Search: “safety”

sGPO: Trading Inference FLOPs for Training Efficiency in RLVR

arXiv:2606.08854v1 Announce Type: cross Abstract: Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each

SMI: Efficient Self-Supervised Learning via Mutual-Information-Inspired Dependency Optimization

DGX agent

arXiv:2606.08332v1 Announce Type: new Abstract: Self-supervised learning (SSL) has achieved remarkable representation learning performance, but many existing methods rely on large batch sizes, memory

safetyarxiv-cs-cv

9 Jun 2026

'So There's a Catch-22 Here': How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency

arXiv:2606.08323v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) systems are rapidly emerging, yet transparency, a cornerstone of responsible AI, remains under-defined in these

some news: it turns out 34,000 Instagram accounts got hit by a Meta AI exploit the other day, per internal company docs hackers also used a …

some news: it turns out 34,000 Instagram accounts got hit by a Meta AI exploit the other day, per internal company docs hackers also used a senior 'Space Force' official's account to post anti-Iran wa

SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning

arXiv:2606.08992v1 Announce Type: cross Abstract: Vision-and-Language Navigation in continuous environments requires agents to understand the spatial structure of previously unseen environments in ord

Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models

arXiv:2606.08446v1 Announce Type: cross Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive. Since R

Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

arXiv:2606.08678v1 Announce Type: cross Abstract: Sophisticated generative speech technology can undermined the reliability of voice biometrics. While spoofing detection systems excel when assessed un

SPIN: Decentralized Swarm Control via Tensorized Policy Coordination

arXiv:2606.07557v1 Announce Type: new Abstract: Decentralized multi-agent swarm coordination on resource-constrained edge platforms remains fundamentally bottlenecked by the exponential scaling of joi

Stage-1 Controls the Entropy Regime, Not the Outcome

arXiv:2606.09059v1 Announce Type: cross Abstract: Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learni

STARIXNet: Multivariate and Multi-attribute Deep Learning Approach to Real-Time Resource Allocation in Cloud Platforms

arXiv:2606.07565v1 Announce Type: new Abstract: Intelligent scaling of microservices in cloud platforms is crucial for mitigating escalating compute costs while avoiding service disruptions. Current s

Steganography Without Modification: Hidden Communication via LLM Seeds

arXiv:2606.09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model

STELLAR: Spatio-Temporal Environmental Learning with Latent Alignment and Refinement for Long-Tailed Species Distribution Modeling

arXiv:2606.08484v1 Announce Type: cross Abstract: Joint Species Distribution Modeling (JSDM) is a key enabler for biodiversity monitoring and conservation planning. However, accurate JSDM faces two co

Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning

arXiv:2606.08735v1 Announce Type: new Abstract: Quality-diversity reinforcement learning (QD-RL) aims to construct policy repertoires that contain both high-performing and behaviorally diverse policie

Summarization is Not Dead Yet

arXiv:2606.08000v1 Announce Type: cross Abstract: The progress of large language models (LLMs) has fueled claims that model-generated summaries rival or even surpass human-written references, raising

Symbolic Reasoning Frameworks Modulate LLM Risk Aversion in Multi-Agent Strategic Settings

arXiv:2606.07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse 'turtle' bias toward defensive p

SynthICL: Scalable In-context Imitation Learning with Synthetic Data

arXiv:2606.08154v1 Announce Type: new Abstract: In-context imitation learning (ICIL) enables robots to learn new tasks from a small number of demonstrations by conditioning a pre-trained policy on tas

Systems-Level Planning and Coordination of Truck-Drone Collaborative Delivery Networks

arXiv:2606.08738v1 Announce Type: cross Abstract: Urban last-mile parcel delivery increasingly relies on heterogeneous fleets whose performance depends on timely coordination, reliable communication,

Targeting World Models to Compromise Robot Learning Pipelines

arXiv:2606.09499v1 Announce Type: cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data

Testing the Black Box: Structural Barriers to Independent Evaluation of Consumer-Facing Health LLMs

arXiv:2606.08483v1 Announce Type: new Abstract: Background: Consumer-facing large language models are now a common source of health information, and they interpret and personalize responses rather tha

The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust

arXiv:2606.07822v1 Announce Type: cross Abstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good prox

The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders

arXiv:2606.07882v1 Announce Type: cross Abstract: Different vision neural networks -- trained to classify, contrast, reconstruct, or match images to text -- should have correspondingly different inter

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

arXiv:2606.07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions al

The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

arXiv:2601.15165v4 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary o

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

arXiv:2606.09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback. However, we identify a hidden bias in PRMs caused

The Spectral Dynamics and Noise Geometry of Muon

arXiv:2606.08388v1 Announce Type: new Abstract: Muon replaces a matrix gradient G=USigma V^op by its polar factor UV^op. This keeps the singular directions selected by the gradient, but makes the upda

Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction

arXiv:2606.08122v1 Announce Type: new Abstract: Predicting a user's next Point-of-Interest (POI) based on their historical check-in records is a fundamental task in location-based services. While rece

This is actually a pretty measured bet compared to spending of the U.S companies. OpenAI alone is about twice as much. If things falls apart…

This is actually a pretty measured bet compared to spending of the U.S companies. OpenAI alone is about twice as much. If things falls apart, the US will be hit harder. 🚨BREAKING: CHINA IS AGI-PILLED

This quote from OpenAI is telling. Translation: We have a rapidly closing window to get this IPO out the door before the bubble bursts, our …

This quote from OpenAI is telling. Translation: We have a rapidly closing window to get this IPO out the door before the bubble bursts, our CFO doesn't want to go through with it because our books are

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles

arXiv:2606.07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.g., output

TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation

arXiv:2606.09337v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become a powerful framework for robotic manipulation, and recent studies have introduced tactile or force feedb

Towards Accurate Emotion-Attributed Video Captioning via Fine-grained Emotion-Cause Pair Extraction

arXiv:2606.08566v1 Announce Type: new Abstract: Emotional Video Captioning (EVC) is a challenging task that aims to generate factually accurate and emotionally rich descriptions for videos. Existing E

Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning

arXiv:2606.08513v1 Announce Type: cross Abstract: Autonomous Underwater Vehicles (AUVs) traditionally rely on complex, heavily engineered pipelines for perception, path planning, and motion control. T

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

arXiv:2511.05017v2 Announce Type: replace Abstract: Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual informati

Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment

arXiv:2606.07581v1 Announce Type: cross Abstract: A modern post-training pipeline often writes one symbol for its policy, pi_theta, while evaluating it through two different programs: a training kerne

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning

arXiv:2606.07631v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task. Standard training signals c

TRUST-SCF: Transformer-based Risk Understanding and Scoring for Transactional Supply Chain Finance

arXiv:2606.08140v1 Announce Type: new Abstract: Supply Chain Finance (SCF) and LendTech platforms need credit scoring systems that respond to evolving transaction behavior, repayment delays, and activ

Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data

arXiv:2606.08520v1 Announce Type: new Abstract: Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies (VLAs) is surprisingly difficult.

Uncertainty-Aware Hierarchical Re-Localization in OpenStreetMap via Semantic Alignment

arXiv:2603.01613v2 Announce Type: replace Abstract: Monocular re-localization enables robots to estimate camera poses from visual observations. However, many existing methods rely on dense maps or lar

Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks

arXiv:2606.08775v1 Announce Type: cross Abstract: Visual world models have shown great potential in learning complex system dynamics. Recent advancements leverage these models as transition functions

VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands

arXiv:2606.09286v1 Announce Type: new Abstract: Humanoid robots hold immense potential for real-world assistance, yet agile interaction with objects in unstructured environments demands tightly couple

Video Understanding by Design: How Datasets Shape Video Models

arXiv:2509.09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures. While exi

Vision-Language Asymmetry in Bistable Image Captioning

arXiv:2606.08031v1 Announce Type: new Abstract: Wittgenstein's duck-rabbit poses a question for vision-language models: when a model captions an ambiguous image, where in the model is the commitment t

Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning

arXiv:2606.09290v1 Announce Type: new Abstract: Visual reasoning requires integrating evidence distributed across regions, attributes, and relations, making single-chain reasoning prone to early perce

wait til you see what happens with SpaceX.

Gary Marcus, a prominent AI researcher and critic, posted a teaser statement on X about upcoming SpaceX developments, likely referring to significant announcements or milestones in the company's space

WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis

arXiv:2606.08670v1 Announce Type: new Abstract: Large and demographically balanced datasets are essential for reliable neuroimaging biomarkers. Full-resolution 3D brain MRI synthesis can support data

Web Agents Should Use Typed Actions Instead of Click-Based Browsing

arXiv:2602.17245v2 Announce Type: replace Abstract: This position paper argues that building a reliable agentic Web requires shifting from low-level interaction primitives to typed actions supported b

what constitutes reasoning in AI is a critical debate. i hope that @dwarkesh_sp will respond.

what constitutes reasoning in AI is a critical debate. i hope that @dwarkesh_sp will respond. what does this even mean, @dwarkesh_sp, “the real deal”? is it even a falsifiable conjecture? what’s the e

what does this even mean, @dwarkesh_sp, “the real deal”? is it even a falsifiable conjecture? what’s the evidence? and if you can agree that…

what does this even mean, @dwarkesh_sp, “the real deal”? is it even a falsifiable conjecture? what’s the evidence? and if you can agree that “If you ask an LLM a question it can't answer, sometimes it