Search: “safety”

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

arXiv:2508.04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being

Fair-GPTQ: Bias-Aware Quantization for Large Language Models

DGX agent

arXiv:2509.15206v3 Announce Type: replace Abstract: The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to l

safetyarxiv-cs-cl

7 Jul 2026

Few-Shot Demonstration-Driven Task Coordination and Trajectory Execution for Multi-Robot Systems

arXiv:2510.15686v2 Announce Type: replace Abstract: Learning coordinated behaviors for multi-robot systems from only a few demonstrations is difficult because temporal task dependencies and spatial tr

Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Decision-Making

arXiv:2607.04019v1 Announce Type: cross Abstract: Physical sensing and actuation noise floors should inform how much belief resolution a decision-making system can reliably use. We introduce Finite Re

Finite-Sample Closed-Loop Stability of Model Predictive Path Integral Control for Linear Time-Invariant Systems

arXiv:2607.04006v1 Announce Type: cross Abstract: We establish finite-sample closed-loop stability guarantees for Model Predictive Path Integral (MPPI) control applied to discrete-time Linear Time-Inv

Fitted Occupancy-Ratio Evaluation without Bellman Completeness

arXiv:2607.05375v1 Announce Type: cross Abstract: Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation. Existing primal-dual and minim

Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

arXiv:2607.03509v1 Announce Type: new Abstract: Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inferen

FM-ChangeNet: Learning Change through Pathwise Feature Transport

arXiv:2607.04750v1 Announce Type: new Abstract: We present FM-ChangeNet, a pathwise-supervised framework for change detection that reformulates bi-temporal reasoning as continuous transport in feature

FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion

arXiv:2607.04125v1 Announce Type: new Abstract: Small object detection in Unmanned Aerial Vehicle (UAV) imagery remains challenging under adverse conditions, including complex weather, low illuminatio

From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

arXiv:2607.05396v1 Announce Type: cross Abstract: Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on

From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation

arXiv:2607.04691v1 Announce Type: new Abstract: While controllable image generation has made significant strides by incorporating visual reference conditions, existing methods predominantly operate as

From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation

arXiv:2607.03792v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding

Full clip of my presentation of the Independent International Scientific Panel’s preliminary report at the opening ceremony yesterday: https…

Full clip of my presentation of the Independent International Scientific Panel’s preliminary report at the opening ceremony yesterday: https://webtv.un.org/en/asset/k1y/k1yd3dlebq?kalturaSeekFrom=3260

safetyyoshua-bengio--x

Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention

arXiv:2607.04422v1 Announce Type: cross Abstract: Recent NVFP4 pretraining methods mainly target transformer linear layers, leaving optimizer states, optimizer arithmetic and attention underexplored i

G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement

arXiv:2607.04607v1 Announce Type: cross Abstract: The rapid advancement of AI-generated videos poses increasing security risks and calls for robust detectors with strong cross-domain generalization. A

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks

arXiv:2607.05369v1 Announce Type: cross Abstract: For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot progr

Generative Pseudo-Labeling for Pre-Ranking with LLMs

arXiv:2602.20995v2 Announce Type: replace-cross Abstract: Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstre

Governing Generative AI Across Financial Institutions: An SR 26-2-Compatible Framework for Generative AI Risk Control

arXiv:2607.04103v1 Announce Type: cross Abstract: The release of SR 26-2 marks a significant modernization of U.S. model risk management by replacing SR 11-7 with a more risk-based and materiality-sen

Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

arXiv:2602.18037v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Model

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

arXiv:2607.02592v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. How

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

arXiv:2607.04265v1 Announce Type: cross Abstract: World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration,

HeartVolMesh: Cardiac Volumetric Mesh Reconstruction via Covariance-Guided Graph Deformation

arXiv:2607.04243v1 Announce Type: new Abstract: Accurate patient-specific tetrahedral cardiac meshes are essential for in-silico trials, yet common segmentation-then-modelling pipelines can blur thin-

High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching

arXiv:2607.03865v1 Announce Type: cross Abstract: Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions, but their

High-Precision Formation Control for Heterogeneous Multi-Robot Systems via Hierarchical Hybrid Physics-Informed Deep Reinforcement Learning

arXiv:2607.03512v1 Announce Type: new Abstract: Existing classical control methods commonly require precise models and struggle to cope with model uncertainties and external disturbances, while end-to

Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation

arXiv:2510.08807v3 Announce Type: replace-cross Abstract: From loco-motion to dextrous manipulation, humanoid robots have made remarkable strides in demonstrating complex full-body capabilities. Howev

Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

arXiv:2606.12471v2 Announce Type: replace-cross Abstract: Klindt, LeCun, and Balestriero (arXiv:2605.26379) proved that Joint-Embedding Predictive Architectures (JEPAs) achieve linear identifiability,

Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse

arXiv:2607.03613v1 Announce Type: new Abstract: We study the implicit bias of noisy stochastic gradient descent in training wide two-layer ReLU networks for multivariate regression. In a mean-field re

Improving LLMs via Validator-to-Generator Alignment

arXiv:2607.02668v1 Announce Type: new Abstract: Large language models are inconsistent: varying prompts or including unrelated information can lead to unexpected changes in model outputs. The generato

Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas

arXiv:2607.04710v1 Announce Type: new Abstract: Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in so

InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

arXiv:2607.04988v1 Announce Type: new Abstract: Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through

Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding

arXiv:2606.13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress. A natural way to bring this to spatial ground

KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment

arXiv:2607.03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads

KVpop -- Key-Value Cache Compression with Predictive Online Pruning

arXiv:2607.05061v1 Announce Type: new Abstract: Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV ev

Lacuna Inc. at SemEval-2026 Task 4: Structurally Gated State-Space Models for Disentangling Narrative Similarity

arXiv:2607.03482v1 Announce Type: new Abstract: In this paper, we present the Invariant-Variant Disentangled State-Space Model (IVD-SSM), our submission to SemEval-2026 Task 4 on Narrative Story Simil

Large Language Models Develop Novel Social Biases Through Adaptive Exploration

arXiv:2511.06148v4 Announce Type: replace-cross Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important

Latent Visual Cache for Video Reasoning

arXiv:2607.02607v1 Announce Type: cross Abstract: Video reasoning requires Large Multimodal Models (LMMs) to remain grounded in dense evidence, yet existing systems largely adopt 'read-once, generate-

LBR: Towards Mitigating Length Bias in Large Language Models for Recommendation

arXiv:2607.04270v1 Announce Type: cross Abstract: Large language models (LLMs) have recently emerged as powerful backbones for recommender systems by reformulating recommendation as a token-level gene

Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension

arXiv:2607.04638v1 Announce Type: new Abstract: Referring expression comprehension (REC) aims to localize the object in an image described by natural language. In Weakly supervised REC (WREC), existin

LivingWorld: Interactive 4D World Generation with Environmental Dynamics

arXiv:2604.01641v2 Announce Type: replace Abstract: We introduce LivingWorld, an interactive framework for generating 4D worlds with environmental dynamics from a single image. While recent advances i

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

arXiv:2607.04412v1 Announce Type: new Abstract: Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. W

LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2

arXiv:2508.16181v2 Announce Type: replace-cross Abstract: Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across inde

LLM-based Human Simulations Have Not Yet Been Reliable

arXiv:2501.08579v3 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current

MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning

arXiv:2607.02990v1 Announce Type: new Abstract: We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning nod

MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement

arXiv:2607.02568v1 Announce Type: new Abstract: View-based point cloud completion aims to recover a complete 3D shape from a partial point cloud, guided by a single-view image. However, existing appro

MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation

arXiv:2603.25126v2 Announce Type: replace-cross Abstract: Multi-Behavior Recommendation (MBR) leverages multiple user interaction types (e.g., views, clicks, purchases) to enrich preference modeling a

MeGA-MP: Metric Graph Advection Message Passing -- A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphs

arXiv:2607.05167v1 Announce Type: new Abstract: Many real-world systems are organized as networks where spatio-temporal dynamics unfold along connections and not discretely between nodes. Examples inc

MentalThink: Shaping Thoughts in Mental SVG World

arXiv:2607.03530v1 Announce Type: new Abstract: We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for 'mental' visualizati

Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models

arXiv:2409.16663v5 Announce Type: replace-cross Abstract: We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a ne