All entries

A Dataset for Automatic Vocal Mode Classification

arXiv:2601.18339v2 Announce Type: replace-cross Abstract: The Complete Vocal Technique (CVT) is a school of singing developed in the past decades by Cathrin Sadolin et al.. CVT groups the use of the v

researcharxiv-cs-lg

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

DGX agent

arXiv:2602.23163v3 Announce Type: replace Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanis

researcharxiv-cs-ai

30 Apr 2026

A Deep Dive into Deep Agents

A Deep Dive into Deep Agents 🚀DeepAgents deploy is a simple, configuration driven way to get an agent harness deployed to the cloud deepagents.toml is the file that configures it. It has four sections

agentsharrison-chase--x

A Diffeomorphism Groupoid and Algebroid Framework for Discontinuous Image Registration

arXiv:2603.11806v2 Announce Type: replace-cross Abstract: In this paper, we propose a novel mathematical framework for piecewise diffeomorphic image registration that involves discontinuous sliding mo

researcharxiv-cs-cv

A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models

arXiv:2604.26351v1 Announce Type: new Abstract: Language models (LMs) behave more like humans when their cognitive resources are restricted, particularly in predicting sentence processing costs such a

Industry

A look at Eka, which trains its robotic claw on a 'vision-force-action model' incorporating realistic joints, motors, and physics principles into its simulation (Will Knight/Wired)

Will Knight / Wired: A look at Eka, which trains its robotic claw on a “vision-force-action model” incorporating realistic joints, motors, and physics principles into its simulation — From sorting chi

industrytechmeme

A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification

arXiv:2604.26807v1 Announce Type: new Abstract: Despite being resource-intensive to train, 3D convolutional neural networks (CNNs) have been the standard approach to classify CT and MRI scans. Recent

Applications

A Multimodal and Explainable Machine Learning Approach to Diagnosing Multi-Class Ejection Fraction from Electrocardiograms

arXiv:2604.25942v1 Announce Type: new Abstract: Left ventricular ejection fraction (LVEF) assessment depends on echocardiography, limiting access in primary care and resource-constrained settings. We

applicationsarxiv-cs-lg

A Multimodal Depth-Aware Method For Embodied Reference Understanding

arXiv:2510.08278v3 Announce Type: replace Abstract: Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues. While

researcharxiv-cs-cv

A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection

arXiv:2604.26379v1 Announce Type: new Abstract: Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is lab

safetyarxiv-cs-cv

A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows

model-releasesarxiv-cs-cv

arXiv:2604.26462v1 Announce Type: new Abstract: Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows.

A New Semisupervised Technique for Polarity Analysis using Masked Language Models

arXiv:2604.26230v1 Announce Type: new Abstract: I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns pol

A Note on How to Remove the lnln T Term from the Squint Bound

arXiv:2604.26926v1 Announce Type: new Abstract: In Orabona and Pal [2016], we introduced the shifted KT potentials, to remove the ln ln T factor in the parameter-free learning with expert bound. In th

A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio

model-releasesarxiv-cs-ai

arXiv:2409.06624v4 Announce Type: replace-cross Abstract: Large Language Models (LLM) often need to be Continual Pre-Trained (CPT) to obtain unfamiliar language skills or adapt to new domains. The hug

A Priori Sampling of Transition States with Guided Diffusion

arXiv:2603.25980v2 Announce Type: replace-cross Abstract: Transition states, the first-order saddle points on the potential energy surfaces, govern the kinetics and mechanisms of chemical reactions an

researcharxiv-cs-lg

Hardware

A projection-based framework for gradient-free and parallel learning

arXiv:2506.05878v2 Announce Type: replace Abstract: We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradien

hardwarearxiv-cs-lg

A Quantitative Confirmation of the Currier Language Distinction

arXiv:2604.25979v1 Announce Type: cross Abstract: We present a quantitative analysis of character-pair substitution ratios in the Voynich manuscript, testing whether Currier's A/B language distinction

A Randomized PDE Energy driven Iterative Framework for Efficient and Stable PDE Solutions

arXiv:2604.25943v1 Announce Type: cross Abstract: Efficient and stable solution of partial differential equations (PDEs) is central to scientific and engineering applications, yet existing numerical s

A Scaled Three-Vehicle Platooning Platform

arXiv:2604.25963v1 Announce Type: new Abstract: Vehicle platooning has attracted increasing attention as a promising approach to improve traffic efficiency, energy consumption, and roadway safety thro

safetyarxiv-cs-ro

A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework

arXiv:2604.25933v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly generate and process clinical text, scalable evaluation has become critical. LLM-as-a-Judge (LaaJ), which

safetyarxiv-cs-ai

A Self-Calibrating Framework for Analog Circuit Sizing Using LLM-Derived Analytical Equations

arXiv:2604.07387v2 Announce Type: replace-cross Abstract: We present a design automation framework for analog circuit sizing that produces calibrated, topology-specific analytical equations from raw c

A self-evolving agent for explainable diagnosis of DFT-experiment band-gap mismatch

model-releasesarxiv-cs-ai

arXiv:2604.26703v1 Announce Type: cross Abstract: Standard density functional theory (DFT) routinely misclassifies the electronic ground state of correlated and structurally complex compounds, predict

A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication

arXiv:2604.25972v1 Announce Type: cross Abstract: In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their action

agentsarxiv-cs-ai

A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models

arXiv:2510.08049v3 Announce Type: replace-cross Abstract: Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward m

safetyarxiv-cs-ai

A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety

arXiv:2505.17342v2 Announce Type: replace Abstract: Safe Reinforcement Learning (SafeRL) is the subfield of reinforcement learning that explicitly deals with safety constraints during the learning and

safetyarxiv-cs-lg

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

arXiv:2505.10924v4 Announce Type: replace-cross Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emul

safetyarxiv-cs-ai

A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection

model-releasesarxiv-cs-cl

arXiv:2604.26319v1 Announce Type: new Abstract: Stance detection identifies the attitude of a text author toward a given target. Recent studies have explored various LLM-based strategies for this task

A Toolkit for Detecting Spurious Correlations in Speech Datasets

arXiv:2604.26676v1 Announce Type: cross Abstract: We introduce a toolkit for uncovering spurious correlations between recording characteristics and target class in speech datasets. Spurious correlatio

Tutorials

A Virtual Mechanical Interaction Layer Enables Resilient Human-to-Robot Object Handovers

arXiv:2511.19543v2 Announce Type: replace Abstract: Object handover is a common form of interaction that is widely present in collaborative tasks. However, achieving it efficiently remains a challenge

tutorialsarxiv-cs-ro

Applications

AARP and Appian bring AI modernization to the back office

AI-led process modernization is redefining how enterprises deploy AI — moving beyond broad rollouts to embedding intelligence into specific, governed business processes that actually scale. But the li

applicationssiliconangle

Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding

arXiv:2604.26779v1 Announce Type: cross Abstract: RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central

safetyarxiv-cs-cl

ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance

arXiv:2604.26348v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image generation, yet their training is predominantly driven by full-reference objectives that en

Local Ai

Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection

arXiv:2509.11058v2 Announce Type: replace Abstract: Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due

local-aiarxiv-cs-cv

Industry

Actual feedback we’ve gotten over the last few years: 2019: The what? For what? Why spend time on this? Maybe you should try doing something…

industrycristobal-valenzuela--x

Actual feedback we’ve gotten over the last few years: 2019: The what? For what? Why spend time on this? Maybe you should try doing something else. 2020: Why would you keep spending time on this? Will

Hardware

AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control

arXiv:2601.11568v2 Announce Type: replace-cross Abstract: Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gra

hardwarearxiv-cs-ai

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

model-releasesarxiv-cs-cl

arXiv:2603.16496v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step

Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning

arXiv:2604.26340v1 Announce Type: new Abstract: LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation

Local Ai

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL

arXiv:2603.19470v2 Announce Type: replace-cross Abstract: Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and furthe

local-aiarxiv-cs-ai

Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning

arXiv:2508.19900v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables learning effective policies from fixed datasets without any environment interaction. Existing methods ty

Adaptive Transform Coding for Semantic Compression

arXiv:2604.26492v1 Announce Type: cross Abstract: Visual data compression is shifting from human-centered reconstruction to machine-oriented representation coding. In this setting, an image is often m

researcharxiv-cs-cv

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control

arXiv:2604.26326v1 Announce Type: cross Abstract: Reinforcement learning (RL) has unlocked complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performa

Advancing multi-site emission control: A physics-informed transfer learning framework with mixture of experts for carbon-pollutant synergy

arXiv:2604.26571v1 Announce Type: new Abstract: Municipal solid waste incineration is increasingly central to urban waste management, yet its sustainability benefit depends on controlling carbon emiss

researcharxiv-cs-lg

Adversarial Robustness of NTK Neural Networks

arXiv:2604.25965v1 Announce Type: cross Abstract: Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversa

safetyarxiv-cs-lg

Affective Flow Language Model for Emotional Support Conversation

model-releasesarxiv-cs-ai

arXiv:2602.08826v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains cha

Applications

AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages

arXiv:2604.00706v2 Announce Type: replace Abstract: Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at commun

applicationsarxiv-cs-cl

AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents

arXiv:2604.26522v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments

agentsarxiv-cs-ai

Agentic opportunity: OpenAI and Stripe build for rising tide of new entrepreneurial firms

In corporate parlance, any metric on a chart that shows rapid, significant growth over a short period of time is known as a “hockey stick.” On Wednesday, Stripe Inc. Chief Executive Patrick Collison s

agentssiliconangle

Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests

model-releasesarxiv-cs-cl

arXiv:2601.17617v3 Announce Type: replace-cross Abstract: LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understan