Search: “safety”

arXiv:2605.26690v1 Announce Type: cross Abstract: Protein sequence optimization under tight oracle budgets requires methods that explore vast combinatorial spaces while making each evaluation informat

arXiv:2605.26973v1 Announce Type: cross Abstract: Neural networks are known to develop latent representations that are aligned, namely structurally similar across networks trained with different archi

arXiv:2512.14140v2 Announce Type: replace Abstract: Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for

arXiv:2605.26704v1 Announce Type: cross Abstract: Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread, creating feedback loops that induce distrib

some data i shared yesterday on anthropic revenue possibly slowing down aren’t as a compelling as i thought; i have deleted my posts and await better data before drawing conclusions. h/t @GergelyOrosz

arXiv:2506.08543v3 Announce Type: replace Abstract: High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circu

arXiv:2605.26606v1 Announce Type: cross Abstract: Reinforcement learning (RL) is the dominant paradigm for post-training large language models. However, in the online, on-policy setting, rollout gener

arXiv:2605.27027v1 Announce Type: new Abstract: The scaling of quantum processors is currently limited by technical challenges such as decoherence and cross-talk. As the number of qubits grows, interf

Starbucks learned the hard way: you literally can’t even trust (current) AI to count. For some reason OpenAI doesn’t seem to be talking about how Starbucks spent years creating and testing an AI inven

arXiv:2605.27140v1 Announce Type: new Abstract: Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hin

arXiv:2601.05729v2 Announce Type: replace Abstract: Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for t

arXiv:2605.27220v1 Announce Type: new Abstract: In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference

arXiv:2605.26670v1 Announce Type: cross Abstract: Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rel

arXiv:2605.26415v1 Announce Type: cross Abstract: Deploying Vision-Language Models on resource-constrained hardware typically requires INT8 quantization, but in joint-embedding architectures such as C

arXiv:2605.27163v1 Announce Type: new Abstract: In strategic classification, an institution (e.g., a bank) anticipates adaptation from users who change their features to increase utility in a classifi

This is fearmongering, @davidsacks, afaik. I see no candidate regulation being taken seriously that is an actual threat to the trillion dollar AI companies (which can easily afford whatever compliance

arXiv:2510.05141v2 Announce Type: replace Abstract: When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs

“Tokens got burned for millions of dollars without any real significant ROI to show for it.” hearing this over and over again The same conversation is happening across tech right now and many of us sa

arXiv:2605.26470v1 Announce Type: new Abstract: Generative posterior sampling using diffusion models has emerged as a dominant paradigm for solving inverse problems in imaging, which usually consists

arXiv:2605.26156v1 Announce Type: cross Abstract: The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulner

arXiv:2601.22648v2 Announce Type: replace Abstract: The key to building trustworthy large language models (LLMs) lies in endowing them with inherent uncertainty expression capabilities, thereby mitiga

arXiv:2605.26424v1 Announce Type: cross Abstract: With the rapid evolution of internet services, recommendation systems have become indispensable. In particular, the blending (re-ranking) stage plays

arXiv:2512.04085v2 Announce Type: replace Abstract: We introduce the 'single-life' learning paradigm, where we train a distinct vision model exclusively on egocentric videos captured by one individual

arXiv:2504.07853v2 Announce Type: replace Abstract: Light field microscopy (LFM) has gained significant attention due to its ability to capture snapshot-based, large-scale 3D fluorescence images. Howe

arXiv:2510.17759v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplor

arXiv:2605.27114v1 Announce Type: new Abstract: Learning from demonstrations is effective for robotic manipulation, but collecting sufficient task-specific data remains a major bottleneck. Under distr

we will have the most science and math submissions ever in the next few years. but most ≠ best. to get to best, quality will have to beat slop Terence Tao: AI is creating a “traffic jam” in math If AI

arXiv:2605.26379v1 Announce Type: cross Abstract: A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove th

arXiv:2605.27348v1 Announce Type: cross Abstract: Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularl

arXiv:2605.26530v1 Announce Type: new Abstract: Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations

You reap what you sow. OpenAI’s public image is becoming a bigger liability as political backlash against AI grows. The company has spoken with several communications executives but has yet to fill th

arXiv:2605.24868v1 Announce Type: new Abstract: Temporal surrogate models are effective for predicting chaotic dynamical systems where computational cost can be prohibitive. Several deep neural networ

arXiv:2605.25051v1 Announce Type: new Abstract: Decentralized multi-robot LiDAR-SLAM is essential for collaborative missions but faces significant challenges in maintaining global consistency. Existin

arXiv:2605.24383v1 Announce Type: new Abstract: Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to

arXiv:2605.26026v1 Announce Type: cross Abstract: Light sheet fluorescence microscopy (LSM) enables high-resolution, three-dimensional (3D) imaging of biological specimens, providing rich volumetric d

arXiv:2605.25540v1 Announce Type: cross Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative disorder and the leading cause of dementia, affecting memory, reasoning, communication, an

A post about Pope Leo XIV's encyclical on AI. Why the Pope is right, but perhaps not right enough. Artificial intelligence is reshaping the world in front of our eyes: how we communicate, how we acces

KYA is a framework-agnostic trust layer designed for autonomous systems that provides verifiable guarantees, addressing the need for trustworthy and transparent operation of AI agents across different

arXiv:2605.24197v1 Announce Type: new Abstract: We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Alt

arXiv:2605.25536v1 Announce Type: cross Abstract: Context. Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering. While reported results are pro

arXiv:2605.24406v1 Announce Type: new Abstract: Optimizing HVAC (Heating, Ventilation and Air Conditioning) can enhance a building's energy efficiency while providing comfort levels for its occupants.

arXiv:2605.24803v1 Announce Type: new Abstract: A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by st

arXiv:2605.24343v1 Announce Type: new Abstract: Human-AI collaboration requires agents that can adapt to diverse partner behaviors and skill levels while remaining robust to unseen partners. Existing

arXiv:2509.10515v1 Announce Type: cross Abstract: Offline preference optimization methods are efficient for large language models (LLMs) alignment. Direct Preference optimization (DPO)-like learning,

arXiv:2605.26013v1 Announce Type: cross Abstract: We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the revers

arXiv:2605.24843v1 Announce Type: cross Abstract: Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However,