All entries

Rosetta Memory: Adaptive Memory for Cross-LLM Agents

arXiv:2606.07711v1 Announce Type: cross Abstract: Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning,

Applications

Routine laboratory trajectories encode the onset of organ-level complications in cancer

DGX agent

arXiv:2606.08538v1 Announce Type: new Abstract: Routine laboratory panels drawn during cancer treatment constitute longitudinal physiological recordings of organ function, yet their temporal structure

applicationsarxiv-cs-lg

9 Jun 2026

RPO-PDT: Demonstrating Role-Play-Based Knowledge Adaptation for Student Support Dialogue (Demonstration System)

arXiv:2606.09255v1 Announce Type: new Abstract: We present RPO-PDT: a retrieval-grounded, role-play-based dialogue system for adaptive student support in higher education. RPO-PDT is: (1) able to prov

safetyarxiv-cs-ro

Applications

RT-SDGOD: Real-Time Single-Domain Generalized Object Detection

arXiv:2606.09367v1 Announce Type: new Abstract: In real-world deployment under strict real-time constraints, weather and imaging variations induce significant distribution shifts, severely degrading d

applicationsarxiv-cs-cv

RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models

arXiv:2606.08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation. High-quality benchmarks are critical infrastructure for

Rubrik turns its platform into an AI agent and ships Agent Cloud for Claude

model-releasessiliconangle

Rubrik Inc. today turned its data security platform into an autonomous agent and made its control layer for Anthropic PBC’s Claude generally available, the headline items in a wave of announcements at

Applications

Rule-based autocorrection of Piping and Instrumentation Diagrams (P&IDs) on graphs

arXiv:2502.18493v2 Announce Type: replace-cross Abstract: A piping and instrumentation diagram (P&ID) is a central reference document in chemical process engineering. Currently, chemical engineers man

applicationsarxiv-cs-ai

RunAgent SuperBrowser: A Theory of Autonomous Web Navigation Grounded in Human Browsing Behaviour

arXiv:2606.09399v1 Announce Type: new Abstract: We present SUPERBROWSER, an autonomous web-navigation agent designed against a single guiding hypothesis: a web agent should browse the way a person bro

SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning

arXiv:2511.05355v3 Announce Type: replace Abstract: Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action

safetyarxiv-cs-lg

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization

arXiv:2606.08496v1 Announce Type: cross Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse featur

researcharxiv-cs-lg

Safe, Fluent and Acceptable Motion Generation and Execution for Human--Robot Interaction in Manufacturing Environments

arXiv:2606.08741v1 Announce Type: new Abstract: Robots operating in human environments must not only ensure physical safety but also exhibit behaviors that are understandable, fluent, and acceptable t

safetyarxiv-cs-ro

Local Ai

Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions

arXiv:2606.09719v1 Announce Type: new Abstract: Autonomous mobile robots operating in tight environments require motion planning frameworks that account for the physical footprint of the robot. Simpli

local-aiarxiv-cs-ro

Safe-RULE: Safe Reinforcement UnLEarning

arXiv:2606.09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such

SafeECGMatch: Calibration-Aware Joint Frequency and Time Space Semi-Supervised Learning for Open-Set ECG Classification

arXiv:2606.08037v1 Announce Type: cross Abstract: Electrocardiogram (ECG) classification models often suffer from severe label scarcity, making semi-supervised learning (SSL) an attractive strategy fo

SafeRun: Enabling Determinism in LLM Planning for Running

arXiv:2606.09027v1 Announce Type: cross Abstract: Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic natur

Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators

arXiv:2606.07874v1 Announce Type: new Abstract: LLMs-as-judges are the only way to evaluate safety at scale. Despite their importance, LLM-judges themselves are rarely evaluated beyond human agreement

Agents

SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection

arXiv:2606.08146v1 Announce Type: new Abstract: Fraud detection in payment, e-commerce, and telecommunications systems requires accuracy at the individual level, robustness under severe class imbalanc

agentsarxiv-cs-ai

SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

arXiv:2511.18493v4 Announce Type: replace-cross Abstract: The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole

Industry

SailPoint shares fall despite earnings beat and raised guidance

Shares in SailPoint Inc. fell more than 11% today after the identity security company beat analyst expectations on revenue and adjusted earnings and raised its outlook, in a selloff that pointed to in

industrysiliconangle

Local Ai

SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths

arXiv:2606.09404v1 Announce Type: cross Abstract: Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interact

local-aiarxiv-cs-ai

Tutorials

Sample-Efficient LLM-Based Detection of Malicious Web Server Logs with Forensically Explainable Reasoning

arXiv:2606.08649v1 Announce Type: cross Abstract: Forensic analysis of web server logs demands both accurate detection and human-readable explanations that can satisfy legal requirements. We present C

tutorialsarxiv-cs-ai

Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

arXiv:2606.07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility. We identify a data-induced failure mode, PhysHack, in wh

SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models

arXiv:2606.07705v1 Announce Type: cross Abstract: Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing pra

SC3: The Multi-Solvent Solubility Challenge and Benchmark

model-releasesarxiv-cs-lg

arXiv:2606.07656v1 Announce Type: cross Abstract: Solubility prediction is a standard benchmark in computational chemistry, yet multi-solvent models which reportedly approach the experimental-noise ce

Scaffold Effects on GAIA: A Controlled Comparison

arXiv:2606.08529v1 Announce Type: new Abstract: Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well

Hardware

Scale Robot Reinforcement Learning with NVIDIA Isaac Lab on Amazon SageMaker AI

In this post, we show how to train robot policies for the Unitree H1 humanoid with NVIDIA Isaac Lab on Amazon SageMaker AI across two compute options: Amazon SageMaker HyperPod and Amazon SageMaker Tr

hardwareaws-ml-blog

ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization

arXiv:2606.07618v1 Announce Type: cross Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales. Howev

Scaling by Diversified Experience for Vision-Language-Action Models

model-releasesarxiv-cs-cv

arXiv:2606.09009v1 Announce Type: new Abstract: Vision-Language-Action models face significant challenges in real-world deployment due to the entanglement of high-level reasoning with low-level contro

Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition

arXiv:2606.08797v1 Announce Type: cross Abstract: Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified model

Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics

model-releasesarxiv-cs-lg

arXiv:2602.15253v2 Announce Type: replace Abstract: Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transf

Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism

arXiv:2606.09377v1 Announce Type: cross Abstract: Formal neural network verification -- proving that a network satisfies safety properties for all inputs in a specified domain -- is bounded in practic

Scaling Participation in Modular AI Systems

arXiv:2606.07812v1 Announce Type: new Abstract: Humanity is a mosaic of multifaceted talents and needs, and any truly intelligent AI must reflect that richness. Yet the LLMs used by all are built by t

scCBGM: Interpretable Single-Cell Counterfactual Editing

model-releasesarxiv-cs-lg

arXiv:2606.07760v1 Announce Type: new Abstract: Understanding cellular phenotypes and how they respond to perturbations is critical for disease biology and therapeutic design. Single-cell RNA sequenci

SceneConductor: 3D Scene Generation from Single Image with Multi-Agent Orchestration

arXiv:2606.08402v1 Announce Type: cross Abstract: Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context fro

Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems

arXiv:2606.08034v1 Announce Type: cross Abstract: Symbolic benchmarks have emerged as a key approach to assess model robustness under minor modifications to STEM-related questions. However, existing s

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing

model-releasesarxiv-cs-cv

arXiv:2602.09809v2 Announce Type: replace Abstract: Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorr

SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents

arXiv:2606.08234v1 Announce Type: new Abstract: LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layers remain structurally divorced from core reasoning

Industry

Screwworms in US: Human risk is low—but they can burrow through your skull

New World screwworms were detected in the United States in June 2026 for the first time in decades , with no reported human infestations and low human risk . When humans are infected, infestations cau

industryars-technica

SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks

arXiv:2503.08703v4 Announce Type: replace-cross Abstract: Event cameras provide superior temporal resolution, dynamic range, energy efficiency, and pixel bandwidth. Spiking Neural Networks (SNNs) natu

researcharxiv-cs-cv

Agents

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

arXiv:2606.09730v1 Announce Type: new Abstract: Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model

agentsarxiv-cs-ai

Industry

Seattle City Council votes 9-0 to enact a one-year moratorium on new large data centers and study their impact; Mayor Katie Wilson is expected to sign the bill (Greg Kim/The Seattle Times)

Greg Kim / The Seattle Times: Seattle City Council votes 9-0 to enact a one-year moratorium on new large data centers and study their impact; Mayor Katie Wilson is expected to sign the bill — Amid a g

industrytechmeme

SecureClaw: Clawing Back Control of LLM Agents

arXiv:2606.09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext in

Securing Self-supervised Data Curation for Foundation Models Robustness

arXiv:2606.09511v1 Announce Type: new Abstract: Self-supervised data curation provides a pathway to scaling and improving the generalization capabilities of machine learning models. By leveraging self

researcharxiv-cs-cv

See how Claude Fable 5 compares across every model: http://cursor.com/evals

Claude Fable 5 is compared against other AI models on various evaluation metrics through Cursor's benchmarking tool. The evaluation likely covers performance across different tasks such as coding, rea

model-releasescursor--x

See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning

arXiv:2606.09262v1 Announce Type: new Abstract: Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underl

safetyarxiv-cs-cv

See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding

arXiv:2606.09064v1 Announce Type: cross Abstract: Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods stil

Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation

arXiv:2606.08492v1 Announce Type: cross Abstract: Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user pr

Local Ai

Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization

arXiv:2606.09587v1 Announce Type: cross Abstract: People are increasingly using AI for creative tasks such as writing. While adoption continues to grow, this form of use risks undermining individual c

local-aiarxiv-cs-ai