Search: “safety”

arXiv:2509.08318v2 Announce Type: replace Abstract: Early-exit cascades over a frozen convolutional backbone enable adaptive inference but suffer from three sources of train-inference mismatch: branch

arXiv:2601.21699v2 Announce Type: replace Abstract: Multi-turn reasoning agents solve complex questions by decomposing them into intermediate retrieval or tool-use steps, for accumulating supporting e

arXiv:2605.07065v1 Announce Type: cross Abstract: Individual treatment effects are not point-identified from data. The Probability of Necessity and Sufficiency (PNS) circumvents this limitation by cha

Checkmate to everyone on X who doubted my coverage of Sam’s firing. Checkmate. 🚨BREAKING: Ilya just confirmed under oath what he saw: Sam lying. And he confirmed that he thought it was appropriate to

arXiv:2605.07040v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used for tutoring, feedback generation, and content creation, but their broad pretraining makes them hard to c

Compute is scarce and has to be bought years in advance, before companies know whether revenue will ever catch up. That is exactly the nature of the largest gamble in history. Heaven help the global e

arXiv:2605.06720v1 Announce Type: cross Abstract: Antibody therapeutics are among the most successful modern medicines, yet computationally designing antibodies with desirable binding and developabili

arXiv:2605.07353v1 Announce Type: new Abstract: Large reasoning models often reach correct answers through flawed intermediate steps, creating a gap between final accuracy and reasoning reliability. E

arXiv:2605.07115v1 Announce Type: new Abstract: Stochastic bandit algorithms are usually analyzed under a mean-reward criterion, yet many problems favor arms with strong upper-tail performance, which

arXiv:2603.05687v3 Announce Type: replace Abstract: Contact-rich dexterous manipulation with multi-finger hands remains an open challenge in robotics because task success depends on multi-point contac

arXiv:2605.07171v1 Announce Type: new Abstract: The classic multi-armed bandit (MAB) problem tackles the challenge of accruing maximum reward while making decisions under uncertainty. However, in appl

arXiv:2605.07724v1 Announce Type: cross Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal

arXiv:2605.07314v1 Announce Type: cross Abstract: Knowledge Graphs (KGs) have proven highly effective for recommendation systems by capturing latent item relationships, while recent integration of Lar

Dear @geoffreyhinton, I literally never said that AI systems “JUST regurgitate”; that’s plainly false. I don’t believe it, and I didn’t say it. (They do *sometimes* regurgitate, and the evidence for t

arXiv:2605.06971v1 Announce Type: cross Abstract: Classical optimization theory largely focuses on fixed objective functions, whereas many modern learning systems operate in dynamic environments where

arXiv:2605.07074v1 Announce Type: new Abstract: Detecting AI-generated images across unseen architectures remains challenging, as existing models often overfit to generator-specific fingerprints and s

arXiv:2512.17129v2 Announce Type: replace Abstract: Biological systems can form complex three-dimensional structures through the collective behavior of agents that share a common update rule and opera

arXiv:2605.07674v1 Announce Type: cross Abstract: Regulatory audits of AI systems increasingly rely on differential privacy (DP) to protect training data and model internals. We study audit design whe

arXiv:2605.07503v1 Announce Type: new Abstract: Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent dis

arXiv:2602.22831v2 Announce Type: replace-cross Abstract: Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this

arXiv:2602.16928v3 Announce Type: replace-cross Abstract: Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual,

arXiv:2605.07483v1 Announce Type: cross Abstract: Successful deep neural networks discover salient features of data. We show when and why they fail to learn out-of-distribution (OOD)-relevant represen

arXiv:2605.06885v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have recently demonstrated capabilities that complement standard autoregressive (AR) models, particularly in non-sequ

arXiv:2605.07041v1 Announce Type: cross Abstract: This paper introduces Dr-BA, a first-of-its-kind radar bundle adjustment (BA) framework that operates directly on 2D spinning radar intensity images.

arXiv:2605.07063v1 Announce Type: cross Abstract: Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant

arXiv:2510.00253v2 Announce Type: replace Abstract: Smoothness is a key inductive bias in machine learning and is closely related to generalization. Existing smoothness-inducing methods typically rely

arXiv:2605.07727v1 Announce Type: cross Abstract: We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a rev

arXiv:2512.09682v2 Announce Type: replace-cross Abstract: This work studies the application of Multi-Agent Reinforcement Learning (MARL) to decentralized control of unmanned aerial vehicles to relay a

arXiv:2603.00041v2 Announce Type: replace-cross Abstract: Causal machine learning (ML) recovers graphical structures that inform us about potential cause-and-effect relationships. Most progress has fo

arXiv:2605.07455v1 Announce Type: new Abstract: Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than

arXiv:2605.05674v2 Announce Type: replace-cross Abstract: Vector search systems built on frozen vision encoders face queries from unseen classes at deployment, yet existing adapter training collapses

arXiv:2604.05777v2 Announce Type: replace Abstract: How do people acquire rich, flexible knowledge about their environment from others despite limited cognitive capacity? Humans are often thought to r

arXiv:2605.07407v1 Announce Type: new Abstract: Health foundation models (FMs) learn useful representations from wearable sensors, but interpreting what they encode and transferring that knowledge acr

arXiv:2605.06156v2 Announce Type: replace-cross Abstract: Integrating expressive generative policies, such as flow-matching models, into offline reinforcement learning (RL) allows agents to capture co

Epistemological standards in SF venture capital are so low that you can write this, and everyone will simply nod along. The actual evidence, including a recent NBER paper on thousands of firms, finds:

arXiv:2605.07381v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models offer broad general capabilities, deploying them on specific hardware requires real-world adaptation to brid

arXiv:2510.16079v2 Announce Type: replace-cross Abstract: Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from th

Ex-OpenAI co-founder Ilya Sutskever claims to have collected proof of Sam Altman’s alleged dishonesty https://www.theglobeandmail.com/business/article-openai-trial-sutskever-sam-altman-musk/?utm_sourc

Excellent explainer video by @FryRsquared on the risks of AI agents. She also raises a crucial point: we shouldn’t make the mistake of thinking current limitations will necessarily persist. As we’ve s

arXiv:2605.07244v1 Announce Type: cross Abstract: We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience

arXiv:2605.06977v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing appr

arXiv:2605.07914v1 Announce Type: cross Abstract: Sharpness-aware and gradient-alignment methods have been shown to improve generalization, however each family of methods targets a single geometric pr

arXiv:2602.09782v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the reasoning capabilities of Large Langu

arXiv:2605.08063v1 Announce Type: cross Abstract: Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scala

arXiv:2605.07268v1 Announce Type: new Abstract: Multiple-choice reasoning benchmarks face dual challenges: rapid saturation from advancing models and data contamination that undermines static evaluati

arXiv:2605.06814v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) achieve high performance but can be opaque to humans, making it difficult to understand and compare the many proposed archi