Search: “safety”

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

arXiv:2607.24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evi

MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution

DGX agent

arXiv:2607.22832v1 Announce Type: new Abstract: Long-horizon embodied tasks require policies that execute many dependent actions before task success can be observed. Representing policies as executabl

safetyarxiv-cs-lg

28 Jul 2026

MIME: Multimodal Interactive Motion Encoder

arXiv:2607.22702v1 Announce Type: new Abstract: Text-motion representation learning has advanced rapidly, with growing interest in multi person interactions for animation, AR/VR, and embodied AI. Thes

Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric

arXiv:2607.23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested e

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

arXiv:2607.23607v1 Announce Type: cross Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/

Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance

arXiv:2607.23451v1 Announce Type: new Abstract: Multi-modal object Re-Identification (ReID) aims to retrieve specific objects by integrating complementary information from multiple modalities. However

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

arXiv:2602.05547v2 Announce Type: replace-cross Abstract: RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment

Multimodal Domain Generalization for Depression Detection: An Attention-Based BiLSTM Network with Domain-Adversarial Training

arXiv:2607.22794v1 Announce Type: cross Abstract: Automatic depression detection with deep learning has shown promise but often suffers from limited generalization due to domain shift arising from int

N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens

arXiv:2607.23782v1 Announce Type: new Abstract: We present N_0-VTLA, a vision-tactile-language-action (VTLA) foundation model capable of (1) fine-grained contact-rich manipulation with tactile percept

safetyarxiv-cs-ro

NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimization

arXiv:2607.23408v1 Announce Type: new Abstract: Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited. T

Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability

arXiv:2607.18368v2 Announce Type: replace Abstract: Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-pol

Model Releases

Not All LLM Reasoning is Visible in the Chain-of-Thought

model-releasesarxiv-cs-ai

arXiv:2607.22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode w

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

arXiv:2607.23855v1 Announce Type: cross Abstract: Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Des

Online Policy Evaluation for MDPs with Dynamic UBSR Measures

arXiv:2607.23030v1 Announce Type: new Abstract: Developing efficient function-approximation methods for policy evaluation is a fundamental challenge in risk-aware reinforcement learning. Existing appr

Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction

arXiv:2607.22729v1 Announce Type: cross Abstract: Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches r

Optimal Reward Shaping: Autonomous Car Parking Case Study

arXiv:2607.23617v1 Announce Type: new Abstract: Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulti

Outcome-Confounded Local Supervision in On-Policy Distillation

arXiv:2607.23731v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes

Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling

arXiv:2607.23772v1 Announce Type: cross Abstract: We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application. RMAB problems are solved using the Whittle ind

Parallel Tokenizers: Rethinking Encoder Models' Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages

arXiv:2510.06128v2 Announce Type: replace Abstract: Tokenization forms the basis of multilingual language models, yet existing methods often limit cross-lingual transfer by mapping semantically equiva

Perturbation-Aware Diffusion-Guided Hybrid Segmentation for Robust and Annotation-Efficient Plant Stress Phenotyping

arXiv:2607.23680v1 Announce Type: new Abstract: Semantic segmentation in agricultural imagery is often evaluated under in-domain protocols, yet practical deployment requires robustness to appearance p

PNAS: Over Half of All Academic Articles Now Show LLM Influence—7.3M-Paper Study [R]

Largest empirical study of AI penetration in academic publishing ever conducted—51%-by-2025 is the most authoritative quantitative marker yet of how thoroughly LLMs have reshaped scientific writing, a

safetyr-machinelearning

Predicting the Outcome of rTMS Depression Therapy using EEG Signals and CNN

arXiv:2607.22776v1 Announce Type: new Abstract: Repetitive transcranial magnetic stimulation (rTMS) is a non invasive therapy for Major Depressive Disorder (MDD). In this study, we generate images usi

PReSS: An Automated Black-Box Framework for Evaluating Political Stance Stability in LLMs

arXiv:2504.17052v4 Announce Type: replace Abstract: Existing evaluations of political bias in large language models (LLMs) typically classify outputs as left- or right-leaning. We extend this perspect

PRISM: Polynomial Representations for Interaction-Structured Motor Control

arXiv:2607.23473v1 Announce Type: new Abstract: Robot policies are typically MLPs mapping observations to actions. Yet robot observations are physical variables, and many action-relevant cues arise no

safetyarxiv-cs-ro

PRISM: Prompt Refinement via Image-grounded Self-rewarding Mechanism for Text-to-Image Generation

arXiv:2607.24353v1 Announce Type: new Abstract: Text-to-image generation models can synthesize high-quality images from natural language descriptions, but their performance remains highly sensitive to

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks

arXiv:2607.22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing traject

Reconstruction of SINR Maps from Sparse Measurements using Group Equivariant Non-Expansive Operators

arXiv:2507.19349v3 Announce Type: replace Abstract: As sixth generation (6G) wireless networks evolve, accurate signal-to-interference-noise ratio (SINR) maps are becoming increasingly critical for ef

Regulating for AI Legitimacy

arXiv:2607.24391v1 Announce Type: cross Abstract: AI systems already govern. They rank speech and allocate attention, filter applicants and triage claims. The dominant frame for AI governance, alignme

Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance

arXiv:2607.22667v1 Announce Type: new Abstract: This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime se

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

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

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

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

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

Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity

arXiv:2512.12713v2 Announce Type: replace-cross Abstract: Control policies are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which require architecture selec

Shift-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment

arXiv:2501.19060v4 Announce Type: replace Abstract: Vision-language models (VLMs), such as CLIP, adapt effectively to downstream tasks through prompt tuning, but fine-tuning can misalign predictive co

Sign-Symmetry Learning Rules are Robust Fine-Tuners

arXiv:2502.05925v2 Announce Type: replace-cross Abstract: Backpropagation (BP) has long been the predominant method for training neural networks due to its effectiveness. However, numerous alternative

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation

arXiv:2607.24025v1 Announce Type: cross Abstract: Transformer architectures have achieved remarkable success across diverse domains; however, directly applying their standard self-attention mechanism

StageGuard: Physiologically Constrained Sleep Staging

arXiv:2607.23284v1 Announce Type: new Abstract: Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficie

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs

arXiv:2607.23046v1 Announce Type: new Abstract: Recent high-resolution Multimodal Large Language Models (MLLMs) generate thousands of visual tokens per input, leading to a visual token explosion that

Systematic Analysis of Large Language Models and Transformer-Based Machine Translation for English-Tamil and Tamil-English Across Diverse Datasets

arXiv:2607.24515v1 Announce Type: new Abstract: The challenge of Machine Translation for low resource languages such as Tamil is primarily caused by the restricted amount of parallel data for these la

Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts

arXiv:2607.24611v1 Announce Type: new Abstract: Deep learning models have achieved state-of-the-art performance in several computer vision tasks. However, they experience severe performance degradatio

The administration is very consistent: All aspects of foreign involvement in AI are banned: people (students and employees), hardware and mo…

The administration is very consistent: All aspects of foreign involvement in AI are banned: people (students and employees), hardware and models. And funding is down to a drip and capital allocation i

safetygary-marcus--x

The Agentic AI Foundation updates MCP with a fully stateless architecture, a hardened authentication model, a formal 12-month deprecation policy, and more (Michael Nuñez/VentureBeat)

Michael Nuñez / VentureBeat: The Agentic AI Foundation updates MCP with a fully stateless architecture, a hardened authentication model, a formal 12-month deprecation policy, and more — The Model Cont

safetytechmeme

The Curse of Precision: A Data Scaling Law for High-Precision Robotic Manipulation

arXiv:2607.23108v1 Announce Type: new Abstract: While scaling laws for imitation learning have primarily focused on generalization in open-world settings, the relationship between data and precision i

safetyarxiv-cs-ro

The Entropic Bound for Transformers: Why Static Rank Fails and Attention-Native Rank Recovers

arXiv:2607.23050v1 Announce Type: new Abstract: Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is th

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

arXiv:2607.24720v1 Announce Type: cross Abstract: Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are tra

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

arXiv:2607.23181v1 Announce Type: new Abstract: Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen sc