All entries

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

arXiv:2601.21636v3 Announce Type: replace Abstract: We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-

researcharxiv-cs-lg

SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery

DGX agent

arXiv:2510.22665v3 Announce Type: replace-cross Abstract: Synthetic Aperture Radar (SAR) is a critical imaging modality due to its all-weather operational capability. Although recent advances in self-

model-releasesarxiv-cs-ai

18 May 2026

Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip

arXiv:2605.16114v1 Announce Type: cross Abstract: We propose a scalable neuromorphic architecture based on spiking dynamics emerging from the autonomous time-continuous evolution of clockless (asynchr

agentsarxiv-cs-lg

ScreenSearch: Uncertainty-Aware OS Exploration

arXiv:2605.16024v1 Announce Type: new Abstract: Desktop GUI agents operate under partial observability: visually similar screens can correspond to different underlying workflow states, so locally plau

SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch

arXiv:2605.15204v1 Announce Type: new Abstract: Multi-agent orchestration frameworks such as LangChain, LangGraph, and CrewAI route tasks through graph-based pipelines but do not enforce the stage con

Industry

Seagate shares drop 6.87%, leading a group-wide sell-off after comments from its CEO raised concerns it won't be able to meet demand fueled by the AI buildout (CJ Haddad/CNBC)

CJ Haddad / CNBC: Seagate shares drop 6.87%, leading a group-wide sell-off after comments from its CEO raised concerns it won't be able to meet demand fueled by the AI buildout — Shares of memory chip

industrytechmeme

Searching on a Budget: HW-NAS with 10 Latency Probes

model-releasesarxiv-cs-lg

arXiv:2504.00663v2 Announce Type: replace Abstract: Existing hardware-aware NAS (HW-NAS) methods typically assume access to precise information circa the target device, either via analytical approxima

Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models

arXiv:2605.16165v1 Announce Type: cross Abstract: Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality compe

Industry

Security researcher Peter G. Neumann, who criticized lax industry attitudes toward computer security and digital privacy, died on May 17 at the age of 93 (John Markoff/New York Times)

John Markoff / New York Times: Security researcher Peter G. Neumann, who criticized lax industry attitudes toward computer security and digital privacy, died on May 17 at the age of 93 — For decades,

industrytechmeme

Local Ai

See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation

arXiv:2605.15585v1 Announce Type: new Abstract: Large language models can generate executable code for educational animations, but the resulting renders often exhibit visual defects, including element

local-aiarxiv-cs-ai

Local Ai

SEED: Targeted Data Selection by Weighted Independent Set

arXiv:2605.15691v1 Announce Type: new Abstract: Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversi

local-aiarxiv-cs-lg

Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

arXiv:2503.02597v3 Announce Type: replace-cross Abstract: Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries,

researcharxiv-cs-ai

Seeing What Matters: Visual Preference Policy Optimization for Visual Generation

arXiv:2511.18719v4 Announce Type: replace Abstract: Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) in

safetyarxiv-cs-cv

Local Ai

Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning

arXiv:2605.15997v1 Announce Type: new Abstract: Recent progress in deep learning has significantly advanced CT image analysis, particularly for segmentation tasks. However, these advances are largely

local-aiarxiv-cs-cv

Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning

arXiv:2605.15523v1 Announce Type: new Abstract: Scene text editing aims to modify text in a target region of an image while preserving surrounding background style and texture. Existing methods rely s

researcharxiv-cs-cv

Self-Supervised ImageNet Representations for In Vivo Confocal Microscopy: Tortuosity Grading without Segmentation Maps

arXiv:2603.15269v2 Announce Type: replace Abstract: The tortuosity of corneal nerve fibers are used as indication for different diseases. Current state-of-the-art methods for grading the tortuosity he

researcharxiv-cs-cv

Self-Supervised Learning by Curvature Alignment

arXiv:2511.17426v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance,

safetyarxiv-cs-cv

SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization

arXiv:2510.25404v3 Announce Type: replace-cross Abstract: Optimizing an experimental system can be extremely challenging when each experiment is expensive, time-consuming, or difficult to perform. Exi

Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment

arXiv:2605.15720v1 Announce Type: new Abstract: Medical referring image segmentation (MRIS) requires pixel-level masks aligned with textual descriptions of anatomical locations, making annotation cost

safetyarxiv-cs-cv

seriou question: how do you handle an intellectual doppelganger who has systematically started adopting every position you have argued for f…

seriou question: how do you handle an intellectual doppelganger who has systematically started adopting every position you have argued for for 30 years while presenting each idea as if it were his own

safetygary-marcus--x

SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting

arXiv:2511.18127v2 Announce Type: replace Abstract: Real-time 3D hand forecasting is a critical component for fluid human-computer interaction in applications like AR and assistive robotics. However,

researcharxiv-cs-cv

SGNO: Spectral Generator Neural Operators for Stable Long Horizon PDE Rollouts

arXiv:2602.18801v2 Announce Type: replace Abstract: Autoregressive neural PDE surrogates predict future states by repeatedly applying a learned one-step operator. This is a simple and widely used meth

researcharxiv-cs-lg

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation

model-releasesarxiv-cs-cl

arXiv:2605.16117v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities across diverse NLP applications, such as translation, text generation, and question a

Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach

arXiv:2501.19128v5 Announce Type: replace-cross Abstract: In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for

agentsarxiv-cs-ai

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?

arXiv:2605.15877v1 Announce Type: cross Abstract: Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suff

tutorialsarxiv-cs-ai

Sharp Spectral Thresholds for Logit Fixed Points

arXiv:2605.15651v1 Announce Type: cross Abstract: Softmax feedback systems are a common mathematical core of entropy-regularized reinforcement learning, logit game dynamics, population choice, and mea

researcharxiv-cs-ai

ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents

arXiv:2605.16116v1 Announce Type: new Abstract: Developing and evaluating e-commerce web agents requires environments that preserve meaningful task structure while enabling controllable, reproducible,

Sigma Computing seals $80M funding round as it pivots toward ‘agentic analytics’

Cloud-native data analytics startup Sigma Computing Inc. has closed on an 80 million Series E funding round that doubles its valuation to 3 billion, almost a year to the day after its previous Series

agentssiliconangle

Industry

Sigma, which sells a cloud-native analytics platform that sits on top of data warehouses, raised an 80M Series E led by Princeville Capital at a 3B valuation (Cristian Dina/The Next Web)

Cristian Dina / The Next Web: Sigma, which sells a cloud-native analytics platform that sits on top of data warehouses, raised an 80M Series E led by Princeville Capital at a 3B valuation — The round

industrytechmeme

Sign-Separated Finite-Time Error Analysis of Q-Learning

arXiv:2605.16103v1 Announce Type: new Abstract: This paper develops a sign-separated finite-time error analysis for constant step-size Q-learning. Starting from the switching-system representation, th

Simulation is a core part of how we build and evaluate robots. I spoke about simulation, robotics, and the role of interactive worlds at AI …

Simulation is a core part of how we build and evaluate robots. I spoke about simulation, robotics, and the role of interactive worlds at AI Engineer Singapore this past weekend! Full talk : https://ww

agentsyohei-nakajima--x

Simultaneous State Estimation and Online Model Learning in a Soft Robotic System

arXiv:2602.14092v2 Announce Type: replace-cross Abstract: Operating complex real-world systems, such as soft robots, can benefit from precise predictive control schemes that require accurate state and

tutorialsarxiv-cs-ro

Skew-adaptive conformal prediction

arXiv:2605.16145v1 Announce Type: cross Abstract: We develop a skew-adaptive extension of split conformal prediction for regression. The method starts from an asymmetric interval family centered at a

tutorialsarxiv-cs-lg

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

arXiv:2604.02268v2 Announce Type: replace Abstract: Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a rel

safetyarxiv-cs-lg

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces

arXiv:2605.15215v1 Announce Type: new Abstract: Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are t

SkiP: When to Skip and When to Refine for Efficient Robot Manipulation

arXiv:2605.15536v1 Announce Type: cross Abstract: Previous imitation learning policies predict future actions at every control step, whether in smooth motion phases or precise, contact-rich operation

SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV geolocalization

arXiv:2603.08063v3 Announce Type: replace Abstract: Cross-view UAV geolocalization is fundamentally a challenging large-scale image retrieval task, aiming to determine the geographic coordinates of Un

Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning

arXiv:2512.15693v2 Announce Type: replace Abstract: The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated vid

SLIP & ETHICS: Graduated Intervention for AI Emotional Companions

arXiv:2605.15915v1 Announce Type: cross Abstract: AI emotional companions face a safety-rapport paradox: restrictive safeguards can damage supportive alliance, while permissive systems risk user harm.

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models

arXiv:2602.01970v2 Announce Type: replace Abstract: Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-inten

researcharxiv-cs-ai

SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution

arXiv:2605.15308v1 Announce Type: new Abstract: LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for de

tutorialsarxiv-cs-ai

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory

model-releasesarxiv-cs-cl

arXiv:2605.15710v1 Announce Type: new Abstract: Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use ev

Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation

arXiv:2505.18853v2 Announce Type: replace Abstract: Diffusion models have achieved state-of-the-art performance in generating images, audio, and video, but their adaptation to text remains challenging

researcharxiv-cs-cl

Applications

So would this be legal under the ruling: Set up a charity, raise $100m etc When setting it up say you may set up a for profit & raise billio…

applicationsemad-mostaque--x

So would this be legal under the ruling: Set up a charity, raise $100m etc When setting it up say you may set up a for profit & raise billions Three years later set up for profit with IP transferred f

Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models

arXiv:2605.15424v1 Announce Type: new Abstract: Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficienc

SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval

arXiv:2605.15868v1 Announce Type: new Abstract: In this work, we address the critical yet underexplored challenge of symmetric multimodal-to-multimodal (MM2MM) retrieval, where queries and contexts ar

Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution

arXiv:2605.15301v1 Announce Type: new Abstract: Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks att

agentsarxiv-cs-ai

some good discussions and experiments around stateful agents in the replies, but seems like we’re not quite there yet, as in we’re starting …

some good discussions and experiments around stateful agents in the replies, but seems like we’re not quite there yet, as in we’re starting to track memory and traces, but not quite agent capability a

agentsyohei-nakajima--x