Search: “papers”

arXiv:2604.08936v1 Announce Type: new Abstract: Medical foundation models (MFMs) aim to learn universal representations from multimodal medical images that can generalize effectively to diverse downst

tutorialsarxiv-cs-cv

Model Releases

Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space

DGX agent

arXiv:2501.15461v4 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have shown great success in various graph-based learning tasks. However, it often faces the issue of over-smoothing as

model-releasesarxiv-cs-lg

13 Apr 2026

MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis

arXiv:2502.13718v2 Announce Type: replace Abstract: Aspect-based sentiment analysis (ABSA) garnered growing research interest in multilingual contexts in the past. However, the majority of the studies

safetyarxiv-cs-cl

Music Audio-Visual Question Answering Requires Specialized Multimodal Designs

arXiv:2505.20638v2 Announce Type: replace-cross Abstract: While recent Multimodal Large Language Models exhibit impressive capabilities for general multimodal tasks, specialized domains like music nec

researcharxiv-cs-cv

Tutorials

MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation

arXiv:2604.08916v1 Announce Type: new Abstract: Conventional 3D instance segmentation methods rely on labor-intensive 3D annotations for supervised training, which limits their scalability and general

tutorialsarxiv-cs-cv

NCL-BU at SemEval-2026 Task 3: Fine-tuning XLM-RoBERTa for Multilingual Dimensional Sentiment Regression

model-releasesarxiv-cs-cl

arXiv:2604.08923v1 Announce Type: new Abstract: Dimensional Aspect-Based Sentiment Analysis (DimABSA) extends traditional ABSA from categorical polarity labels to continuous valence-arousal (VA) regre

Nested Radially Monotone Polar Occupancy Estimation: Clinically-Grounded Optic Disc and Cup Segmentation for Glaucoma Screening

arXiv:2604.09062v1 Announce Type: new Abstract: Valid segmentation of the optic disc (OD) and optic cup (OC) from fundus photographs is essential for glaucoma screening. Unfortunately, existing deep l

researcharxiv-cs-cv

No Single Best Model for Diversity: Learning a Router for Sample Diversity

arXiv:2604.02319v2 Announce Type: replace Abstract: When posed with prompts that permit a large number of valid answers, comprehensively generating them is the first step towards satisfying a wide ran

researcharxiv-cs-cl

Local Ai

Off-the-shelf Vision Models Benefit Image Manipulation Localization

arXiv:2604.09096v1 Announce Type: new Abstract: Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differen

local-aiarxiv-cs-cv

Local Ai

Offline-First LLM Architecture for Adaptive Learning in Low-Connectivity Environments

arXiv:2603.03339v5 Announce Type: replace-cross Abstract: Artificial intelligence (AI) and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, per

local-aiarxiv-cs-cl

On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs

arXiv:2509.25214v3 Announce Type: replace-cross Abstract: As increasingly large pre-trained models are released, deploying them on edge devices for privacy-preserving applications requires effective c

On the Representational Limits of Quantum-Inspired 1024-D Document Embeddings: An Experimental Evaluation Framework

arXiv:2604.09430v1 Announce Type: cross Abstract: Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language M

On the Terminology and Geometric Aspects of Redundant Parallel Manipulators

arXiv:2604.09156v1 Announce Type: new Abstract: Parallel kinematics machines (PKM) can exhibit kinematic as well as actuation redundancy. While the meaning of kinematic redundancy has been clarified a

researcharxiv-cs-ro

Out-of-the-box: Black-box Causal Attacks on Object Detectors

arXiv:2512.03730v2 Announce Type: replace-cross Abstract: Adversarial perturbations are a useful way to expose vulnerabilities in object detectors. Existing perturbation methods are frequently white-b

Local Ai

Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing

arXiv:2604.09499v1 Announce Type: new Abstract: Autonomous racing without prebuilt maps is a grand challenge for embedded robotics that requires kinodynamic planning from instantaneous sensor data at

local-aiarxiv-cs-ro

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos

arXiv:2508.04853v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) has become a crucial tool for reducing the memory and compute costs of modern deep neural networks, including

PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing

arXiv:2604.09111v1 Announce Type: cross Abstract: Recently, artificial intelligence-based dubbing technology has advanced, enabling automated dubbing (AD) to convert the source speech of a video into

R3PM-Net: Real-time, Robust, Real-world Point Matching Network

arXiv:2604.05060v2 Announce Type: replace Abstract: Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two p

applicationsarxiv-cs-cv

RansomTrack: A Hybrid Behavioral Analysis Framework for Ransomware Detection

model-releasesarxiv-cs-lg

arXiv:2604.08739v1 Announce Type: cross Abstract: Ransomware poses a serious and fast-acting threat to critical systems, often encrypting files within seconds of execution. Research indicates that ran

Agents

Reasoning Provenance for Autonomous AI Agents: Structured Behavioral Analytics Beyond State Checkpoints and Execution Traces

arXiv:2603.21692v2 Announce Type: replace Abstract: As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across

agentsarxiv-cs-ai

Retrieval Augmented Classification for Confidential Documents

arXiv:2604.08628v1 Announce Type: cross Abstract: Unauthorized disclosure of confidential documents demands robust, low-leakage classification. In real work environments, there is a lot of inflow and

Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics

arXiv:2604.08764v1 Announce Type: new Abstract: Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inhere

researcharxiv-cs-cl

Industry

Sam Altman's Molotov attack suspect listed the names of other AI CEOs and investors in a 'last warning' note, the feds said

A Texas man, 20-year-old Daniel Moreno-Gama, was charged with attempted murder after allegedly throwing a Molotov cocktail at OpenAI CEO Sam Altman's San Francisco home on April 10, 2026, with surveil

industryr-chatgpt

Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence

arXiv:2604.09104v1 Announce Type: cross Abstract: Scheming, the covert pursuit of misaligned goals by AI systems, represents a potentially catastrophic risk, yet scheming research suffers from signifi

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

arXiv:2604.08988v1 Announce Type: new Abstract: Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, faili

{sf TriDeliver}: Cooperative Air-Ground Instant Delivery with UAVs, Couriers, and Crowdsourced Ground Vehicles

arXiv:2604.09049v1 Announce Type: new Abstract: Instant delivery, shipping items before critical deadlines, is essential in daily life. While multiple delivery agents, such as couriers, Unmanned Aeria

applicationsarxiv-cs-ro

SPP-SBL: Space-Power Prior Sparse Bayesian Learning for Block Sparse Recovery

model-releasesarxiv-cs-lg

arXiv:2505.08518v2 Announce Type: replace-cross Abstract: The recovery of block-sparse signals with unknown structural patterns remains a fundamental challenge in structured sparse signal reconstructi

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

arXiv:2604.08865v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard tok

StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning

arXiv:2604.08620v1 Announce Type: cross Abstract: Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-differenc

Structured Exploration and Exploitation of Label Functions for Automated Data Annotation

arXiv:2604.08578v1 Announce Type: cross Abstract: High-quality labeled data is critical for training reliable machine learning and deep learning models, yet manual annotation remains costly and error-

Summary: AI Governance to Avoid Extinction

With AI capabilities rapidly increasing, humans appear close to developing AI systems that are better than human experts across all domains. This raises a series of questions about how the world will—

safetymiri

Agents

Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study

arXiv:2604.08621v1 Announce Type: new Abstract: In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging str

agentsarxiv-cs-ai

SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data

arXiv:2604.09411v1 Announce Type: new Abstract: Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dens

applicationsarxiv-cs-cv

Agents

'Take Me Home, Wi-Fi Drone': A Drone-based Wireless System for Wilderness Search and Rescue

arXiv:2604.09115v1 Announce Type: cross Abstract: Wilderness Search and Rescue (WiSAR) represents a longstanding and critical societal challenge, demanding innovative and automatic technological solut

agentsarxiv-cs-ro

Task-Distributionally Robust Data-Free Meta-Learning

arXiv:2311.14756v2 Announce Type: replace-cross Abstract: Data-Free Meta-Learning (DFML) aims to enable efficient learning of unseen few-shot tasks, by meta-learning from multiple pre-trained models w

applicationsarxiv-cs-ai

Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems

arXiv:2511.09829v3 Announce Type: replace Abstract: Adversarial patches have emerged as a popular privacy-preserving approach for resisting AI-driven surveillance systems. However, their conspicuous a

applicationsarxiv-cs-ai

TinyNeRV: Compact Neural Video Representations via Capacity Scaling, Distillation, and Low-Precision Inference

model-releasesarxiv-cs-cv

arXiv:2604.09220v1 Announce Type: new Abstract: Implicit neural video representations encode entire video sequences within the parameters of a neural network and enable constant time frame reconstruct

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models

arXiv:2603.01400v2 Announce Type: replace Abstract: Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pru

researcharxiv-cs-cv

Toward World Models for Epidemiology

arXiv:2604.09519v1 Announce Type: new Abstract: World models have emerged as a unifying paradigm for learning latent dynamics, simulating counterfactual futures, and supporting planning under uncertai

safetyarxiv-cs-lg

Towards Knowledgeable Deep Research: Framework and Benchmark

arXiv:2604.07720v2 Announce Type: replace Abstract: Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive r

Unbiased Rectification for Sequential Recommender Systems Under Fake Orders

arXiv:2604.08550v1 Announce Type: cross Abstract: Fake orders pose increasing threats to sequential recommender systems by misleading recommendation results through artificially manipulated interactio

VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning

arXiv:2604.08639v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) is essential for deploying deep learning models in safety critical applications, yet no consensus exists on which UQ m

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

arXiv:2604.08558v1 Announce Type: cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent t…

model-releasesjerry-liu--x

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark t

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

arXiv:2603.03099v5 Announce Type: replace-cross Abstract: Despite Adam demonstrating faster empirical convergence than SGD in many applications, much of the existing theory yields guarantees essential

creative_coding_

Nous Research's MacbethAI shared a post about creative coding, likely showcasing or discussing generative art, algorithmic design, or experimental programming techniques. The content probably highligh

researchnous-research--x

12 Apr 2026

https://x.com/dair_ai/status/2043354446923465200

DAIR.AI (Democratizing AI Research) is an organization focused on AI education and research democratization, frequently sharing updates on their X (formerly Twitter) account about prompt engineering,

researchdair-ai--x

12 Apr 2026

Hermes Agents can communicate with eachother on Telegram now! Check it out