All entries

arXiv:2607.23389v1 Announce Type: cross Abstract: Conventional CAPTCHAs pose puzzles that modern AI systems increasingly solve, while behavioral and cryptographic-attestation defenses carry privacy or

hardwarearxiv-cs-lg

Restoration Flow Matching-Based Channel Refinement and Equalization Correction for MIMO Semantic Communications

DGX agent

arXiv:2607.23615v1 Announce Type: new Abstract: In multiple-input multiple-output (MIMO) semantic communication, imperfect channel state information (CSI) and equalization mismatch can seriously degra

researcharxiv-cs-lg

28 Jul 2026

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

arXiv:2607.24731v1 Announce Type: cross Abstract: On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should beha

Rethinking Expert Training for Model Merging with Prompt Learning

model-releasesarxiv-cs-cv

arXiv:2607.24465v1 Announce Type: new Abstract: Model merging aims to combine multiple domain-specialized experts trained from a shared foundation model into a single multi-task model. Existing approa

Rethinking the Generation Order of Block Diffusion Language Models

arXiv:2607.24306v1 Announce Type: new Abstract: Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion model

researcharxiv-cs-cl

Retrieval-Augmented Generation of Ontologies from Relational Databases

arXiv:2506.01232v2 Announce Type: replace-cross Abstract: Deriving OWL ontologies from relational database schemas supports semantic interoperability and downstream tasks such as knowledge graph popul

Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Management

arXiv:2607.24352v1 Announce Type: new Abstract: The aim of this article is to verify whether integrating large language models (LLMs) with the Retrieval-Augmented Generation (RAG) architecture enables

local-aiarxiv-cs-cl

Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting

arXiv:2602.17634v2 Announce Type: replace-cross Abstract: Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time ser

Revitalizing Public Urban Places through Cultural and Political Memory: A Technological Approach with LLMs and Augmented Reality

arXiv:2607.22613v1 Announce Type: cross Abstract: This paper explores the intersection of memory, place, and identity, examining how new technologies, particularly Apple Vision Pro, can illuminate thi

Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety Architecture

arXiv:2607.22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk. Existi

Risk reversal for least squares estimators under nested convex constraints

model-releasesarxiv-cs-lg

arXiv:2601.16041v2 Announce Type: replace-cross Abstract: In constrained stochastic optimization, one expects that restricting the feasible set, provided it still contains the true parameter, should n

RM-Distiller: Exploiting Generative LLM for Reward Model Distillation

arXiv:2601.14032v2 Announce Type: replace Abstract: Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-qua

safetyarxiv-cs-cl

RMS@CC-MMD 2026: Multimodal Misogyny Detection via Geometric Interaction and Multi-View Consensus

arXiv:2607.22709v1 Announce Type: cross Abstract: The proliferation of internet memes has introduced new complexities to automated content moderation, particularly in detecting misogyny. Memes often r

RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction

arXiv:2607.23758v1 Announce Type: new Abstract: Large-scale road surface reconstruction supports high-definition mapping, autonomous-driving perception, annotation, and simulation. Existing road-speci

agentsarxiv-cs-cv

Tools

Robot policies can move but can't think. LLMs can think but can't move. So we connected them. Real robot: 16.7% → 97.3% Sim (LIBERO-PRO): 12…

A team led by Liane Galanti linked large‑language models (LLMs) with robotic motion policies, allowing a robot to combine reasoning capabilities with physical movement. In experiments on a real robot,

toolstogether-ai--x

Robust 6-DoF Object Pose Tracking with Built-In Recovery under Occlusions and Rapid Object Motions

arXiv:2607.23468v1 Announce Type: new Abstract: Real-time 6-DoF object pose tracking is essential for many robotics applications, and several approaches exist. Yet even today's approaches remain unrel

safetyarxiv-cs-cv

Robust Conformalized Selection with Noisy Responses

arXiv:2607.22985v1 Announce Type: cross Abstract: Conformalized selection has been widely applied to select high-quality candidates from large datasets with rigorous uncertainty quantification, such a

local-aiarxiv-cs-lg

Robustifying pathology foundation models via fine-tuning

arXiv:2607.22861v1 Announce Type: cross Abstract: Pathology foundation models (FMs) produce powerful tile-level representations which remain sensitive to scanner and staining variability, undermining

Robustness and Cybersecurity in the EU Artificial Intelligence Act

arXiv:2502.16184v3 Announce Type: replace Abstract: The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems. While prior work has sought to cl

RODR: Riemannian Orthogonally Decoupled Regularization for Disentangled Manifold Representation

arXiv:2607.23958v1 Announce Type: new Abstract: Point cloud denoising is essentially a geometric recovery task that aims to reconstruct the intrinsic structure of a smooth 2D Riemannian manifold embed

RoleMix: Unifying Sequential and Non-Sequential Features via Semantic Tokenization for Post-Click Conversion Rate Prediction

arXiv:2607.22700v1 Announce Type: new Abstract: Post-click conversion rate (PCVR) prediction is central to industrial recommendation, but remains challenged by the structural mismatch between sparse,

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models

arXiv:2607.24447v1 Announce Type: new Abstract: On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories ge

local-aiarxiv-cs-cv

RRTrack: Robust and Recoverable Object 6D Pose Tracking for Dynamic Scenes

model-releasesarxiv-cs-cv

arXiv:2607.23669v1 Announce Type: new Abstract: Robust object 6D pose tracking is critical for robotic systems operating in dynamic and occluded scenes. Per-frame estimators are accurate but computati

SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotations

arXiv:2607.24706v1 Announce Type: new Abstract: Few-shot segmentation (FSS) commonly assumes clean pixel-level support masks, yet practical support supervision often uses boxes, scribbles, coarse mask

SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes

model-releasesarxiv-cs-cl

arXiv:2412.20541v2 Announce Type: replace Abstract: Memes act as cryptic tools for sharing sensitive ideas, often requiring contextual knowledge to interpret them correctly. It makes multimodal meme m

SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems

arXiv:2603.03536v2 Announce Type: replace-cross Abstract: Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an un

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI

arXiv:2607.22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem. SAGE is a safety-first, authoriz

Sam Altman: “Concentration of power with AI is a terrifying thing.” 'A lot of the talk about safety concerns is well-founded, and then a lot…

Sam Altman: “Concentration of power with AI is a terrifying thing.” 'A lot of the talk about safety concerns is well-founded, and then a lot of it is about people that just really, even if it's slight

safetyclem-delangue--x

Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations

arXiv:2607.22872v1 Announce Type: cross Abstract: Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressin

Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy

arXiv:2607.22554v1 Announce Type: new Abstract: Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same qu

Sampling Decisions: Exact Path-Space Correction, Prior Cancellation and Local-Boltzmann Guidance

arXiv:2503.14549v3 Announce Type: replace-cross Abstract: How can a cheap but biased sequential, finite-horizon sampler over a discrete space be corrected so that its terminal output follows a prescri

SARATR-X-v2: Scale-Aware Structural Pre-Training for SAR Foundation Models

arXiv:2607.23238v1 Announce Type: new Abstract: Masked image modeling has become a dominant paradigm for SAR pre-training, yet the design of the reconstruction target remains fundamentally unsettled.

SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs

arXiv:2607.22571v1 Announce Type: new Abstract: Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing ag

Scale Weight Decay and Train Better

arXiv:2607.23777v1 Announce Type: cross Abstract: The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant dec

Scaling GUI Agents with Visual State Transitions

arXiv:2607.24112v1 Announce Type: new Abstract: We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal

agentsarxiv-cs-ai

Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL

arXiv:2607.22572v1 Announce Type: new Abstract: Large language models can generate fluent SQL from natural language, but on real enterprise Oracle databases they frequently fail at execution time: col

local-aiarxiv-cs-ai

scMIR: a vision-language foundation model for single-cell light microscopy image representation

arXiv:2607.22712v1 Announce Type: cross Abstract: Single-cell light microscopy images have become an important data source for characterizing cell phenotypes, but their complexity and heterogeneity po

Applications

Scoping Review of AI, Metrology, and ESG in the Semiconductor Sector: Implications for Safe and Sustainable by Design (SSbD)

arXiv:2607.23082v1 Announce Type: cross Abstract: The semiconductor sector faces a dual transition: scaling manufacturing execution through Artificial Intelligence (AI) while satisfying stringent sust

applicationsarxiv-cs-ai

SCTA: An Agentic Framework for Stable and Interpretable Target Gene Discovery from Single-Cell RNA Sequencing

arXiv:2607.23821v1 Announce Type: new Abstract: Identifying therapeutic target genes from single-cell RNA sequencing (scRNA-seq) data remains a fundamental challenge in translational biology. Unlike b

agentsarxiv-cs-lg

SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions

arXiv:2607.18290v2 Announce Type: replace-cross Abstract: In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scie

local-aiarxiv-cs-ai

SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents

arXiv:2607.23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface task

agentsarxiv-cs-ai

Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling

arXiv:2510.14717v2 Announce Type: replace-cross Abstract: Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While

Segmentation Robustness and Predictive Utility in Glioblastoma Radiomics: Evidence for a Trade-off in Survival Modelling

arXiv:2607.23626v1 Announce Type: cross Abstract: Radiomic biomarkers derived from magnetic resonance imaging (MRI) have been widely investigated as non-invasive tools for tumor characterization and p

SEGRA: Structured Experience-Guided Graph Reasoning Agent for Gremlin Based Question Answering

arXiv:2607.22713v1 Announce Type: new Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historic

Self-Attention Dynamics with Rotary Position Embeddings: Twisted States and Explicit Consensus Rates on the Sphere

arXiv:2607.24502v1 Announce Type: cross Abstract: Rotary position embeddings (RoPE) modify attention scores through position-dependent rotations, but their effect on normalized token dynamics is not c

researcharxiv-cs-lg

Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents

arXiv:2607.24300v1 Announce Type: new Abstract: Self-improving agents accumulate capability by repeatedly rewriting procedural policies, controllers, or heuristic rules. They typically rely on self-au

safetyarxiv-cs-cl

Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation

arXiv:2607.23125v1 Announce Type: new Abstract: Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods

safetyarxiv-cs-lg

Self-Distillation of Hidden Layers for Self-Supervised Representation Learning

arXiv:2603.15553v2 Announce Type: replace Abstract: The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.g. MAE) that reconstruct raw low-level data, and