder

A10 - Breakdown
BLAKE: Jenna? [Gan throws Jenna to the floor] Jenna. Jenna! [Gan drags Jenna to front of flight deck]
BLAKE: Gan! Gan, it's me, Blake. Gan, listen to me. [Gan attacks Blake. Avon, Cally, and Vila run in. Avon and Vila pull Gan off Blake]
https://blake.torpidity.net/m/110/9

Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?
Hui-Peng Du, Yang Ai, Rui-Chen Zheng, Ye-Xin Lu, Zhen-Hua Ling
https://arxiv.org/abs/2508.07711 https://

Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?
Recently, mainstream mel-spectrogram-based neural vocoders rely on generative adversarial network (GAN) for high-fidelity speech generation, e.g., HiFi-GAN and BigVGAN. However, the use of GAN restricts training efficiency and model complexity. Therefore, this paper proposes a novel FreeGAN vocoder, aiming to answer the question of whether GAN is necessary for mel-spectrogram-based neural vocoders. The FreeGAN employs an amplitude-phase serial prediction framework, eliminating the need for GAN …

GaN/InN HEMT based UV photodetector on SiC with hexagonal boron nitride passivation
Mustafa Kilin, Firat Yasar
https://arxiv.org/abs/2508.06782 https://arx…

GaN/InN HEMT based UV photodetector on SiC with hexagonal boron nitride passivation
This work presents a novel Gallium nitride (GaN) high-electron-mobility transistor (HEMT) based ultraviolet photodetector architecture integrating advanced material and structural design strategies to enhance detection performance and stability under room-temperature operation. The device is constructed on a high-thermal-conductivity silicon carbide (SiC) substrate and incorporates an n-GaN buffer, an indium nitride (InN) channel layer for improved electron mobility and two-dimensional electron…

I first read CoolGaY on an ad.
https://www.infineon.com/products/power/gallium-nitride/gan-bidirectional-switches/high-voltage-gan-bidirectional-switches

High-voltage GaN bidirectional switches | Infineon Technologies
Learn more about monolithic bidirectional switches based on GaN technology 650V

Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Seyed Muhammad Hossein Mousavi, S. Younes Mirinezhad
https://arxiv.org/abs/2508.09188

Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation
Affective computing faces a major challenge: the lack of high-quality, diverse depth facial datasets for recognizing subtle emotional expressions. We propose a framework for synthetic depth face generation using an optimized GAN with Knowledge Distillation (EMA teacher models) to stabilize training, improve quality, and prevent mode collapse. We also apply Genetic Algorithms to evolve GAN latent vectors based on image statistics, boosting diversity and visual quality for target emotions. The ap…

Rankin-Selberg integrals for $\mathrm{GSpin}$ groups with application to the global Gan-Gross-Prasad conjecture
Pan Yan
https://arxiv.org/abs/2508.09066 https://

Rankin-Selberg integrals for $\mathrm{GSpin}$ groups with application to the global Gan-Gross-Prasad conjecture
We construct Rankin-Selberg integrals using Bessel models for a product of tensor product partial $L$-functions \begin{equation*} L^S(s,π\timesτ_1) L^S(s,π\timesτ_2)\cdots L^S(s,π\timesτ_r) \end{equation*} where $π$ is an irreducible cuspidal automorphic representation of a quasi-split $\mathrm{GSpin}$ group, and $τ_1, \cdots, τ_r$ are irreducible unitary cuspidal automorphic representations of $\mathrm{GL}_{k_1}, \cdots, \mathrm{GL}_{k_r}$ respectively. As an application, we prove one…

Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example
Yahya Sherif Solayman Mohamed Saleh, Ahmed Mohammed Dabbous, Lama Alkhaled, Hum Yan Chai, Muhammad Ehsan Rana, Hamam Mokayed
https://arxiv.org/abs/2508.08892

Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example
One of the fastest-growing domains in AI is healthcare. Given its importance, it has been the interest of many researchers to deploy ML models into the ever-demanding healthcare domain to aid doctors and increase accessibility. Delivering reliable models, however, demands a sizable amount of data, and the recent COVID-19 pandemic served as a reminder of the rampant and scary nature of healthcare that makes training models difficult. To alleviate such scarcity, many published works attempted to …

Haitian Gang Leader 'Barbecue' Indicted for Conspiracy to Violate U.S. Sanctions (US Department of Justice)
https://www.justice.gov/opa/pr/haitian-gang-leader-barbecue-indicted-conspiracy-violate-us-sanctions
http://www.memeorandum.com/250812/p143#a250812p143

Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why
Chenhao Li, Marco Hutter, Andreas Krause
https://arxiv.org/abs/2507.05906 https://…

Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why
This survey provides a comparative analysis of feature-based and GAN-based approaches to learning from demonstrations, with a focus on the structure of reward functions and their implications for policy learning. Feature-based methods offer dense, interpretable rewards that excel at high-fidelity motion imitation, yet often require sophisticated representations of references and struggle with generalization in unstructured settings. GAN-based methods, in contrast, use implicit, distributional s…

Controlling GaN nucleation via O$_2$-plasma-perforated graphene masks on c-plane sapphire
Su Young An, Chinkyo Kim
https://arxiv.org/abs/2509.08275 https://

Controlling GaN nucleation via O$_2$-plasma-perforated graphene masks on c-plane sapphire
Atomically thin, perforated graphene on $c$-plane sapphire functions as a nanoscale mask that enables GaN growth through thru-holes. We tune the perforated-area fraction $f_p$ by controlled O$_2$-plasma exposure and quantify its impact on early-stage nucleation: the nucleation-site density scales with $f_p$, while the nucleation-delay time decreases approximately as $1/f_p$. Time-resolved areal coverage and domain counts exhibit systematic $f_p$-dependent trends. A kinetic Monte Carlo (kMC) mod…

DepthVision: Robust Vision-Language Understanding through GAN-Based LiDAR-to-RGB Synthesis
Sven Kirchner, Nils Purschke, Ross Greer, Alois C. Knoll
https://arxiv.org/abs/2509.07463

DepthVision: Robust Vision-Language Understanding through GAN-Based LiDAR-to-RGB Synthesis
Ensuring reliable robot operation when visual input is degraded or insufficient remains a central challenge in robotics. This letter introduces DepthVision, a framework for multimodal scene understanding designed to address this problem. Unlike existing Vision-Language Models (VLMs), which use only camera-based visual input alongside language, DepthVision synthesizes RGB images from sparse LiDAR point clouds using a conditional generative adversarial network (GAN) with an integrated refiner net…

Robust quantum computational advantage with programmable 3050-photon Gaussian boson sampling
Hua-Liang Liu, Hao Su, Si-Qiu Gong, Yi-Chao Gu, Hao-Yang Tang, Meng-Hao Jia, Qian Wei, Yukun Song, Dongzhou Wang, Mingyang Zheng, Faxi Chen, Libo Li, Siyu Ren, Xuezhi Zhu, Meihong Wang, Yaojian Chen, Yanfei Liu, Longsheng Song, Pengyu Yang, Junshi Chen, Hong An, Lei Zhang, Lin Gan, Guangwen Yang, Jia-Min Xu, Yu-Ming He, Hui Wang, Han-Sen Zhong, Ming-Cheng Chen, Xiao Jiang, Li Li, Nai-Le Liu, Yu…

Robust quantum computational advantage with programmable 3050-photon Gaussian boson sampling
The creation of large-scale, high-fidelity quantum computers is not only a fundamental scientific endeavour in itself, but also provides increasingly robust proofs of quantum computational advantage (QCA) in the pres- ence of unavoidable noise and the dynamic competition with classical algorithm improvements. To overcome the biggest challenge of photon-based QCA experiments, photon loss, we report new Gaussian boson sampling (GBS) experiments with 1024 high-efficiency squeezed states injected i…

Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases
Ning Li, Kounianhua Du, Han Zhang, Quan Gan, Minjie Wang, David Wipf, Weinan Zhang
https://arxiv.org/abs/2508.08327

Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases
Relational databases (RDBs) have become the industry standard for storing massive and heterogeneous data. However, despite the widespread use of RDBs across various fields, the inherent structure of relational databases hinders their ability to benefit from flourishing deep learning methods. Previous research has primarily focused on exploiting the unary dependency among multiple tables in a relational database using the primary key - foreign key relationships, either joining multiple tables in…

Euler-type methods for Levy-driven McKean-Vlasov SDEs with super-linear coefficients: mean-square error analysis
Jingtao Zhu, Yuying Zhao, Siqing Gan
https://arxiv.org/abs/2509.09302

Euler-type methods for Levy-driven McKean-Vlasov SDEs with super-linear coefficients: mean-square error analysis
We develop and analyze a general class of Euler-type numerical schemes for Levy-driven McKean-Vlasov stochastic differential equations (SDEs), where the drift, diffusion and jump coefficients grow super-linearly in the state variable. These numerical schemes are derived by incorporating projections or nonlinear transformations into the classical Euler method, with the primary objective of establishing moment bounds for the numerical solutions. This class of schemes includes the tanh-Euler, tame…

#Blakes7 Series A, Episode 02 - Space Fall
VILA: Now I want to show you a little trick here. Right, Gan. You know this one.
DAINER: Now, I'll watch carefully this time.
VILA: Right, now watch carefully, watch the old piece of cloth, right... And a one...

Magnetic fields in galactic environments probed by Fast Radio Bursts
Ilya S. Khrykin, Nicolas Tejos, J. Xavier Prochaska, Alexandra Mannings, Lluis Mas-Ribas, Kentaro Nagamine, Khee-Gan Lee, Bryan Gaensler, Zhao Joseph Zhang, Lucas Bernales-Cortes
https://arxiv.org/abs/2509.08896

Magnetic fields in galactic environments probed by Fast Radio Bursts
FRBs constitute a unique probe of various astrophysical and cosmological environments via their characteristic dispersion and rotation (RM) measures that encode information about the ionized gas traversed by the FRB sightlines. In this work, we analyse observed RM measured for 14 localized FRBs at $0.05 \lesssim z \lesssim 0.5$, to infer total magnetic fields in various galactic environments. Additionally, we calculate $f_{\rm gas}$ - the average fraction of halo baryons in the ionized CGM. We …

Replaced article(s) found for physics.ins-det. https://arxiv.org/list/physics.ins-det/new
[1/1]:
- Enhanced UV Detection in GaN-Based Photodetectors through InN/AlN Heterostructure Integration and...
M. Kilin, O. Tanriverdi, B. Karahan, F. Yasar

Demonstration of TFTs 3D Monolithically Integrated on GaN HEMTs using Cascode Configuration with High Breakdown Voltage (>1900V)
Tian-Li Wu, Hsin-Jou Ho, Chia-Wei Liu, Yi-Chen Chen
https://arxiv.org/abs/2507.07512

Demonstration of TFTs 3D Monolithically Integrated on GaN HEMTs using Cascode Configuration with High Breakdown Voltage (>1900V)
This study demonstrates 3D monolithic integration of amorphous indium-gallium-zinc oxide (a-IGZO) thin-film transistors (TFTs) on Gallium Nitride (GaN) high electron mobility transistors (HEMTs) in a cascode configuration, achieving high breakdown voltage capabilities exceeding 1900 V. Two device configurations, differing in a-IGZO channel thickness (30 nm / 10 nm), are fabricated and evaluated. Sample B, with a 10 nm a-IGZO channel, demonstrates superior electrical performance, including a hig…

Validation of a CT-brain analysis tool for measuring global cortical atrophy in older patient cohorts
Sukhdeep Bal, Emma Colbourne, Jasmine Gan, Ludovica Griffanti, Taylor Hanayik, Nele Demeyere, Jim Davies, Sarah T Pendlebury, Mark Jenkinson
https://arxiv.org/abs/2509.08012

Validation of a CT-brain analysis tool for measuring global cortical atrophy in older patient cohorts
Quantification of brain atrophy currently requires visual rating scales which are time consuming and automated brain image analysis is warranted. We validated our automated deep learning (DL) tool measuring the Global Cerebral Atrophy (GCA) score against trained human raters, and associations with age and cognitive impairment, in representative older (>65 years) patients. CT-brain scans were obtained from patients in acute medicine (ORCHARD-EPR), acute stroke (OCS studies) and a legacy sample. …

Non-tempered Gan-Gross-Prasad conjecture for Archimedean general linear groups
Cheng Chen, Rui Chen
https://arxiv.org/abs/2507.04355 https://

Non-tempered Gan-Gross-Prasad conjecture for Archimedean general linear groups
The local non-tempered Gan-Gross-Prasad conjecture suggests that, for a pair of irreducible Arthur type representations of two successive general linear groups, they have a non-zero Rankin-Selberg period if and only if they are "relevant". In this paper, we prove the "period implies relevance" direction of this conjecture for general linear groups over Archimedean local fields. Our proof is based on a previous result of Gourevitch-Sayag-Karshon on the annihilator varieties of distinguished repr…

Long time strong convergence analysis of one-step methods for McKean-Vlasov SDEs with superlinear growth coefficients
Taiyuan Liu, Yaozhong Hu, Siqing Gan
https://arxiv.org/abs/2509.09274

Long time strong convergence analysis of one-step methods for McKean-Vlasov SDEs with superlinear growth coefficients
This paper presents a strong convergence rate analysis of general discretization approximations for McKean-Vlasov SDEs with super-linear growth coefficients over infinite time horizon. Under some specified non-globally Lipschitz conditions, we derive the propagation of chaos, and the mean-square convergence rate over infinite time horizon for general one-step time discretization schemes for the underlying Mckean-Vlasov SDEs. As an application of the general result it is obtained the mean-square…

Anomalous Sodium Insertion in Highly Oriented Graphite: Thermodynamics, Kinetics and Evidence for Two-Sided Intercalation
Chuanhai Gan, Chuanlian Xiao, Hongguang Wang, Peter A. van Aken, Rotraut Merkle, Sebastian Bette, Bettina V. Lotsch, Joachim Maier
https://arxiv.org/abs/2508.08806

Anomalous Sodium Insertion in Highly Oriented Graphite: Thermodynamics, Kinetics and Evidence for Two-Sided Intercalation
The difficult intercalation of sodium (Na) into graphite is studied by systematic and long-time investigations (of up to 2 years) using highly oriented pyrolytic graphite (HOPG). By studying chemical insertion of solid, liquid and gaseous Na at low and high temperatures (LT, HT) as well as using electrochemical insertion at 25 degree Celsius into uncoated and coated HOPG, it became clear that insertion equilibrium requires HT. On decreasing chemical intercalation temperature from HT (500 degree…

Replaced article(s) found for q-fin.TR. https://arxiv.org/list/q-fin.TR/new
[1/1]:
- MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading
Chen, Jiang, Ma, Cao, Keung, Kuang, Gan, Wu, Wu

QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
Aaron Mark Thomas, Yu-Cheng Chen, Hubert Okadome Valencia, Sharu Theresa Jose, Ronin Wu
https://arxiv.org/abs/2509.05051

QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
Navigating the vast chemical space of molecular structures to design novel drug molecules with desired target properties remains a central challenge in drug discovery. Recent advances in generative models offer promising solutions. This work presents a novel quantum circuit Born machine (QCBM)-enabled Generative Adversarial Network (GAN), called QCA-MolGAN, for generating drug-like molecules. The QCBM serves as a learnable prior distribution, which is associatively trained to define a latent sp…

Replaced article(s) found for cs.CR. https://arxiv.org/list/cs.CR/new
[1/1]:
- Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
Zhao, Gan, Guo, Wu, Jia, Xiao, Nguyen, Tuan

SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation
Guido Manni, Clemente Lauretti, Loredana Zollo, Paolo Soda
https://arxiv.org/abs/2508.06429

SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation
Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low labeled-data regimes, evaluated across settings with 5 to 50 labeled samples per class. Our approach integrates three specialized neural networks -- a generator for class-conditioned image translation, a discriminator for authenticity assessment and classificatio…

Cross-correlations between the CLAMATO Lyman-alpha forest and galaxies within the COSMOS field
Benjamin Zhang, Khee-Gan Lee, Andrei Cuceu, Andreu Font-Ribera, Rieko Momose
https://arxiv.org/abs/2509.07453

Cross-correlations between the CLAMATO Lyman-alpha forest and galaxies within the COSMOS field
We compute the 3D cross-correlation between the absorption of the $z\sim 2.3$ Lyman-alpha forest measured by the COSMOS Lyman-Alpha Mapping And Tomography Observations (CLAMATO) survey, and 1642 foreground galaxies with spectroscopic redshifts from several different surveys, including 3D-HST, CLAMATO, zCOSMOS-Deep, MOSDEF, and VUDS. For each survey, we compare the measured cross-correlation with models incorporating the galaxy linear bias as well as observed redshift dispersion and systematic r…

High-Performance Self-Powered Photoelectrochemical Detection Using Scalable InGaN/GaN Nanowire Arrays
Kishan Lal Kumawat, Md. Afjalur Rahman, Nirmal Anand, Dipon Kumar Ghosh, Christy Giji Jenson, Md. Moinul Islam, Samuel Olakunle Adigbo, Sheik Munim Hussain, Md Zunaid Baten, Sharif Md. Sadaf
https://arxiv.org/abs/2507.06501

High-Performance Self-Powered Photoelectrochemical Detection Using Scalable InGaN/GaN Nanowire Arrays
Photoelectrochemical photodetectors (PEC-PDs) are promising owing to their simple, low-cost fabrication, self-powered operation, high photoresponse, and environmental sensitivity. In this work, we report for the first time the self-powered PEC photodetection characteristics of nanowire (NW) based green-emitting InGaN/GaN multiple quantum well (MQW) PEC-PDs, fabricated via a scalable top-down approach.The device exhibits strong UV sensitivity with a peak at 365 nm and an extended response into t…

Series B, Episode 05 - Pressure Point
VERON: No!
GAN: It's all right, it's all right. We won't hurt you. [Hands her pill he has taken from a container.] Take this.
VERON: No.
GAN: Please.
VERON: [Swallows pill] Who are you?
https://blake.torpidity.net/m/205/255

Significant Mobility Enhancement in Coupled AlGaN/GaN Quantum Wells considering Inter-Well Distance and Asymmetric Widths
Le Tri Dat, Tran Trong Tai, Truong Van Tuan, Vo Van Tai, Nguyen Duy Vy
https://arxiv.org/abs/2508.02024

Significant Mobility Enhancement in Coupled AlGaN/GaN Quantum Wells considering Inter-Well Distance and Asymmetric Widths
We demonstrate that coupled AlGaN/GaN quantum wells with asymmetric widths ($L_1-L_2<30 $ A achieve up to 4.5 times higher mobility than single wells at optimal separation (d = 100 A). Crucially, mobility surpasses single wells when d>40 A reversing the trend at smaller distances. This enhancement stems from double-layer screening that suppresses remote/background impurities and dislocations, while LO phonon scattering remains unaffected. For identical wells, coupled systems underperform single…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/6]:
- MLP-SRGAN: A Single-Dimension Super Resolution GAN using MLP-Mixer
Samir Mitha, Seungho Choe, Pejman Jahbedar Maralani, Alan R. Moody, April Khademi

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450 FPS
Wanhua Li, Yujie Zhao, Minghan Qin, Yang Liu, Yuanhao Cai, Chuang Gan, Hanspeter Pfister
https://arxiv.org/abs/2507.07136

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
In this paper, we introduce LangSplatV2, which achieves high-dimensional feature splatting at 476.2 FPS and 3D open-vocabulary text querying at 384.6 FPS for high-resolution images, providing a 42 $\times$ speedup and a 47 $\times$ boost over LangSplat respectively, along with improved query accuracy. LangSplat employs Gaussian Splatting to embed 2D CLIP language features into 3D, significantly enhancing speed and learning a precise 3D language field with SAM semantics. Such advancements in 3D …

Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
Obasho M, Shambhavi Jaiswal, Santanu Das, Krishna Mohan Parattu
https://arxiv.org/abs/2509.00139

Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
Extracting cosmological information from microwave sky observations requires accurate estimation of the underlying Cosmic Microwave Background (CMB) by removing foreground contamination, instrumental noise, and the effects of beam convolution. In this work, we develop a machine learning-based approach for CMB reconstruction using a generative adversarial network (GAN) architecture, where the generator is modeled as a U-Net-based convolutional neural network. To train the network, we generate …

Gravitational waves in minimal Maxwell $f(R)$ gravity
Salvatore Capozziello, Qingyu Gan
https://arxiv.org/abs/2507.06094 https://arxi…

Gravitational waves in minimal Maxwell $f(R)$ gravity
We discuss the conversion mechanism from scalar field to gravitational waves in magnetic background in $f(R)$ gravity minimal coupled to the Maxwell electrodynamics. Applying the conversion in early universe with primordial magnetic field and the neutron star with strong magnetosphere, the generated gravitational waves, converted from the scalar field, exhibit distinct power spectra which can be potentially probed by future experiments such as DECIGO, BBO, CE and ET.

Learning AI Auditing: A Case Study of Teenagers Auditing a Generative AI Model
Luis Morales-Navarro, Michelle Gan, Evelyn Yu, Lauren Vogelstein, Yasmin B. Kafai, Dana\'e Metaxa
https://arxiv.org/abs/2508.04902

Learning AI Auditing: A Case Study of Teenagers Auditing a Generative AI Model
This study investigates how high school-aged youth engage in algorithm auditing to identify and understand biases in artificial intelligence and machine learning (AI/ML) tools they encounter daily. With AI/ML technologies being increasingly integrated into young people's lives, there is an urgent need to equip teenagers with AI literacies that build both technical knowledge and awareness of social impacts. Algorithm audits (also called AI audits) have traditionally been employed by experts to a…

Series A, Episode 09 - Project Avalon
GAN: There. [Avalon takes the phial out of the tunic and holds it up, dropping the tunic]
JENNA: [Entering from the corridor] Gan, that's not Avalon. [Avalon drops the phial and it lands on her tunic. She struggles with Jenna and Gan, but is obviously stronger than they are. Blake and Vila arrive and the four of them overpower her.]

Newton to Einstein: Axiom-Based Discovery via Game Design
Pingchuan Ma, Benjamin Tod Jones, Tsun-Hsuan Wang, Minghao Guo, Michal Piotr Lipiec, Chuang Gan, Wojciech Matusik
https://arxiv.org/abs/2509.05448

Newton to Einstein: Axiom-Based Discovery via Game Design
This position paper argues that machine learning for scientific discovery should shift from inductive pattern recognition to axiom-based reasoning. We propose a game design framework in which scientific inquiry is recast as a rule-evolving system: agents operate within environments governed by axioms and modify them to explain outlier observations. Unlike conventional ML approaches that operate within fixed assumptions, our method enables the discovery of new theoretical structures through syst…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/4]:
- LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without T...
Sikui Zhang, Guangze Gao, Ziyun Gan, Chunfeng Yuan, Zefeng Lin, Houwen Peng, Bing Li, Weiming Hu

TAKE *THAT* FLAT-EARTHERS!
https://mastodon.social/@livelakemichigan/114965099390022808

Lake Michigan! Live! (@livelakemichigan@mastodon.social)
Attached: 1 image Current* conditions near Petoskey, MI:

Technical Developments of DA on $\mathbb{T}^3$
Hangyue Zhang
https://arxiv.org/abs/2509.04634 https://arxiv.org/pdf/2509.04634

Technical Developments of DA on $\mathbb{T}^3$
We constructed a DA on $\mathbb{T}^3$, which complements the work of Gan, Li, Viana, and Yang (\cite{GanLiVianaYang2021}) by providing an example of a $C^\infty$-diffeomorphism with partial volume expansion, where $\dim(E^{cs}) = 2$. In contrast to their work, in \cite{GanLiVianaYang2021}, they provided an example of a non-invertible embedding in the case $\dim(E^{cs}) = 2$. The inverse map of the DA we constructed has a mostly expanding center (\cite{AnderssonVasquez2018}). Using a similar app…

Series A, Episode 10 - Breakdown
JENNA: Lateral one-eighty.
ZEN: Lateral one eighty.
BLAKE: I'll handle this Jenna. You can help Gan.
FARREN: [Into com unit] They'll take no further action without orders from me!
https://blake.torpidity.net/m/110/558 B7B5

🇺🇦 #NowPlaying on #BBC6Music's #6Musics90sForever
Gang Starr:
🎵 Code Of The Streets
#GangStarr
https://mthomas.bandcamp.com/track/gang-starr-code-of-the-streets-mass-thomas-edit
https://open.spotify.com/track/2mLjLAlChZXZpIZfyPF8Le

A Tactical Behaviour Recognition Framework Based on Causal Multimodal Reasoning: A Study on Covert Audio-Video Analysis Combining GAN Structure Enhancement and Phonetic Accent Modelling
Wei Meng
https://arxiv.org/abs/2507.21100

A Tactical Behaviour Recognition Framework Based on Causal Multimodal Reasoning: A Study on Covert Audio-Video Analysis Combining GAN Structure Enhancement and Phonetic Accent Modelling
This paper introduces TACTIC-GRAPHS, a system that combines spectral graph theory and multimodal graph neural reasoning for semantic understanding and threat detection in tactical video under high noise and weak structure. The framework incorporates spectral embedding, temporal causal edge modeling, and discriminative path inference across heterogeneous modalities. A semantic-aware keyframe extraction method fuses visual, acoustic, and action cues to construct temporal graphs. Using graph atten…

Audio Deepfake Verification
Li Wang, Junyi Ao, Linyong Gan, Yuancheng Wang, Xueyao Zhang, Zhizheng Wu
https://arxiv.org/abs/2509.08476 https://arxiv.org/pd…

Audio Deepfake Verification
With the rapid development of deepfake technology, simply making a binary judgment of true or false on audio is no longer sufficient to meet practical needs. Accurately determining the specific deepfake method has become crucial. This paper introduces the Audio Deepfake Verification (ADV) task, effectively addressing the limitations of existing deepfake source tracing methods in closed-set scenarios, aiming to achieve open-set deepfake source tracing. Meanwhile, the Audity dual-branch architect…

Mobility Extraction and Analysis of GaN HEMTs for RF Applications Using TCAD and Experimental Data
Tanjim Rahman
https://arxiv.org/abs/2507.11849 https://

Mobility Extraction and Analysis of GaN HEMTs for RF Applications Using TCAD and Experimental Data
This paper presents an analysis of GaN high-electron-mobility transistors (HEMTs) using both TCAD simulation and experimental characterization. The energy band structure was studied using Nextnano simulation software to observe two-dimensional electron gas (2DEG) formation and carrier confinement under equilibrium conditions. Additionally, I-V and C-V data from fabricated research-grade GaN HEMTs were analyzed to extract key electrical parameters. The device demonstrated an ON current of 1.9 mA…

Emerging ultra-wide band gap semiconductors for future high-frequency electronics
Emily M. Garrity, Theodora Ciobanu, Andriy Zakutayev, Vladan Stevanovic
https://arxiv.org/abs/2508.05823

Emerging ultra-wide band gap semiconductors for future high-frequency electronics
To meet the growing demands of advanced electronic systems, next-generation power and RF semiconductor devices must operate efficiently at higher power levels and switching frequencies while remaining compact. Current state-of-the-art GaN semiconductor devices alone cannot meet all these demands. Emerging ultra-wide band gap (UWBG) alternatives like diamond, BN, AlN, and Ga2O3, face significant challenges including limited wafer availability, doping difficulties, and thermal management constrai…

RANGAN: GAN-empowered Anomaly Detection in 5G Cloud RAN
Douglas Liao, Jiping Luo, Jens Vevstad, Nikolaos Pappas
https://arxiv.org/abs/2508.20985 https://ar…

RANGAN: GAN-empowered Anomaly Detection in 5G Cloud RAN
Radio Access Network (RAN) systems are inherently complex, requiring continuous monitoring to prevent performance degradation and ensure optimal user experience. The RAN leverages numerous key performance indicators (KPIs) to evaluate system performance, generating vast amounts of data each second. This immense data volume can make troubleshooting and accurate diagnosis of performance anomalies more difficult. Furthermore, the highly dynamic nature of RAN performance demands adaptive methodolog…

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation
Sashuai Zhou, Weinan Gan, Qijiong Liu, Ke Lei, Jieming Zhu, Hai Huang, Yan Xia, Ruiming Tang, Zhenhua Dong, Zhou Zhao
https://arxiv.org/abs/2509.03131

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation
Recent advances in LLM-based recommendation have shown promise, yet their cross-domain generalization is hindered by a fundamental mismatch between language-centric pretraining and the recommendation task. Existing methods, relying on language-level knowledge, fail to capture dynamic, item-level user interests across domains. To bridge this gap, we propose RecBase, a domain-agnostic foundational model pretrained with a recommendation-oriented objective. RecBase leverages a large-scale, heteroge…

Series A, Episode 02 - Space Fall
BLAKE: Make it good Vila.
VILA: Gan?...
[Vila and Gan head towards the guard]
BLAKE: We'll be ready in exactly fifteen minutes. Will that give you enough time?
[Avon nods.]
https://blake.torpidity.net/m/102/239 B7B5

On interval decomposition of persistence modules
Wee Liang Gan, Nadiya Upegui Keagy
https://arxiv.org/abs/2507.01303 https://arxiv.or…

On interval decomposition of persistence modules
We give down-to-earth proofs of the structure theorems for persistence modules.

A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
Behnoud Shafiezadeh, Amir Mashmool, Farshad Eshghi, Manoochehr Kelarestaghi
https://arxiv.org/abs/2509.06868

A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
Automatic License-Plate Recognition (ALPR) plays a pivotal role in Intelligent Transportation Systems (ITS) as a fundamental element of Smart Cities. However, due to its high variability, ALPR faces challenging issues more efficiently addressed by deep learning techniques. In this paper, a selective Generative Adversarial Network (GAN) is proposed for deblurring in the preprocessing step, coupled with the state-of-the-art You-Only-Look-Once (YOLO)v5 object detection architectures for License-Pl…

Discrepancy-Aware Contrastive Adaptation in Medical Time Series Analysis
Yifan Wang, Hongfeng Ai, Ruiqi Li, Maowei Jiang, Ruiyuan Kang, Jiahua Dong, Cheng Jiang, Chenzhong Li
https://arxiv.org/abs/2508.05572

Discrepancy-Aware Contrastive Adaptation in Medical Time Series Analysis
In medical time series disease diagnosis, two key challenges are identified. First, the high annotation cost of medical data leads to overfitting in models trained on label-limited, single-center datasets. To address this, we propose incorporating external data from related tasks and leveraging AE-GAN to extract prior knowledge, providing valuable references for downstream tasks. Second, many existing studies employ contrastive learning to derive more generalized medical sequence representation…

Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Mahin Montasir Afif, Abdullah Al Noman, K. M. Tahsin Kabir, Md. Mortuza Ahmmed, Md. Mostafizur Rahman, Mufti Mahmud, Md. Ashraful Babu
https://arxiv.org/abs/2506.17165

Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Generative Adversarial Networks (GAN) have shown potential in expanding limited medical imaging datasets. This study explores how different ratios of GAN-generated and real brain tumor MRI images impact the performance of a CNN in classifying healthy vs. tumorous scans. A DCGAN was used to create synthetic images which were mixed with real ones at various ratios to train a custom CNN. The CNN was then evaluated on a separate real-world test set. Our results indicate that the model maintains hig…

Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding
Luis Felipe Chary, Miguel Arjona Ramirez
https://arxiv.org/abs/2509.02244 https://

Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding
We present a neural speech codec that challenges the need for complex residual vector quantization (RVQ) stacks by introducing a simpler, single-stage quantization approach. Our method operates directly on the mel-spectrogram, treating it as a 2D data and quantizing non-overlapping 4x4 patches into a single, shared codebook. This patchwise design simplifies the architecture, enables low-latency streaming, and yields a discrete latent grid. To ensure high-fidelity synthesis, we employ a late-sta…

CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
Zeyu Gan, Hao Yi, Yong Liu
https://arxiv.org/abs/2509.04027 https://

CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
Reinforcement Learning (RL) has become a pivotal approach for enhancing the reasoning capabilities of Large Language Models (LLMs). However, a significant theoretical gap persists, as traditional token-level RL frameworks fail to align with the reasoning-level nature of complex, multi-step thought processes like Chain-of-Thought (CoT). To address this challenge, we introduce CoT-Space, a novel theoretical framework that recasts LLM reasoning from a discrete token-prediction task to an optimizat…

MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading
Yang Chen, Yueheng Jiang, Zhaozhao Ma, Yuchen Cao Jacky Keung, Kun Kuang, Leilei Gan, Yiquan Wu, Fei Wu
https://arxiv.org/abs/2509.05080

MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading
The inherent non-stationarity of financial markets and the complexity of multi-modal information pose significant challenges to existing quantitative trading models. Traditional methods relying on fixed structures and unimodal data struggle to adapt to market regime shifts, while large language model (LLM)-driven solutions - despite their multi-modal comprehension - suffer from static strategies and homogeneous expert designs, lacking dynamic adjustment and fine-grained decision mechanisms. To …

Enhanced Raman scattering by fast GaN phonon-polaritons
Mayssoune Mina, Toni Alhaddad, Olivier Pag\`es
https://arxiv.org/abs/2509.02057 https://arxiv.org/p…

Enhanced Raman scattering by fast GaN phonon-polaritons
Phonon-polaritons propagating in crystal volume offer the possibility of transferring information throughout matter (via phonons) at high (photon-like) velocity and tunable frequency/wavelength in the far-infrared. However, from the phonon-polariton Raman cross section, the phonon and photon advantages seem mutually exclusive. Either the phonon-polaritons are fast (photon-like) but hardly supported by the lattice (not phonon-like), or they are well supported by the lattice (testified by a high …

Series A, Episode 05 - The Web
JENNA: [Joins Blake. Cally moves to the console and begins altering settings] Navigation computers can't cope with a change of course. We're running blind.
CALLY: [Gan enters stealthily from other passageway]. Don't move.
https://blake.torpidity.net/m/105/77

Molecular Beam Epitaxy of 2H-TaS$_2$ few-layers on GaN(0001)
Constantin Hilbrunner, Tobias Meyer, Joerg Malindretos, Angela Rizzi
https://arxiv.org/abs/2508.21537 https://

Molecular Beam Epitaxy of 2H-TaS$_2$ few-layers on GaN(0001)
2H-TaS$_2$ few layers have been grown epitaxially onto GaN(0001). A high substrate growth temperature of 825$^{\circ}$C induces best structural properties of the overlayer, as revealed by in-situ electron diffraction (RHEED and LEED). The 2D-overlayer grows unstrained right after deposition of a monolayer. However, evidence of pits at the interface is provided by scanning transmission electron microscopy, most probably due to GaN thermal decomposition at the high growth temperature. In-situ x-r…

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[2/3]:
- Transformable Modular Robots: A CPG-Based Approach to Independent and Collective Locomotion
Jiayu Ding, Rohit Jakkula, Tom Xiao, Zhenyu Gan

Power System Voltage Stability Boundary: Computational Results and Applications
Zhenyao Li, Yifan Yao, Deqiang Gan
https://arxiv.org/abs/2508.03119 https://

Power System Voltage Stability Boundary: Computational Results and Applications
The objective of this paper is to report some computational results for the theory of DAE stability boundary, with the aim of advancing applications in power system voltage stability studies. Firstly, a new regularization transformation for standard differential-algebraic equations (DAEs) is proposed. Then the existence of anchor points on voltage stability boundary is examined, and an optimization method for computing the controlling pseudo-saddle is suggested. Subsequently, a local representa…

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/2]:
- HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN
Abhinav Sagar

Fast Forward and Inverse Thermal Modeling for Parameter Estimation of Multi-Layer composites -- Part I: Forward Modeling
Gan Fu, Calina Ciuhu, Mitrofan Curti, Elena A. Lomonova
https://arxiv.org/abs/2507.06727

Fast Forward and Inverse Thermal Modeling for Parameter Estimation of Multi-Layer composites -- Part I: Forward Modeling
This study presents fast and accurate analytical methods for transient thermal modeling in multi-layer composites with an arbitrary number of layers. The proposed approach accounts for internal heat generation and non-homogeneities in the heat diffusion equation. The separation of variables (SOV) method is employed to decouple spatial and temporal components, enabling the determination of eigenvalues. The orthogonal expansion (OE) technique is then applied to compute Fourier coefficients using …

Series A, Episode 03 - Cygnus Alpha
BLAKE: Listen, I've got a ship. I can take you and the others off this planet.
GAN: We can't leave here.
BLAKE: What are you talking about?
GAN: The sickness. We're all infected.
https://blake.torpidity.net/m/103/389 B7B4

Electronic structure and defect properties of Bi-doped GaN: origins of photoluminescence and optical absorption
Yujie Liu, Ishtiaque Ahmed Navid, Zetian Mi, Emmanouil Kioupakis
https://arxiv.org/abs/2507.01346

Electronic structure and defect properties of Bi-doped GaN: origins of photoluminescence and optical absorption
Extreme lattice-mismatched III-V nitrides, such as Bi-incorporated GaN, have been realized experimentally thanks to recent advances in epitaxial growth and characterization techniques. However, theoretical insights into defect-related optical absorption and emission phenomena in these materials remain scarce. Here, we apply hybrid density functional theory to systematically explore the role of substitutional bismuth atoms on both cationic $\mathrm{Bi_{Ga}}$ and anionic $\mathrm{Bi_{N}}$ sites i…

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation
Peiyu Wang, Yi Peng, Yimeng Gan, Liang Hu, Tianyidan Xie, Xiaokun Wang, Yichen Wei, Chuanxin Tang, Bo Zhu, Changshi Li, Hongyang Wei, Eric Li, Xuchen Song, Yang Liu, Yahui Zhou
https://arxiv.org/abs/2508.03320

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation
We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation r…

Fast Forward and Inverse Thermal Modeling for Parameter Estimation of Multi-Layer Composites -- Part II: Inverse Modeling and Applications
Gan Fu, Mitrofan Curti, Calina Ciuhu, Elena A. Lomonova
https://arxiv.org/abs/2507.06746

Fast Forward and Inverse Thermal Modeling for Parameter Estimation of Multi-Layer Composites -- Part II: Inverse Modeling and Applications
A fast inverse heat conduction model (IHCM) is developed for estimating unknown properties of multi-layer composites considering internal heat generation. This work builds on the validated analytical forward models presented in Part I. Transient temperature at a single point is used as input, with the objective function minimized through an interior-point optimization algorithm. The IHCM accurately estimates thermal properties such as thermal conductivity, specific heat capacity, density, and h…

Series A, Episode 09 - Project Avalon
BLAKE: [V.O.] Can you identify it?
GAN: Well, the detectors read it as a military command cruiser and the trajectory suggested it could have come from Federation space headquarters.
https://blake.torpidity.net/m/109/143 B7B2

Deep-Learning-Assisted Highly-Accurate COVID-19 Diagnosis on Lung Computed Tomography Images
Yinuo Wang, Juhyun Bae, Ka Ho Chow, Shenyang Chen, Shreyash Gupta
https://arxiv.org/abs/2507.04252

Deep-Learning-Assisted Highly-Accurate COVID-19 Diagnosis on Lung Computed Tomography Images
COVID-19 is a severe and acute viral disease that can cause symptoms consistent with pneumonia in which inflammation is caused in the alveolous regions of the lungs leading to a build-up of fluid and breathing difficulties. Thus, the diagnosis of COVID using CT scans has been effective in assisting with RT-PCR diagnosis and severity classifications. In this paper, we proposed a new data quality control pipeline to refine the quality of CT images based on GAN and sliding windows. Also, we use cl…

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
Bin Wen, Tien-Ping Tan
https://arxiv.org/abs/2508.14525 https://arxi…

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse acoustic features efficiently. An enhanced attention mechanism with dual normalization and residual refinement further improves training stability and convergence. Additionally, dynamic pruning is applied to reduce model size while maintaining performance, making…

Ultrathin oxide freestanding membranes with large-scale continuity and structural perfection
Yuhao Hong, Yang Hu, Jianyao Zheng, Minh D. Nguyen, Jelle R. H. Ruiters, Daniel M. Cunha, Iris C. G. van den Bosch, Edwin Dollekamp, Mark Huijben, Yulin Gan, Nini Pryds, Daesung Park, Christoph Baeumer, Qinghua Zhang, Guus Rijnders, Zhaoliang Liao, Gertjan Koster
https:…

Ultrathin oxide freestanding membranes with large-scale continuity and structural perfection
Freestanding oxide membranes offer integration with advanced semiconductor platforms, unlocking opportunities for flexible electronics, silicon-based spintronics, neuromorphic computing, and high-performance energy technologies. Scalable fabrication of such membranes is essential for bridging fundamental discoveries in complex oxides with practical device deployment. However, the lateral dimensions of crack- and wrinkle-free membranes remain limited to millimeter scales, forming a critical bott…

Series A, Episode 05 - The Web
JENNA: Look.
[Main viewscreen shows the web dissolving.]
GAN: He did it. We're free.
JENNA: Not yet.
https://blake.torpidity.net/m/105/503 B7B5

QHARMA-GAN: Quasi-Harmonic Neural Vocoder based on Autoregressive Moving Average Model
Shaowen Chen, Tomoki Toda
https://arxiv.org/abs/2507.01611 https://

QHARMA-GAN: Quasi-Harmonic Neural Vocoder based on Autoregressive Moving Average Model
Vocoders, encoding speech signals into acoustic features and allowing for speech signal reconstruction from them, have been studied for decades. Recently, the rise of deep learning has particularly driven the development of neural vocoders to generate high-quality speech signals. On the other hand, the existing end-to-end neural vocoders suffer from a black-box nature that blinds the speech production mechanism and the intrinsic structure of speech, resulting in the ambiguity of separately mode…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/6]:
- Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images
Jinghe Yang, Mingming Gong, Ye Pu

UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound Synthesis
Zhuo Li, Xuhang Chen, Shuqiang Wang
https://arxiv.org/abs/2507.03341

UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound Synthesis
Functional ultrasound (fUS) is a neuroimaging technique known for its high spatiotemporal resolution, enabling non-invasive observation of brain activity through neurovascular coupling. Despite its potential in clinical applications such as neonatal monitoring and intraoperative guidance, the development of fUS faces challenges related to data scarcity and limitations in generating realistic fUS images. This paper explores the use of a generative adversarial network (GAN) framework tailored for…

Series B, Episode 03 - Weapon
AVON: Auron may be different, Cally, but on Earth it is considered ill-mannered to kill your friends while committing suicide.
GAN: Why that base, Cally?
https://blake.torpidity.net/m/203/31 B7B3

Series B, Episode 02 - Shadow
GAN: The manual controls won't respond.
VILA: Do something, Gan.
GAN: Something is draining off the power. [Lights dim]
VILA: Orac, it has to be Orac.
https://blake.torpidity.net/m/202/565 B7B3

Spatiotemporal Mapping of Anisotropic Thermal Transport in GaN Thin Films via Ultrafast X-ray Diffraction
Thanh Nguyen, Chuliang Fu, Mouyang Cheng, Buxuan Li, Tyra E. Espedal, Zhantao Chen, Kuan Qiao, Kumar Neeraj, Abhijatmedhi Chotrattanapituk, Denisse Cordova Carrizales, Eunbi Rha, Tongtong Liu, Shivam N. Kajale, Deblina Sarkar, Donald A. Walko, Haidan Wen, Svetlana V. Boriskina, Gang Chen, Jeehwan Kim, Mingda Li

Spatiotemporal Mapping of Anisotropic Thermal Transport in GaN Thin Films via Ultrafast X-ray Diffraction
Efficient thermal management is essential for the reliability of modern power electronics, where increasing device density leads to severe heat dissipation challenges. However, in thin-film systems, thermal transport is often compromised by interfacial resistance and microscale defects introduced during synthesis or transfer, which are difficult to characterize using conventional techniques. Here we present a non-contact, spatiotemporal-resolved ultrafast x-ray diffraction method to extract in-…

Series A, Episode 08 - Duel
GAN: WAS inhabited.
BLAKE: Hmm?
GAN: Look here [Points them to the memorials] as far as the eye can see.
BLAKE: Grave markers?
JENNA: So many.
https://blake.torpidity.net/m/108/68 B7B3

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

IC-Custom: Diverse Image Customization via In-Context Learning
Yaowei Li, Xiaoyu Li, Zhaoyang Zhang, Yuxuan Bian, Gan Liu, Xinyuan Li, Jiale Xu, Wenbo Hu, Yating Liu, Lingen Li, Jing Cai, Yuexian Zou, Yancheng He, Ying Shan
https://arxiv.org/abs/2507.01926

IC-Custom: Diverse Image Customization via In-Context Learning
Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-awa…

Interlayer Coupling and Exciton Dynamics in 2D Hybrid Structures based on an InGaN Quantum Well coupled to a MoSe2 Monolayer
D. Chen, D. Lagarde, L. Hemmen, L. Lombez, P. Renucci, M. Mauguet, L. Ren, C. Robert, N. Grandjean, X. Marie
https://arxiv.org/abs/2509.06547

Interlayer Coupling and Exciton Dynamics in 2D Hybrid Structures based on an InGaN Quantum Well coupled to a MoSe2 Monolayer
Hybrid structures incorpora1ng both III-nitride and Transi1on Metal Dichalcogenide (TMD) semiconductors have strong applica1on poten1al for light harves1ng and optoelectronics. Here we have inves1gated the proper1es of hybrid structures based on a MoSe2 monolayer coupled to an InGaN quantum well (QW). The coupling efficiency is controlled by a thin GaN barrier of variable thickness located between them. Time-integrated and 1me-resolved micro-photoluminescence experiments show a quenching of the…

MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detection
Chengming Wang, Guodong Fan, Jinjiang Li, Min Gan, C. L. Philip Chen
https://arxiv.org/abs/2508.01555

MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detection
With the advancement of remote sensing satellite technology and the rapid progress of deep learning, remote sensing change detection (RSCD) has become a key technique for regional monitoring. Traditional change detection (CD) methods and deep learning-based approaches have made significant contributions to change analysis and detection, however, many outstanding methods still face limitations in the exploration and application of multimodal data. To address this, we propose the multimodal graph…

Series A, Episode 03 - Cygnus Alpha
BLAKE: [Whispers] Vila. [Pause, then louder] Vila. [Pause] Gan. [Pause] Gan.
GAN: [Moves to bars] Blake.
BLAKE: What is it? What's the matter with everybody?
GAN: How did you get here?
https://blake.torpidity.net/m/103/377 …

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Two-flow Feedback Multi-scale Progressive Generative Adversarial Network
Sun Weikai, Song Shijie, Chi Wenjie
https://arxiv.org/abs/2508.16089 https://arxiv…

Two-flow Feedback Multi-scale Progressive Generative Adversarial Network
Although diffusion model has made good progress in the field of image generation, GAN\cite{huang2023adaptive} still has a large development space due to its unique advantages, such as WGAN\cite{liu2021comparing}, SSGAN\cite{guibas2021adaptive} \cite{zhang2022vsa} \cite{zhou2024adapt} and so on. In this paper, we propose a novel two-flow feedback multi-scale progressive generative adversarial network (MSPG-SEN) for GAN models. This paper has four contributions: 1) : We propose a two-flow feedbac…

Series A, Episode 09 - Project Avalon
JENNA: Well, yes, I've only met her once, but, yes, that's her.
AVON: Then it must be Chevner.
GAN: Chevner. How do you think he'll do it?
https://blake.torpidity.net/m/109/349 B7B2

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Qingdong He, Xueqin Chen, Chaoyi Wang, Yanjie Pan, Xiaobin Hu, Zhenye Gan, Yabiao Wang, Chengjie Wang, Xiangtai Li, Jiangning Zhang
https://arxiv.org/abs/2507.01908

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Instruction-based image editing (IIE) has advanced rapidly with the success of diffusion models. However, existing efforts primarily focus on simple and explicit instructions to execute editing operations such as adding, deleting, moving, or swapping objects. They struggle to handle more complex implicit hypothetical instructions that require deeper reasoning to infer plausible visual changes and user intent. Additionally, current datasets provide limited support for training and evaluating rea…

MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
Tingting Liu, Yuan Liu, Jinhui Tang, Liyin Yuan, Chengyu Liu, Chunlai Li, Xiubao Sui, Qian Chen
https://arxiv.org/abs/2506.17540

MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
Thermal infrared (TIR) images, acquired through thermal radiation imaging, are unaffected by variations in lighting conditions and atmospheric haze. However, TIR images inherently lack color and texture information, limiting downstream tasks and potentially causing visual fatigue. Existing colorization methods primarily rely on single-band images with limited spectral information and insufficient feature extraction capabilities, which often result in image distortion and semantic ambiguity. In …

Transforming H&E images into IHC: A Variance-Penalized GAN for Precision Oncology
Sara Rehmat, Hafeez Ur Rehman
https://arxiv.org/abs/2506.18371 https:…

Transforming H&E images into IHC: A Variance-Penalized GAN for Precision Oncology
The overexpression of the human epidermal growth factor receptor 2 (HER2) in breast cells is a key driver of HER2-positive breast cancer, a highly aggressive subtype requiring precise diagnosis and targeted therapy. Immunohistochemistry (IHC) is the standard technique for HER2 assessment but is costly, labor-intensive, and highly dependent on antibody selection. In contrast, hematoxylin and eosin (H&E) staining, a routine histopathological procedure, offers broader accessibility but lacks HER2 …

Negative capacitance overcomes Schottky-gate limits in GaN high-electron-mobility transistors
Asir Intisar Khan, Jeong-Kyu Kim, Urmita Sikder, Koushik Das, Thomas Rodriguez, Rohith Soman, Srabanti Chowdhury, Sayeef Salahuddin
https://arxiv.org/abs/2506.16758

Negative capacitance overcomes Schottky-gate limits in GaN high-electron-mobility transistors
For high-electron-mobility transistors based on two-dimensional electron gas (2DEG) within a quantum well, such as those based on AlGaN/GaN heterostructure, a Schottky-gate is used to maximize the amount of charge that can be induced and thereby the current that can be achieved. However, the Schottky-gate also leads to very high leakage current through the gate electrode. Adding a conventional dielectric layer between the nitride layers and gate metal can reduce leakage; but this comes at the p…

Series A, Episode 10 - Breakdown
BLAKE: Jenna, you take my place. Brief Cally.
[Computer room, Gan tries to pull piping from wall]
AVON: Gan, no! You'll break the computer links, we'll never get them started. [Avon tries to stop Gan, who thows him off]
https://blake.torpidity.net/m/110/295

PAMBE growth of GaN nanowires on metallic ZrN buffers -- a critical impact of ZrN layer thickness on the growth temperature
Karol Olszewski, Zbigniew R. Zytkiewicz, Aleksandra Wierzbicka, Marek Guziewicz, Marta Sobanska
https://arxiv.org/abs/2506.11754

PAMBE growth of GaN nanowires on metallic ZrN buffers -- a critical impact of ZrN layer thickness on the growth temperature
An impact of thin metallic ZrN layers on Si and sapphire wafers on substrate temperature during MBE growth of GaN nanowires is studied. Using nucleation kinetics of GaN as a sensitive probe we show that a thin ZrN layer strongly increases the substrate temperature, which significantly affects the dimensions and density of the nanowires. To quantify the effect we developed a technique of optical pyrometer calibration that allows reliable determination of emissivity, and thus precise measurement …

Hydra-Bench: A Benchmark for Multi-Modal Leaf Wetness Sensing
Yimeng Liu, Maolin Gan, Yidong Ren, Gen Li, Jingkai Lin, Younsuk Dong, Zhichao Cao
https://arxiv.org/abs/2507.22685

Hydra-Bench: A Benchmark for Multi-Modal Leaf Wetness Sensing
Leaf wetness detection is a crucial task in agricultural monitoring, as it directly impacts the prediction and protection of plant diseases. However, existing sensing systems suffer from limitations in robustness, accuracy, and environmental resilience when applied to natural leaves under dynamic real-world conditions. To address these challenges, we introduce a new multi-modal dataset specifically designed for evaluating and advancing machine learning algorithms in leaf wetness detection. Our …

Series A, Episode 03 - Cygnus Alpha
VILA: Gan. [Echo] Gan.
ARCO: He might be in trouble. Come on.
VILA: Shouldn't we wait a bit longer? I mean, he might be all right. And if he isn't, what chance do the rest of us stand?
ARCO: Come on.
https://blake.torpidity.net/m/103/243

Series B, Episode 03 - Weapon
GAN: Yes.
AVON: [Smiles] Virtually alone, then.
CALLY: And for that attack we shall need all the weapons we can get.
BLAKE: [Enters] And where better to get them than the Weapons Development Base?
https://blake.torpidity.net/m/203/39 B7B6

Series B, Episode 03 - Weapon
GAN: That doesn't sound very promising. Someone must have made an attack on the base.
VILA: Who'd be stupid enough to do that?
AVON: [Snaps his fingers] Justify "stupid."
https://blake.torpidity.net/m/203/112 B7B2

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Series A, Episode 04 - Time Squad
AVON: [V.O.] I hear you.
BLAKE: Bring us back. [Pause. V.O.] Bring us back.
[Interior. Liberator teleport area. Avon is at the console. Gan is there]
AVON: I can't. The teleport control is burnt out.
https://blake.torpidity.net/m/104/130…

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.

Series B, Episode 05 - Pressure Point
BLAKE: I'm very sorry about your mother. She was a remarkable woman. You lie here and rest while we decide what's to be done.
VERON: Thank you. [She lies down, Blake and Gan move away from her.]
https://blake.torpidity.net/m/205/271 B7B5

Series A, Episode 08 - Duel
GAN: He seems to be working to a plan.
VILA: I wish we were.
AVON: [Entering] Well? Did any of the controls respond?
GAN: Nothing here.
VILA: Nothing on mine.
CALLY: Nothing on these.
https://blake.torpidity.net/m/108/338 B7B3

Series B, Episode 02 - Shadow
AVON: She was dying anyway.
BEK: Oh I know that. Just another dreamhead. But what about the low-life scum that really killed her? What about the Terra Nostra?
BLAKE: That is who we're waiting for now.
GAN: We're what?
https://blake.torpidity.net/m/202/625

Series B, Episode 02 - Shadow
ORAC: The bridge is complete.
VILA: What? What did he say?
GAN: Something's wrong.
VILA: No, that wasn't it.
ZEN: Information. Liberator is losing power from all systems. Orbital maintenance is threatened.
https://blake.torpidity.net/m/202/555

Blakes7Bot | Search
Companion site to the Blakes7Bot Twitter, Mastodon, and Bluesky accounts. Automated lines of Blakes 7 dialog. Includes a script search facility.