A new arXiv paper (2609.10613v1) proposes a posterior reweighting framework that models safety-aligned multimodal large language models (MLLMs) as implicitly operating over competing behavioral modes,…
Researchers introduced RDDMPI, a conditional residual diffusion framework for probabilistic multivariate time series imputation, detailed in arXiv paper 2609.11648v1. RDDMPI reformulates imputation as…
Researchers introduced CoRA-NAS, a two-stage neural architecture search framework that combines a static ranking prior with low-cost learning-curve refinement, according to a new arXiv paper (arXiv:26…
Researchers introduced SolCloudLLM, an LLM-based multimodal forecasting framework that fuses ground-based sky images with historical time-series data through bidirectional multimodal fusion to predict…
A new arXiv paper (2609.11780v1) reports that spectral metrics from the WeightWatcher framework can predict membership inference attack (MIA) vulnerability in machine learning models without training …
A new arXiv paper (2609.11538v1) shows that Generative Marginalization Models (MaMs) are equivalent to Generative Flow Networks (GFlowNets), and introduces Particle GFlowNets, which extends MaMs' samp…
ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder, achieved 75.41% average task success and an 8.20% average obstacle collision rate across 61 real-ro…
A large-scale empirical study of 265,363 Python notebooks submitted to Kaggle competitions found that general Python code quality is decoupled from machine learning performance, showing negligible or …
Researchers built and verified numbat, a machine-learning stack written entirely in Zig with no third-party runtime dependencies, exposing over 1,400 C ABI entry points and bindings for six languages,…
A variational, label-free physics-informed graph neural network (PI-GNN) developed by researchers posting to arXiv keeps von Mises error below 3.58% across a stiffness-contrast sweep of E_inc/E_mat fr…
A tensor network-guided reinforcement learning framework called GenQAS improves fixed-budget success probability in quantum architecture search by combining a fixed matrix product state warm-start wit…
A new arXiv paper (2609.11699v1) introduces Negative Self-Distillation (NSD), a framework that improves large language model reasoning by diverging from self-generated flawed reasoning rather than imi…
Researchers introduced CausalArena, a unified and evolvable benchmark for causal discovery, detailed in arXiv paper 2609.11897v1. CausalArena combines synthetic structural causal models (SCMs), semant…
Social media platforms are rolling out their own tools and guidelines to help users identify AI-generated content as the volume of such material rises online, according to Forbes Innovation contributo…
OpenAI withdrew its sponsorship of Caltech's AI math hackathon on Thursday after current and former Caltech mathematicians published an open letter on Wednesday warning the event "is likely to have de…
Anthropic published a 154-page threat intelligence report on Thursday detailing attempts by criminals, state-sponsored groups, spyware vendors, scientists and propagandists to misuse its AI models to …
Google DeepMind released the AlphaGenome Atlas, a resource mapping 9 billion human DNA variants that turns the company's AI predictions into a tool for researchers and a new cloud opportunity, accordi…
Mykola Maksymenko, a quantum physicist at Haiqu, told his team "I think AGI is here," saying agentic AI is compressing months of quantum research into days and extracting useful work from existing qua…
OpenAI announced ChatGPT for Financial Services on Thursday, a product that embeds financial datasets from Daloopa, PitchBook, and LSEG News directly into ChatGPT and adds "granular citations" so anal…
Agentic AI represents a new attack surface for enterprise security, according to a Forbes Councils column by Ivan Mans, which warns that the next class of enterprise threats will already be inside the…