safety

arXiv:2608.28576v1 Announce Type: cross Abstract: Synthetic data can improve statistical inference when real data are scarce, but naively treating synthetic samples as real data can introduce bias and

arXiv:2608.28564v1 Announce Type: cross Abstract: We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent alphageq 0 for polyno

arXiv:2608.27719v1 Announce Type: new Abstract: Biological heterogeneity in Alzheimer's Disease (AD) poses a critical diagnostic challenge, particularly for traditional linear methods that fail to cap

arXiv:2608.28300v1 Announce Type: new Abstract: Robotic industrial panel operation requires not only accurate control localization but also compliance with operating procedures, safety rules, and devi

arXiv:2608.27507v1 Announce Type: new Abstract: Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently parameterized policies in replica

arXiv:2512.17581v2 Announce Type: replace Abstract: Benchmarking competitions are central to the development of artificial intelligence (AI) in medical imaging, defining performance standards and shap

arXiv:2608.27651v1 Announce Type: new Abstract: Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus g

arXiv:2608.28276v1 Announce Type: new Abstract: Structured generation underpins large language model (LLM) agents that produce JSON, SQL, and function calls, where a single wrong field can cause the d

arXiv:2608.27826v1 Announce Type: cross Abstract: Federated recommendation (FedRec) enables personalized modeling without centralizing users' interaction histories, but most existing methods assume a

arXiv:2606.14580v2 Announce Type: replace Abstract: Identifying persuasive rhetorical cues is critical across domains, from detecting information manipulation and improving AI safety to advancing publ

arXiv:2608.28508v1 Announce Type: new Abstract: Forced alignment evaluation typically requires manually annotated timestamps, limiting large-scale and multilingual analysis. We introduce two corpus-le

arXiv:2608.27609v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have shown strong promise for general-purpose robotic manipulation by mapping language instructions and vision obse

arXiv:2604.07809v2 Announce Type: replace Abstract: Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependenc

arXiv:2603.28387v3 Announce Type: replace-cross Abstract: Trustworthy clinical AI must use real evidence and avoid relying on surface-level artifacts. We evaluate 12 open-weight vision-language models

arXiv:2608.27877v1 Announce Type: new Abstract: Linking the internal representations of deep neural networks (DNNs) to human mental representations is important for using DNNs as computational models

arXiv:2603.21366v2 Announce Type: replace Abstract: Autoregressive video diffusion has recently emerged as a promising paradigm for long-video generation, enabling causal synthesis beyond the temporal

arXiv:2608.28499v1 Announce Type: new Abstract: To determine the real-world effectiveness of machine learning based malware detection, it is vital to evaluate its robustness against highly capable adv

arXiv:2608.27688v1 Announce Type: new Abstract: In this paper, we develop SafeStep, an interactive browser-based semantic communication platform for live pedestrian safety monitoring. SafeStep extract

Seems concerning: There are major incidents happening, and yet we're ~entirely dependent on AI companies to self-disclose information about them. It's not hard to see how this goes badly. While there

Six Dubious Strategies The AI industry Has Tried: Doom (Oh No! AI Civilizations!) Gloom (You will all lose your jobs!) Nerd Rapture (AI will be better than all humans by the end of next year!) Terror

arXiv:2608.28090v1 Announce Type: new Abstract: Humanoid robots with quasi-direct-drive actuators continuously generate joint torque while standing, whereas seated humans delegate weight support to ch

arXiv:2509.19212v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisi

arXiv:2608.28408v1 Announce Type: new Abstract: Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient f

arXiv:2608.27948v1 Announce Type: new Abstract: Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which invo

arXiv:2603.19423v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously comp

arXiv:2608.27540v1 Announce Type: cross Abstract: We develop a mathematical theory of superposition in neural networks using tools from frame theory and compressed sensing. In our model, a sparse bina

arXiv:2608.28246v1 Announce Type: new Abstract: Robotic sorting of recyclable waste is challenging due to the deformable and geometrically inconsistent nature of target objects. We present a training-

arXiv:2201.13259v4 Announce Type: replace Abstract: Generative flow networks (GFlowNets) are a method for learning a stochastic policy for generating compositional objects, such as graphs or strings,

arXiv:2608.27467v1 Announce Type: new Abstract: We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participate

arXiv:2608.28306v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) improves reasoning by training a problem-only student on its own rollouts using dense token-level supervision from

arXiv:2608.28010v1 Announce Type: new Abstract: Flow matching enables likelihood-free training, yet alignment methods increasingly reuse conditional flow matching (CFM) losses as endpoint negative log

arXiv:2608.28382v1 Announce Type: new Abstract: Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's i

arXiv:2608.28518v1 Announce Type: cross Abstract: We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that

arXiv:2608.27658v1 Announce Type: new Abstract: Subword tokenization hinders low-resource language processing by imposing frequency patterns from dominant languages onto script-sharing variants. Byte-

11/ METR and Redwood’s work is extremely valuable, but it assesses model behavior and alignment. That is only half the picture. We also need an independent account of how OpenAI’s containment failed.

14/ If frontier labs are serious about defense, they should offer cyber models to defenders at cost and stop fighting open weights through the regulatory channel. They created the problem, and for muc

I've been genuinely shocked at the complacency here. There's no evidence anyone is really *doing* anything! Like, that was swell of OpenAI, whose models committed a federal crime, to let some independ

or: they don’t have any more to announce. Today I was asked why we haven’t announced more math results from Astra since these problems. At @OpenAI we aim to devote time to finding and announcing math

We will not get through this era of history well if we lose ourselves in anthropomorphism. @anilkseth dissects @dwarkesh_sp’s misleadingly anthropomorphic summary of the HF incident: @dwarkesh_sp's su

“What Ilya saw” is what Dario saw which is that Sam can’t be trusted. Which is why they left. A lot of other people have discovered the same, since. If OpenAI is going to IPO or OpenAI has AGI Then Wh

arXiv:2608.26859v1 Announce Type: new Abstract: Current object pose estimation research remains predominantly model-centric, focusing on architectural innovations and post-processing refinements. This

arXiv:2608.27239v1 Announce Type: cross Abstract: Adverse drug reactions (ADRs) are a major, largely preventable source of patient harm. In high-income settings, electronic health records store a pati

arXiv:2608.26506v1 Announce Type: cross Abstract: Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior wo

arXiv:2608.26493v1 Announce Type: new Abstract: Decentralized learning systems aim to collaboratively train models across multiple clients without relying on a central coordinator. While decentralizat

arXiv:2511.06611v2 Announce Type: replace Abstract: Accurate measurement of circular centers is a fun-damental geometric sensing problem in instrumentation and measurement tasks involving cameras, LiD

arXiv:2603.28410v2 Announce Type: replace Abstract: Preference-based many-objective Bayesian optimization typically assumes that all pairwise comparisons arise from a single latent utility function, d