safety

ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents

arXiv:2606.27814v1 Announce Type: new Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillati

BiDeMem: Bidirectional Degradation Memory for Explainable Image Restoration

DGX agent

arXiv:2606.28112v1 Announce Type: cross Abstract: Degradation-aware prompts, conditions, and latent priors are increasingly used in image restoration, yet they are usually judged by a single endpoint:

safetyarxiv-cs-ai

29 Jun 2026

CacheMPC: Certified Cached Model Predictive Control for Quadruped Locomotion

arXiv:2606.28300v1 Announce Type: new Abstract: Model Predictive Control (MPC) is the standard predictive layer in hierarchical quadruped controllers, but the per-cycle QP solve limits the update rate

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training

arXiv:2602.16065v2 Announce Type: replace-cross Abstract: As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degr

Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

arXiv:2510.16492v4 Announce Type: replace Abstract: As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While

safetyarxiv-cs-cl

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

arXiv:2606.28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Exis

Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning

arXiv:2603.00374v2 Announce Type: replace Abstract: Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories. We co

Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding

arXiv:2604.02546v2 Announce Type: replace Abstract: Pretraining 3D encoders by aligning with Contrastive Language Image Pretraining (CLIP) has emerged as a promising direction to learn generalizable r

CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association

arXiv:2606.28179v1 Announce Type: cross Abstract: Identifying robust associations between cardiac imaging phenotypes and clinical diseases is fundamental to population-scale cardiovascular research an

CSD: Content-aware Speculative Decoding for Efficient Image Generation

arXiv:2606.27829v1 Announce Type: new Abstract: Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation,

CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation

arXiv:2606.27676v1 Announce Type: new Abstract: Achieving everyday tasks with humanoid robots requires coordinating stable locomotion with versatile manipulation. However, existing whole-body controll

Dangerous Liaisons of Convex Learning and Non-Affine Aggregation

arXiv:2606.28123v1 Announce Type: new Abstract: Last-iterate convergence and generalization guarantees in first-order convex learning hinge on the monotonicity of the update operator. While linear ave

Data Scaling Laws in Imitation Learning for Robotic Manipulation

arXiv:2410.18647v4 Announce Type: replace Abstract: Data scaling has revolutionized fields like natural language processing and computer vision, providing models with remarkable generalization capabil

Democratic ICAI: Debating Our Way to Steering Principles from Preferences

arXiv:2606.28294v1 Announce Type: new Abstract: Preference-based alignment often struggles to capture the reasoning that underlies human judgments. Many evaluations rely on multiple interacting criter

Deployment-Side Adaptiveness in Multi-Horizon Volatility Forecasting

arXiv:2606.27688v1 Announce Type: cross Abstract: In financial forecasting, predictive performance depends not only on which model is trained, but also on how the trained model is deployed. We study t

DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

arXiv:2606.28323v1 Announce Type: cross Abstract: Dexterous manipulation policies can solve individual skills, but composing them to perform multiple tasks with a single hand remains challenging. Addi

Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control

arXiv:2606.27964v1 Announce Type: new Abstract: Building interactive world models requires generating realistic videos while maintaining controllable dynamics over long horizons. Autoregressive video

Drifting in the Future: Stabilizing Path Following Drifting on High-Latency Vehicle Systems

arXiv:2606.27914v1 Announce Type: new Abstract: Autonomously controlling and handling a vehicle at and beyond its stability limit is a mathematically and computationally demanding task. Prior demonstr

Dual-Learning based Penalized Multi-Align Clustering for Multi-View Incomplete and Disorderly Data

arXiv:2606.27984v1 Announce Type: new Abstract: Multimodal feature fusion can effectively capture complex patterns in real-world data by integrating complementary information from different modalities

DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners Insights from Online Forums

arXiv:2606.27619v1 Announce Type: new Abstract: Dyslexic learners increasingly use artificial intelligence (AI) tools to support reading, writing, organisation, and study-related tasks. However, their

EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography

arXiv:2606.28164v1 Announce Type: new Abstract: Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis. Interpreti

Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching

arXiv:2606.28226v1 Announce Type: cross Abstract: Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inferen

Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off

arXiv:2606.28097v1 Announce Type: new Abstract: Post-hoc controllability of fair machine learning models, the ability to control the trade-off between fairness and accuracy after training, is valuable

GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion

arXiv:2606.27659v1 Announce Type: new Abstract: We present GeoFace, a geometry-constrained multi-view diffusion framework for consistent face generation from a single input. % While recent multi-view

Graph Unfolding and Sampling for Transitory Video Keyframe Selection via Gershgorin Disc Alignment

arXiv:2408.01859v2 Announce Type: replace Abstract: User-generated videos (UGVs) uploaded from mobile phones to social media sites like YouTube and TikTok are short and non-repetitive. We summarize a

Halt Fast! Early Stopping for Certified Robustness

arXiv:2606.27694v1 Announce Type: cross Abstract: Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited b

hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freeways

arXiv:2606.27577v1 Announce Type: cross Abstract: This paper formulates frame-level freeway risk assessment as a multi-agent scene graph-level binary classification problem, where each video or trajec

Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs

arXiv:2606.28122v1 Announce Type: cross Abstract: Neural operators provide deep neural networks for learning mappings between function spaces. Among them, the Fourier Neural Operator (FNO) is particul

HunyuanImage 3.0 Technical Report

arXiv:2509.23951v3 Announce Type: replace Abstract: We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with

Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning

arXiv:2606.27483v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-hor

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs

arXiv:2601.21233v2 Announce Type: replace Abstract: Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-d

Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition

arXiv:2606.27536v1 Announce Type: cross Abstract: Speech emotion recognition (SER) often relies on hard consensus labels that collapse annotator disagreement. We study distribution-based supervision f

Learning to Refine Hidden States for Reliable LLM Reasoning

arXiv:2606.17524v2 Announce Type: replace Abstract: Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where

Learning to Throw: Agile and Accurate Cable-Suspended Payload Delivery with a Quadrotor

arXiv:2606.27603v1 Announce Type: new Abstract: Quadrotors offer the agility needed to rapidly transport suspended payloads during time-critical applications, including search-and-rescue and medical d

Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation

arXiv:2511.14271v2 Announce Type: replace Abstract: Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still

Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning

arXiv:2606.27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We invest

MacKenzie Scott has donated over 26 billion to nonprofits. Around 1 billion of that ($786M confirmed but many donation amounts aren't disc…

MacKenzie Scott has donated over 26 billion to nonprofits. Around 1 billion of that (786M confirmed but many donation amounts aren't disclosed) has funded 226 organizations focused either fully or par

safetyelon-musk--x

Marc Andreessen is appointed to the DOD's Defense Policy Board, a committee tasked with giving strategic advice to the defense secretary and other top officials (Nick Wadhams/Bloomberg)

Nick Wadhams / Bloomberg: Marc Andreessen is appointed to the DOD's Defense Policy Board, a committee tasked with giving strategic advice to the defense secretary and other top officials — Billionaire

safetytechmeme

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

arXiv:2510.10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling

arXiv:2606.27705v1 Announce Type: new Abstract: Large Language Models (LLMs) still struggle with the ``lost-in-the-middle'' problem, where critical information located in the middle of long-context in

safetyarxiv-cs-cl

ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-On

arXiv:2606.27773v1 Announce Type: new Abstract: Image-based virtual try-on has emerged as a compelling task in e-commerce and augmented reality, yet existing methods struggle to simultaneously preserv

MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction

arXiv:2603.03710v3 Announce Type: replace-cross Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-pos

On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models

arXiv:2606.27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken. We prove this is not a c

OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators

arXiv:2606.28065v1 Announce Type: cross Abstract: Understanding model predictions is essential for physical applications, where outputs often inform safety-critical decisions, such as structural load

OverFlowLight: Real-Time Gridlock Prevention and Traffic Signal Optimization for Urban Intersections

arXiv:2606.27381v1 Announce Type: cross Abstract: Queue overflow, a severe consequence of urban traffic congestion, occurs when vehicle queues exceed intersection capacity, obstructing upstream traffi

PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction

arXiv:2606.27752v1 Announce Type: new Abstract: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. While recent gen

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

arXiv:2606.28128v1 Announce Type: cross Abstract: Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-sp

Position: The Term 'Machine Unlearning' Is Overused in LLMs

arXiv:2606.27379v1 Announce Type: cross Abstract: Large language models increasingly face demands to 'forget' training data, knowledge, or behaviors due to regulatory deletion obligations, copyright/l