Search: “concepts”

Generating Synthetic Malware Samples Using Generative AI

arXiv:2604.22084v1 Announce Type: new Abstract: Malware attacks have a significant negative impact on organizations of varied scales in the field of cybersecurity. Recently, malware researchers have i

researcharxiv-cs-lg

27 Apr 2026

Syntheses

Wiki Lint Report — 2026-04-26

Automated lint: 44 errors, 10 warnings, 3 info

linthealth-checkautomated

26 Apr 2026

Addressing divergent representations from causal interventions on neural networks

arXiv:2511.04638v5 Announce Type: replace-cross Abstract: A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to under

researcharxiv-cs-ai

Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning

arXiv:2509.23744v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-m

DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion

arXiv:2604.21627v1 Announce Type: new Abstract: Advancing face morphing attack techniques is crucial to anticipate evolving threats and develop robust defensive mechanisms for identity verification sy

Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI

arXiv:2604.21300v1 Announce Type: new Abstract: Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods ofte

tutorialsarxiv-cs-cl

ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation

arXiv:2604.21465v1 Announce Type: new Abstract: Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital secu

Information Bottleneck-Guided Heterogeneous Graph Learning for Interpretable Neurodevelopmental Disorder Diagnosis

arXiv:2502.20769v3 Announce Type: replace Abstract: Developing interpretable models for neurodevelopmental disorders (NDDs) diagnosis presents significant challenges in effectively encoding, decoding,

tutorialsarxiv-cs-cv

LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation

arXiv:2604.21279v1 Announce Type: new Abstract: Facial attribute editing and style manipulation are crucial for applications like virtual avatars and photo editing. However, achieving precise control

Quotient-Space Diffusion Models

arXiv:2604.21809v1 Announce Type: cross Abstract: Diffusion-based generative models have reformed generative AI, and have enabled new capabilities in the science domain, for example, generating 3D str

S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images

arXiv:2604.21409v1 Announce Type: new Abstract: We present S1-VL, a multimodal reasoning model for scientific domains that natively supports two complementary reasoning paradigms: Scientific Reasoning

tutorialsarxiv-cs-cv

Model Releases

Symbolic Grounding Reveals Representational Bottlenecks in Abstract Visual Reasoning

model-releasesarxiv-cs-ai

arXiv:2604.21346v1 Announce Type: new Abstract: Vision--language models (VLMs) often fail on abstract visual reasoning benchmarks such as Bongard problems, raising the question of whether the main bot

The Effect of Idea Elaboration on the Automatic Assessment of Idea Originality

arXiv:2604.20569v1 Announce Type: cross Abstract: Automatic systems are increasingly used to assess the originality of responses in creative tasks. They offer a potential solution to key limitations o

Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces

arXiv:2604.02832v2 Announce Type: replace-cross Abstract: Accurate forecasting of recovery rates (RR) is central to credit risk management and regulatory capital determination. In many loan portfolios

UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

arXiv:2604.21904v1 Announce Type: new Abstract: In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent

VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models

arXiv:2510.18457v3 Announce Type: replace Abstract: The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizers. While recent works have explore

CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis

arXiv:2510.21464v2 Announce Type: replace Abstract: Deep learning models have achieved remarkable accuracy in chest X-ray diagnosis, yet their widespread clinical adoption remains limited by the black

Image Generators are Generalist Vision Learners

arXiv:2604.20329v1 Announce Type: cross Abstract: Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent

tutorialsarxiv-cs-ai

MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing

arXiv:2604.20317v1 Announce Type: new Abstract: GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one

tutorialsarxiv-cs-cv

Membership Inference for Contrastive Pre-training Models with Text-only PII Queries

arXiv:2603.14222v2 Announce Type: replace-cross Abstract: Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet the

Not all ANIMALs are equal: metaphorical framing through source domains and semantic frames

arXiv:2604.20454v1 Announce Type: new Abstract: Metaphors are powerful framing devices, yet their source domains alone do not fully explain the specific associations they evoke. We argue that the inte

researcharxiv-cs-cl

On the definition and importance of interpretability in scientific machine learning

arXiv:2505.13510v3 Announce Type: replace Abstract: Though neural networks trained on large datasets have been successfully used to describe and predict many physical phenomena, there is a sense among

researcharxiv-cs-lg

ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

arXiv:2604.20816v1 Announce Type: cross Abstract: Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a si

Sampling-Aware Quantization for Diffusion Models

arXiv:2505.02242v2 Announce Type: replace Abstract: Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computatio

Agents

Scalable Quantum Reinforcement Learning on NISQ Devices with Dynamic-Circuit Qubit Reuse and Grover Optimization

arXiv:2509.16002v2 Announce Type: replace-cross Abstract: A scalable and resource-efficient quantum reinforcement learning framework is presented that eliminates the linear qubit-scaling barrier in mu

agentsarxiv-cs-lg

Towards Certified Unlearning for Deep Neural Networks

arXiv:2408.00920v4 Announce Type: replace Abstract: In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency a

Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference

arXiv:2604.19566v1 Announce Type: cross Abstract: Reliable biomedical and clinical retrieval requires more than strong ranking performance: it requires a practical way to find systematic model failure

safetyarxiv-cs-cl

Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval

arXiv:2604.19135v1 Announce Type: new Abstract: This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-bas

DT2IT-MRM: Debiased Preference Construction and Iterative Training for Multimodal Reward Modeling

arXiv:2604.19544v1 Announce Type: new Abstract: Multimodal reward models (MRMs) play a crucial role in aligning Multimodal Large Language Models (MLLMs) with human preferences. Training a good MRM req

How to Teach Large Multimodal Models New Skills

arXiv:2510.08564v2 Announce Type: replace Abstract: How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills wh

Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs

arXiv:2604.19292v1 Announce Type: cross Abstract: Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of b

PREF-XAI: Preference-Based Personalized Rule Explanations of Black-Box Machine Learning Models

arXiv:2604.19684v1 Announce Type: new Abstract: Explainable artificial intelligence (XAI) has predominantly focused on generating model-centric explanations that approximate the behavior of black-box

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

arXiv:2604.19083v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threate

Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP

arXiv:2604.18722v1 Announce Type: new Abstract: Cross-lingual transfer in NLP is often hindered by the ``script barrier'' where differences in writing systems inhibit transfer learning between languag

researcharxiv-cs-cl

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing

arXiv:2604.19587v1 Announce Type: new Abstract: Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for ad

Local Ai

'The Order in the Horse's Heart': A Case Study in LLM-Assisted Stylometry for the Discovery of Biblical Allusion in Modern Literary Fiction

arXiv:2604.19447v1 Announce Type: new Abstract: We present a dual-track pipeline for detecting biblical allusions in literary fiction and apply it to the novels of Cormac McCarthy. A bottom-up embeddi

local-aiarxiv-cs-cl

Agents

ARMove: Learning to Predict Human Mobility through Agentic Reasoning

arXiv:2604.17419v1 Announce Type: cross Abstract: Human mobility prediction is a critical task but remains challenging due to its complexity and variability across populations and regions. Recently, l

agentsarxiv-cs-lg

Can we generate portable representations for clinical time series data using LLMs?

arXiv:2603.23987v2 Announce Type: replace Abstract: Deploying clinical ML is slow and brittle: models that work at one hospital often degrade under distribution shifts at the next. In this work, we st

Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts

arXiv:2604.18091v1 Announce Type: new Abstract: Recent multimodal large language models have shown promising ability in generating humorous captions for images, yet they still lack stable control over

safetyarxiv-cs-cl

DGSSM: Diffusion guided state-space models for multimodal salient object detection

arXiv:2604.17585v1 Announce Type: new Abstract: Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging

Federated Rule Ensemble Method in Medical Data

arXiv:2604.17956v1 Announce Type: new Abstract: Machine learning has become integral to medical research and is increasingly applied in clinical settings to support diagnosis and decision-making; howe

Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease

arXiv:2601.00921v2 Announce Type: replace Abstract: Quantum methods are increasingly proposed for healthcare, but translational biomarker studies demand transparent benchmarking and robust small-datas

Model Releases

GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning

model-releasesarxiv-cs-cv

arXiv:2604.17822v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Langua

Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization

arXiv:2604.16496v1 Announce Type: cross Abstract: Continual learning, the ability to acquire new tasks sequentially without forgetting prior knowledge, is essential for deploying neural networks in dy

Local Ai

How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them

arXiv:2604.17105v1 Announce Type: new Abstract: Tokenization is the first step in every language model (LM), yet it never takes the sounds of words into account. We investigate how tokenization influe

local-aiarxiv-cs-cl

In-Context Learning Under Regime Change

arXiv:2604.16988v1 Announce Type: new Abstract: Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models m

Integrated Wheel Sensor Communication using ESP32 -- A Contribution towards a Digital Twin of the Road System

arXiv:2509.04061v2 Announce Type: replace Abstract: While current onboard state estimation methods are adequate for most driving and safety-related applications, they do not provide insights into the

safetyarxiv-cs-ro

Is SAM3 ready for pathology segmentation?

arXiv:2604.18225v1 Announce Type: new Abstract: Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales