Automated alignment is harder than you think
arXiv:2605.06390v2 Announce Type: replace Abstract: A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as c
Knowledge catalogue
arXiv:2605.06390v2 Announce Type: replace Abstract: A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as c
arXiv:2601.15161v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct
arXiv:2605.13381v1 Announce Type: new Abstract: As AI-generated synthetic images become increasingly realistic, Vision Transformers (ViTs) have emerged as a cornerstone of modern deepfake detection. H
arXiv:2605.13214v1 Announce Type: cross Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model
arXiv:2605.13455v1 Announce Type: new Abstract: Synapses are densely packed submicron structures that dynamically reorganize during learning and memory formation. Longitudinal extit{in vivo} imaging o
arXiv:2605.12843v1 Announce Type: cross Abstract: Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to m
arXiv:2605.13088v1 Announce Type: new Abstract: Dynamical modelling is central to many scientific domains, including pharmacometrics, systems biology, physiology, and epidemiology. In these settings,
arXiv:2409.02038v3 Announce Type: replace-cross Abstract: Existing text-to-SQL benchmarks have largely been constructed from public databases with well-structured schemas and simplistic question-SQL p
arXiv:2605.12726v1 Announce Type: new Abstract: Final-token safety probes monitor a single hidden state after prompt prefill, but jailbreak prompts can contain probe-visible unsafe evidence distribute
arXiv:2605.12730v1 Announce Type: new Abstract: Existing AI systems for modeling human behavior operate at the level of individuals or detect events after they occur. As a result, they systematically
arXiv:2510.01502v2 Announce Type: replace-cross Abstract: Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social in
arXiv:2605.12710v1 Announce Type: new Abstract: Residual risk metrics have recently been introduced to assess the safety implications of automated driving systems. Existing approaches typically assume
arXiv:2512.18951v3 Announce Type: replace Abstract: Infants learn not only object categories but also fine-grained visual attributes such as color, size, and texture from limited experience. Prior inf
arXiv:2605.13574v1 Announce Type: cross Abstract: This study investigates deep self-disclosure toward generative AI by examining perceived non-humanity and structural similarity as psychological facto
arXiv:2605.12894v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are uncle
arXiv:2605.13520v1 Announce Type: cross Abstract: We address shortcomings of principal component analysis (PCA) for visualizing high-dimensional data lying on a nonlinear low-dimensional manifold via
arXiv:2605.12512v1 Announce Type: cross Abstract: Driven by large language models (LLMs), social bot can autonomously engage in local interactions, whose human-like behaviors enable them to evade soci
arXiv:2605.13383v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) perform computations on graphs by routing the signal between graph regions using a graph shift operator or a message passin
arXiv:2605.13652v1 Announce Type: cross Abstract: Pre-training large language models is dominated by the memory cost of storing full-rank weights, gradients, and optimizer states. Low-rank pre-trainin
arXiv:2509.24728v2 Announce Type: replace Abstract: Latent categorical variables are frequently found in deep learning architectures. They can model actions in discrete reinforcement-learning environm
arXiv:2605.13525v1 Announce Type: cross Abstract: Automated driving has made remarkable progress, yet situations still arise where human intervention is necessary. Teleoperation provides a scalable so
arXiv:2603.05582v2 Announce Type: replace-cross Abstract: The issue of algorithmic biases in deep learning has led to the development of various debiasing techniques, many of which perform complex tra
arXiv:2605.12534v1 Announce Type: cross Abstract: Most work in audio enhancement targets human speech, while bioacoustics is less studied due to noisy recordings and the distinct traits of animal soun
arXiv:2605.12804v1 Announce Type: new Abstract: Positive-negative pressure regulation is critical to soft robotic actuators, enabling large motion ranges and versatile actuation modes. However, achiev
arXiv:2605.13794v1 Announce Type: cross Abstract: We present BlitzGS, a distributed 3DGS framework that reduces active Gaussian workload for fast city-scale reconstruction. BlitzGS manages this worklo
arXiv:2506.13456v2 Announce Type: replace Abstract: Diffusion Policy has demonstrated strong visuomotor modeling capabilities, but its high computational cost renders it impractical for real-time robo
arXiv:2605.13382v1 Announce Type: new Abstract: While autoregressive (AR) Vision-Language-Action (VLA) models have demonstrated formidable reasoning capabilities in robotic tasks, their sequential dec
arXiv:2605.12520v1 Announce Type: cross Abstract: Taxonomy induction is crucial for organizing concepts into explicit and interpretable semantic hierarchies. While existing methods have achieved promi
arXiv:2605.13669v1 Announce Type: cross Abstract: This paper proposes a nonlinear guidance strategy capable of intercepting a constant-velocity, non-maneuvering target while strictly satisfying the pr
arXiv:2605.12560v1 Announce Type: cross Abstract: Improving patient outcomes depends on the prompt and accurate diagnosis of brain tumors, but manual MRI scan analysis is still time-consuming and unre
arXiv:2605.13059v1 Announce Type: new Abstract: Clinical diagnostic workups typically follow a modality escalation pathway: after initial clinical evaluation, clinicians begin with routine structural
arXiv:2605.13054v1 Announce Type: cross Abstract: Cross-domain offline reinforcement learning aims to adapt a policy from a source domain to a target domain using only pre-collected datasets, where en
arXiv:2605.12517v1 Announce Type: cross Abstract: Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality
arXiv:2605.13360v1 Announce Type: new Abstract: There is a growing demand for agentic AI technologies for a range of downstream applications like customer service and personal assistants. For applicat
arXiv:2605.13283v1 Announce Type: new Abstract: We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local ell_1-regularized robust estimation wit
arXiv:2605.13544v1 Announce Type: new Abstract: Fine-grained Vision-Language Pre-training (FVLP) demonstrates significant potential in 3D medical image understanding by aligning anatomy-level visual r
arXiv:2508.01031v5 Announce Type: replace Abstract: Computer-Aided Design (CAD) is widely used for conceptual design and parametric 3D modeling, but typically requires a high level of expertise from d
arXiv:2605.13208v1 Announce Type: new Abstract: Efficient Gas Source Localization (GSL) in real-world settings is crucial, especially in emergency scenarios. Mobile robots equipped with low-cost, in-s
arXiv:2605.12507v1 Announce Type: cross Abstract: While Large Language Model (LLM) multi-agent systems (MAS) offer a transformative approach to simulating human behavior in complex systems, it remains
arXiv:2605.13295v1 Announce Type: cross Abstract: LLM-based multi-agent systems have demonstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling,
arXiv:2410.14375v3 Announce Type: replace Abstract: Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlati
arXiv:2605.13589v1 Announce Type: cross Abstract: Causal discovery, the problem of inferring the direction of causality, is generally ill-posed. We use the language of structural causal models (SCM) t
arXiv:2605.13646v1 Announce Type: cross Abstract: End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recentl
arXiv:2605.12580v1 Announce Type: new Abstract: Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permi
arXiv:2508.01049v2 Announce Type: replace Abstract: Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games,
arXiv:2605.12876v1 Announce Type: new Abstract: Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continu
arXiv:2605.12718v1 Announce Type: new Abstract: Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structu
arXiv:2605.12553v1 Announce Type: cross Abstract: Accurate channel state information (CSI) prediction is essential for improving the reliability and spectral efficiency of massive MIMO-OFDM systems in
arXiv:2509.23597v5 Announce Type: replace-cross Abstract: Time series forecasting remains a critical challenge across numerous domains, yet the effectiveness of complex models often varies unpredictab
arXiv:2605.13675v1 Announce Type: new Abstract: Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. Ho
arXiv:2406.05410v3 Announce Type: replace Abstract: Current multimodal large language models (MLLMs) are mainly focused on the understanding and processing of perceptual modalities such as images and
arXiv:2605.13262v1 Announce Type: new Abstract: Modern SMILES-based chemical language models obtain strong MoleculeNet performance by treating SMILES as generic text and compensating with multi-millio
arXiv:2605.13709v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely applied in educational practices, such as for generating children's stories. However, the generated stories ar
arXiv:2605.12857v1 Announce Type: cross Abstract: Existing API-based agentic systems for RTL code generation are fundamentally misaligned with industrial practice: they assume a golden testbench is av
arXiv:2605.12882v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answ
arXiv:2605.13178v1 Announce Type: cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To ad
arXiv:2407.01602v2 Announce Type: replace-cross Abstract: Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously char
arXiv:2605.13638v1 Announce Type: cross Abstract: A quantum compiler is a critical piece in the quantum computing pipeline since it allows an abstract quantum circuit to be run on a physical quantum c
arXiv:2605.13138v1 Announce Type: cross Abstract: Automated detection of vulnerability-fixing commits (VFCs) is critical for timely security patch deployment, as advisory databases lag patch releases
arXiv:2511.00839v2 Announce Type: replace-cross Abstract: Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targete