Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization to reduce high-fidelity CFD cost while retaining RANS-level...
Physical selectors (lasers choosing a mode, Ising machines settling on a ground state, condensates occupying a spin state) produce high-dimensional signatures a...
Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended ho...
Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work ...
Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reason...
Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achiev...
We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D...
Learning in simulation provides a useful foundation for scaling robotic manipulation capabilities. However, this paradigm often suffers from a lack of data-gene...
Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black bo...
Recent advances in Large Language Models (LLMs) have enabled conversational AI agents to engage in extended multi-turn interactions spanning weeks or months. Ho...
Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks rem...
Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny...
Reliable multi-horizon traffic forecasting is challenging because network conditions are stochastic, incident disruptions are intermittent, and effective spatia...
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experi...
Massively parallel hardware (GPUs) and long sequence data have made parallel algorithms essential for machine learning at scale. Yet dynamical systems, like rec...
Adapting transformer positional encoding to meshes and graph-structured data presents significant computational challenges: exact spectral methods require cubic...
The ``LLM-as-a-judge'' paradigm has become a standard method for evaluating open-ended generation. To address the quadratic scalability costs of pairwise compar...
Federated Learning (FL) is increasingly applied in sectors like healthcare, finance, and IoT, enabling collaborative model training while safeguarding user priv...
Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient...
Large language models are increasingly deployed as autonomous agents that must plan, act, and recover from mistakes through long-horizon interaction with enviro...
Stochastic resetting, where a dynamical process is intermittently returned to a fixed reference state, has emerged as a powerful mechanism for optimizing first-...
Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectu...
Automated presentation generation remains a challenging task requiring coherent content creation, visual design, and audience-aware communication. This work pro...
Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models...
Overview Google is rolling out Personal Intelligence to all free Gemini users in the United States, after a testing period with paid plans. The feature lets Ge...
Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the va...
Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language models (LLMs) often exhibit cultural biases that misalign wi...
Immersive extended reality (XR) applications introduce latency-critical workloads that must satisfy stringent real-time responsiveness while operating on energy...
Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications. Retrieval-augmented generation (RAG) and co...
Integration of CPU and GPU technologies is a key enabler for modern AI and graphics workloads, combining control-oriented processing with massive parallel compu...
Collaborative filtering (CF) recommendation has been significantly advanced by integrating Graph Neural Networks (GNNs) and Graph Contrastive Learning (GCL). Ho...
We study mean estimation for a Gaussian distribution with identity covariance in mathbb{R}^d under a missing data scheme termed realizable ε-contamination model...
Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in indu...
!Into the Omniverse: How Industrial AI and Digital Twins Accelerate Design, Engineering and Manufacturing Across Industrieshttps://blogs.nvidia.com/wp-content/u...
Overview OpenAI released GPT‑5.4 in early March, positioning it for professional tasks such as programming and data analysis. The company has now introduced tw...
!https://www.androidauthority.com/wp-content/uploads/2026/02/the-gemini-app-with-nano-banana-selected-scaled.jpg TL;DR - Gemini is adding the ability to mark up...
Robust task-oriented spoken dialogue agents require exposure to the full diversity of how people interact through speech. Building spoken user simulators that a...
Gradient inversion attacks reveal that private training text can be reconstructed from shared gradients, posing a privacy risk to large language models (LLMs). ...
Multi-turn conversations are a common and critical mode of language model interaction. However, current open training and evaluation data focus on single-turn s...
Google announced on Tuesdayhttps://blog.google/products-and-platforms/products/search/personal-intelligence-expansion/ that all users in the US will now have ac...
Large language models (LLMs) are increasingly deployed in applications with societal impact, raising concerns about the cultural biases they encode. We probe th...
In this report, we introduce the IQuest-Coder-V1 series-(7B/14B/40B/40B-Loop), a new family of code large language models (LLMs). Moving beyond static code repr...
!https://9to5google.com/wp-content/uploads/sites/4/2026/03/Gemini-Personal-intelligence-free-1.jpg?quality=82&strip=all&w=1600 Following the announcement in Jan...
The features on social media apps like Snapchat evolve nearly as fast as what’s trending. To keep pace, its parent company Snap has adopted open data processing...
Spiking Neural Networks (SNNs) offer an energy efficient alternative to conventional Artificial Neural Networks (ANNs) but typically still require a large numbe...
markdown ← Back to Articleshttps://huggingface.co/blog !https://huggingface.co/avatars/c3988435f58abccd0950f50f6ef4a2e4.svghttps://huggingface.co/plcedoz38 !htt...
The problem Every time your agent starts a conversation, it starts from zero. Sure, you can stuff a summary into the system prompt, use RAG, or call Mem0 or Ze...
Most operators assume their agents are running efficiently. They're not. Not because anyone built them badly, but because nobody audits them. You build the thin...
