Search: “safety”

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

arXiv:2605.09430v1 Announce Type: new Abstract: Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies o

Safety

Force Policy: Learning Hybrid Force-Position Control Policy under Interaction Frame for Contact-Rich Manipulation

DGX agent

arXiv:2602.22088v2 Announce Type: replace Abstract: Contact-rich manipulation demands human-like integration of perception and force feedback: vision should guide task progress, while high-frequency i

safetyarxiv-cs-ro

12 May 2026

Formal Policy Enforcement for Real-World Agentic Systems

arXiv:2602.16708v3 Announce Type: replace-cross Abstract: Security policy enforcement in contemporary agentic systems predominantly consists of embedding natural-language policies within an agent's sy

FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing

arXiv:2605.09362v1 Announce Type: cross Abstract: We present FrameTwin, a curve-anchored Gaussian alignment framework that uses sparse-view images to close the control loop for adaptive wireframe 3D p

Frequency Adapter with SAM for Generalized Medical Image Segmentation

arXiv:2605.09925v1 Announce Type: new Abstract: Medical image segmentation is a critical task in computer-aided diagnosis and treatment planning. However, deep learning models often struggle to genera

Frictional Q-Learning

arXiv:2509.19771v5 Announce Type: replace-cross Abstract: Off-policy reinforcement learning suffers from extrapolation errors when a learned policy selects actions that are weakly supported in the rep

From Holo Pockets to Electron Density: GPT-style Drug Design with Density

arXiv:2605.08767v1 Announce Type: new Abstract: Recent advances in generative modeling have enabled significant progress in structure-based drug design (SBDD). Existing methods typically condition mol

From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay

arXiv:2605.09419v1 Announce Type: new Abstract: While experience replay is essential for data efficiency in reinforcement learning (RL), standard methods treat the replay buffer as a passive memory sy

Functional Graphs for Predicting and Explaining Goal Failure in Sparse Goal-Conditioned RL

arXiv:2605.09335v1 Announce Type: new Abstract: Sparse goal-conditioned reinforcement learning can produce policies whose failures are hidden by aggregate success rates. We analyze trained goal-condit

GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

arXiv:2605.10525v1 Announce Type: new Abstract: Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial bl

Gender Fairness in Audio Deepfake Detection: Performance and Disparity Analysis

arXiv:2603.09007v2 Announce Type: replace-cross Abstract: Audio deepfake detection aims to detect real human voices from those generated by Artificial Intelligence (AI) and has emerged as a significan

Generalized Category Discovery in Federated Graph Learning

arXiv:2605.08178v1 Announce Type: cross Abstract: Federated Graph Learning (FGL) enables collaborative learning over distributed graph data, yet existing approaches largely rely on a closed-world assu

Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction

arXiv:2511.17879v4 Announce Type: replace Abstract: Most applications of generative AI involve a sequential interaction in which a person inputs a prompt and waits for a response, and where reaction t

Good science starts with intellectual honesty, and I am not seeing it. I 100% believe the quote below and zero percent believe the seemingly…

Good science starts with intellectual honesty, and I am not seeing it. I 100% believe the quote below and zero percent believe the seemingly similar– but actually very different—quote that @geoffreyhi

safetygary-marcus--x

Governed Metaprogramming for Intelligent Systems: Reclassifying Eval as a Governed Effect

arXiv:2605.05248v2 Announce Type: replace-cross Abstract: AI systems increasingly synthesize executable structure at runtime: LLMs generate programs, agents construct workflows,self-improving systems

Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support

arXiv:2605.09534v1 Announce Type: cross Abstract: Engineering managers increasingly must decide how to introduce generative artificial intelligence (AI), retrieval-augmented generation, and coding age

Guided Streaming Stochastic Interpolant Policy

arXiv:2605.10051v1 Announce Type: cross Abstract: Inference-time guidance is essential for steering generative robot policies toward dynamic objectives without retraining, yet existing methods are lar

Happy One Year Anniversary, AGI!* What an amazing, hallucination-free year it has been!* Glad we can totally trust you now!* *I was being sa…

Happy One Year Anniversary, AGI!* What an amazing, hallucination-free year it has been!* Glad we can totally trust you now!* *I was being sarcastic. @codeslubber tyler cowen literally said o3 was AGI.

safetygary-marcus--x

HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation

arXiv:2605.09971v1 Announce Type: cross Abstract: Text-to-vibration generation converts natural language into haptic feedback, enabling vibration-effect designers to get scenarios-fitted vibrations mo

HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detection

arXiv:2602.09524v3 Announce Type: replace Abstract: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detec

How Much is Brain Data Worth for Machine Learning?

arXiv:2605.09243v1 Announce Type: new Abstract: If a person can solve a task, can measuring their brain make it easier to train a model to solve that task too? Recent NeuroAI work suggests that supple

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control

arXiv:2605.08283v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a pivotal technique for enhancing the reasoning capabilities of Large Language Mo

https://x.com/xiaochuan8688/status/2053007309459341699 'ByteDance has quietly shut down 30% of its AI projects' Even ByteDance faces the sam…

https://x.com/xiaochuan8688/status/2053007309459341699 'ByteDance has quietly shut down 30% of its AI projects' Even ByteDance faces the same fate as OpenAI's Sora. While the Chinese public enjoys 'AI

safetygary-marcus--x

HY-Himmel Technical Report: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding

arXiv:2605.08158v1 Announce Type: cross Abstract: Long-video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB frames, qua

HyNeuralMap: Hyperbolic Mapping of Visual Semantics to Neural Hierarchies

arXiv:2605.09392v1 Announce Type: new Abstract: Understanding the intricate mappings between visual stimuli and neural responses is a fundamental challenge in cognitive neuroscience. While current app

HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction

arXiv:2602.06527v2 Announce Type: replace Abstract: Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-

Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation

arXiv:2601.22904v2 Announce Type: replace-cross Abstract: Recent studies have explored using pretrained Vision Foundation Models (VFMs) such as DINO for generative autoencoders, showing strong generat

I sat down with @JonHernandezIA in Madrid to discuss the growing risks and impacts of AI and the urgent need to improve our social, politica…

I sat down with @JonHernandezIA in Madrid to discuss the growing risks and impacts of AI and the urgent need to improve our social, political, and technical safeguards. Thanks for an excellent convers

safetyyoshua-bengio--x

Improving Human Image Animation via Semantic Representation Alignment

arXiv:2605.10523v1 Announce Type: new Abstract: The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, espe

Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling

arXiv:2605.08950v1 Announce Type: cross Abstract: Lexical difficulty prediction is a fundamental problem in language learning and readability assessment, requiring models to estimate word difficulty a

Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards

arXiv:2603.00918v3 Announce Type: replace-cross Abstract: Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models

Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization

arXiv:2605.08131v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) learns a reward function and a corresponding policy that best fit the demonstration data of an expert. However, in

Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations

arXiv:2605.09090v1 Announce Type: cross Abstract: Visual Grounding benchmarks assume that the object described by a referring expression is always present in the image, and grounding models are theref

Is Class Signal Clustered or Routed in Task-Induced Implicit Neural Representation Weight Spaces?

arXiv:2605.08281v1 Announce Type: new Abstract: Implicit neural representations (INRs) encode images as neural-network weights, making image classification a problem of weight-space classifiability. A

Ister: Linear Transformer for Efficient Multivariate Time Series Forecasting

arXiv:2412.18798v3 Announce Type: replace-cross Abstract: Transformer-based models have achieved remarkable success in multivariate time series forecasting (MTSF) by capturing long-range dependencies.

Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs

arXiv:2605.08686v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typ

KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes

arXiv:2512.11321v3 Announce Type: replace Abstract: Facial animation is a core component for creating digital characters in Computer Graphics (CG) industry. A typical production workflow relies on spa

Language Conditioned Multi-Finger Dexterous Manipulation Enabled by Physical Compliance and Switching of Controllers

arXiv:2410.14022v2 Announce Type: replace-cross Abstract: Human dexterity arises from combining high-level task reasoning with finger-level dexterity control and physical compliance at the muscle and

LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss

arXiv:2605.08755v1 Announce Type: new Abstract: Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primar

Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning

arXiv:2605.09009v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of ex

LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations

arXiv:2605.08279v1 Announce Type: cross Abstract: Learning predictive world models from visual observations is a core problem in embodied AI, with applications to model-based reinforcement learning an

Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling

arXiv:2603.03759v2 Announce Type: replace-cross Abstract: Many large-scale platforms and networked control systems have a centralized decision maker interacting with a massive population of agents und

Learning the Preferences of a Learning Agent

arXiv:2605.09217v1 Announce Type: new Abstract: For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a har

Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval

arXiv:2605.09859v1 Announce Type: new Abstract: Fine-grained image retrieval (FGIR) typically relies on supervision from seen categories to learn discriminative embeddings for retrieving unseen catego

Learning to Compress Time-to-Control: A Reinforcement Learning Framework for Chronic Disease Management

arXiv:2605.09818v1 Announce Type: new Abstract: Reinforcement learning (RL) in healthcare has had mixed results, with reward sparsity, unreliable off-policy evaluation, and deployment-simulation gap a

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

arXiv:2605.08978v1 Announce Type: new Abstract: Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of e

Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift

arXiv:2605.09183v1 Announce Type: new Abstract: Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment