3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
OpenAI fired three safety researchers who helped investigate the Hugging Face hack.
OpenAI is standing firm on its decision to fire three safety researchers after an investigation found they committed "a significant breach of trust." In a post on X on Friday, the company said Jasmine Wang, Tomek Korbak…
The AI firm instead claims the researchers were fired for mishandling sensitive information.
AI researchers hate this one weird modest proposal.
arXiv:2610.11527v2 Announce Type: replace Abstract: Atomistic simulation is a fundamental tool for studying long-term materials evolution, from diffusion and defect dynamics to interfacial reactions and fracture.
arXiv:2610.10827v2 Announce Type: replace-cross Abstract: Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate into an actiona…
arXiv:2610.11096v2 Announce Type: replace-cross Abstract: Visual tracking across the air-water interface is challenged by splashes, bubbles, refraction, reflections, and abrupt appearance changes that can temporarily inv…
arXiv:2610.11454v2 Announce Type: replace-cross Abstract: Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-…
arXiv:2610.12026v2 Announce Type: replace-cross Abstract: Humanoid robots are a promising platform for general-purpose manipulation.
arXiv:2610.11231v1 Announce Type: new Abstract: Small vision-language models may be able to read external evidence yet struggle to obtain it.
arXiv:2610.11344v1 Announce Type: new Abstract: Physics-based models connect scientific explanation with quantitative prediction.
arXiv:2610.11352v1 Announce Type: new Abstract: Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities.
arXiv:2610.11380v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and improve efficiency.
arXiv:2610.11392v2 Announce Type: replace Abstract: System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generative interface.
arXiv:2610.11399v2 Announce Type: replace Abstract: Many applications of language models hinge not on individual samples but on the expectation of a test functional under the model.
arXiv:2610.11502v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL), particularly through Group Relative Policy Optimizat…
arXiv:2610.11715v1 Announce Type: new Abstract: Hypernetworks that map a context directly to a LoRA adapter let a large language model carry that context in its weights, but prior work has demonstrated them only on base…
arXiv:2610.11989v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated responses using token-level teacher supervision.
arXiv:2610.12090v1 Announce Type: new Abstract: Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot acti…
arXiv:2610.12129v1 Announce Type: new Abstract: A large body of research measures model coherence based on output variance without adequately considering competing causes.
arXiv:2610.12168v1 Announce Type: new Abstract: We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abil…
arXiv:2610.12303v1 Announce Type: new Abstract: Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing dependencies as weigh…
arXiv:2610.12393v1 Announce Type: new Abstract: Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet capturing synergistic information remains challenging due to…
arXiv:2610.02660v1 Announce Type: cross Abstract: Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Transformer evaluations…
arXiv:2610.05711v1 Announce Type: cross Abstract: Strong image generation models are conditioned on class labels, aligned to frozen pretrained encoders, or built on separately trained autoencoders.
arXiv:2610.10560v1 Announce Type: cross Abstract: AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting.
arXiv:2610.10782v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for post-training vision-language models (VLMs), but it typically assumes a static trai…
arXiv:2610.10924v1 Announce Type: cross Abstract: The Tensor-Memory Equilibrium (TME) model of "FP8 is All You Need (Part 1)" calculates the execution time of Ozaki Scheme II emulation of fp64 as the maximum of a tensor-…
arXiv:2610.10933v1 Announce Type: cross Abstract: Spiking language models face a tradeoff between representing continuous semantic features over short temporal windows and retaining costly nonlinear attention operations.
arXiv:2610.10974v1 Announce Type: cross Abstract: Off-policy evaluation (OPE) estimates the value of a target policy from logged data, but limited behavior-policy coverage can force high-variance reweighting or reward-mo…
arXiv:2610.10975v1 Announce Type: cross Abstract: Muon has motivated a growing family of optimizers that compose multiple matrix normalizations, but these methods remain fragmented and lack a unified perspective.
arXiv:2610.10978v1 Announce Type: cross Abstract: When a field that an authority contract needs exists only in unstructured evidence, a model can sense it.
arXiv:2610.11019v1 Announce Type: cross Abstract: Multimodal large language models learn mostly from paired image-text data or annotated video, and raw web video is rarely used to further train an existing language model…
arXiv:2610.11031v1 Announce Type: cross Abstract: A long-standing hypothesis in artificial intelligence and neuroscience posits that intelligence is closely related to compression: the ability to compress information eff…
arXiv:2610.11163v1 Announce Type: cross Abstract: Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identical to a remotely depl…
arXiv:2610.11168v1 Announce Type: cross Abstract: Robotic manipulation often contains repeated motions whose local observations look similar at different phases.
arXiv:2610.11175v2 Announce Type: replace-cross Abstract: Modern data-driven decision-making methods, such as imitation learning (IL) and reinforcement learning (RL), have achieved great success in solving many complex t…
arXiv:2610.11387v1 Announce Type: cross Abstract: Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs.
arXiv:2610.11546v1 Announce Type: cross Abstract: Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated parameters.
arXiv:2610.11599v1 Announce Type: cross Abstract: Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs).
arXiv:2610.11659v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals.
arXiv:2610.11690v1 Announce Type: cross Abstract: In the graph model for conflict resolution (GMCR), a decision maker (DM) either moves the conflict to another state or does nothing.
arXiv:2610.11692v1 Announce Type: cross Abstract: Foundation models supply reinforcement learning (RL) with priors that mitigate its longstanding weaknesses in sample efficiency and transfer, but their token-by-token gen…
arXiv:2610.11694v1 Announce Type: cross Abstract: Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic function.
arXiv:2610.11734v1 Announce Type: cross Abstract: We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting.
arXiv:2610.11792v1 Announce Type: cross Abstract: We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and preference-adaptive mo…
arXiv:2610.11818v1 Announce Type: cross Abstract: While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limits adoption in instit…
arXiv:2610.11826v1 Announce Type: cross Abstract: Object hallucination remains a major obstacle for large vision-language models (LVLMs) to generate reliable content.
arXiv:2610.12007v1 Announce Type: cross Abstract: Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-of…
arXiv:2610.12104v1 Announce Type: cross Abstract: Building a capable video editor remains significantly harder than a video generator: editing requires (source, instruction, edited) triplets that are prohibitively expens…