Soft Learning
arXiv:2605.18889v1 Announce Type: cross Abstract: Modern machine learning forces practitioners to choose between powerful but expensive deep networks and fast but limited classical algorithms. Here we
Knowledge catalogue
arXiv:2605.18889v1 Announce Type: cross Abstract: Modern machine learning forces practitioners to choose between powerful but expensive deep networks and fast but limited classical algorithms. Here we
This is Optimizer, a weekly newsletter sent from Verge senior reviewer Victoria Song that dissects and discusses the latest gizmos and potions that swear they're going to change your life. This week's
arXiv:2505.09067v2 Announce Type: replace-cross Abstract: In this article, we consider the infinite-horizon reach-avoid (RA) and stabilize-avoid (SA) zero-sum game problems for general nonlinear conti
arXiv:2602.17001v2 Announce Type: replace Abstract: Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries
Alexander Martin / The Record: Sources: an attack exploiting a previously unknown vulnerability in Huawei router software caused a three-hour nationwide telecoms outage in Luxembourg in 2025 — An atta
Financial Times: Sources: Nvidia's business development group, not its VC arm NVentures, has led much of its ~90B dealmaking push across 145+ companies over the past 16 months — Nvidia's Huang bankrol
Wall Street Journal: Sources: OpenAI is preparing to file confidentially for an IPO as early as Friday; the company plans to be ready to go public as early as September — The artificial-intelligence g
Elon Musk posted on X praising SpaceX's Starship as a work of art, likely expressing appreciation for the vehicle's design, engineering, or aesthetic qualities. The statement reflects Musk's perspecti
arXiv:2605.06270v2 Announce Type: replace Abstract: Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input i
arXiv:2605.19378v1 Announce Type: new Abstract: This paper systematically diagnoses the training failure modes of Token-Choice sparse Mixture-of-Experts (MoE) on video Diffusion Transformers. Starting
arXiv:2505.23747v2 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving
arXiv:2605.20085v1 Announce Type: new Abstract: Robotic manipulation is often specified through language instructions or task identifiers, yet cluttered environments with similar objects are better ha
arXiv:2605.18836v1 Announce Type: cross Abstract: Dataset Distillation (DD) synthesizes a compact synthetic dataset that preserves the training utility of a full dataset. However, its standard formula
arXiv:2605.19607v1 Announce Type: cross Abstract: Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integra
arXiv:2605.18791v1 Announce Type: cross Abstract: Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multi
Spent some time with the Hermes + xurl flow from @NousResearch and @XDevelopers. What I like: xurl is a real CLI. It speaks the X API surface directly, and Hermes loads it as a skill. The SuperGrok OA
arXiv:2605.18856v1 Announce Type: cross Abstract: Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeate
arXiv:2605.19974v1 Announce Type: new Abstract: The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However
arXiv:2605.19822v1 Announce Type: cross Abstract: Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability r
Ivan Mehta / TechCrunch: Stability AI releases a new family of audio models called Stable Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs — Stability AI, the co
arXiv:2605.18905v1 Announce Type: cross Abstract: Neural operators have emerged as a powerful, discretization-invariant framework for solving partial differential equations (PDEs). Although establishe
arXiv:2605.19856v1 Announce Type: cross Abstract: Training very deep neural networks requires controlling the propagation of magnitudes across depth. Without such control, activations and gradients ma
arXiv:2605.20035v1 Announce Type: new Abstract: Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequence
arXiv:2605.18835v1 Announce Type: new Abstract: Traditional sheet metal forming relies on time-consuming and expensive Finite Element Analysis (FEA) for design validation, a process that significantly
arXiv:2605.19338v1 Announce Type: cross Abstract: Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, l
arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG)
Starship aesthetic is unparalleled 'Cathedrals everywhere for those with eyes to see' Starship v3 is truly wild > 200+ feet (just the upper stage ship itself) > 220,000 lb payload capacity to low eart
Starship Rising These vehicles are the first of many – made possible by the tireless effort of SpaceX engineers and technicians – and are designed to enable the core revolutionary capabilities of Star
arXiv:2605.19804v1 Announce Type: cross Abstract: For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic prefere
arXiv:2602.18718v2 Announce Type: replace-cross Abstract: For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorith
Stoked to work closely with @Vtrivedy10 on this. I've spoken about it before but an emerging trend i'm seeing with many of the ai-native companies I work with (shoutout @larsen_weigle_ ) is a focus on
arXiv:2605.18890v1 Announce Type: cross Abstract: The scientific claims drawn from LLM social simulations should be no stronger than the robustness audits that support them. Generative agents bring ne
arXiv:2605.19895v1 Announce Type: new Abstract: Constraint programming practitioners accelerate hard problems through a layered set of techniques applied in order of risk. Standard hardening (symmetry
arXiv:2605.18851v1 Announce Type: new Abstract: Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs).
arXiv:2605.19876v1 Announce Type: new Abstract: Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work iden
arXiv:2605.19866v1 Announce Type: new Abstract: Vision-Language Models (VLMs) parse documents end-to-end but frequently break down on layouts unlike those seen in training. We attribute this to a two-
arXiv:2603.05933v2 Announce Type: replace Abstract: Applying Small Language Models (SLMs) to Chinese character-driven generation remains challenging due to data scarcity and the difficulty of disentan
arXiv:2605.19247v1 Announce Type: new Abstract: Current neural architecture search (NAS) methods are often limited by their predefined, restrictive search spaces. While recent large language model (LL
arXiv:2605.19931v1 Announce Type: cross Abstract: Estimating forest aboveground biomass (AGB) from Earth observation combines two structurally incompatible label sources: spaceborne lidar provides can
Subagents running locally and simultaneously on MacBook Pro M5 with Codex CLI + @lmstudio to review code and find bugs using Qwen 3.6 Powered by the updated MLX engine with batching in beta in the app
arXiv:2601.20309v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memor
arXiv:2605.18988v1 Announce Type: cross Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary atta
arXiv:2511.16766v3 Announce Type: replace Abstract: Scalable Vector Graphics are a standard representation for editable visual design, yet they are usually authored as single view two dimensional illu
arXiv:2605.19319v1 Announce Type: new Abstract: Visual prediction has emerged as a promising paradigm for embodied control, where future observations are generated and then translated into actions. Ho
arXiv:2605.19264v1 Announce Type: new Abstract: Voting methods weighted by stakes are the fundamental governance paradigm in Proof-of-Stake (PoS) blockchains. Such a paradigm is known to be prone to p
arXiv:2605.18816v1 Announce Type: cross Abstract: Neural surrogates enable orders-of-magnitude acceleration of computational fluid dynamics (CFD) simulations, with the potential to transform engineeri
arXiv:2605.19799v1 Announce Type: cross Abstract: We present a semi-supervised framework for joint segmentation and classification of fetal cardiac ultrasound images. Built upon the EchoCare multi-tas
arXiv:2605.18920v1 Announce Type: cross Abstract: Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over i
arXiv:2605.19766v1 Announce Type: cross Abstract: An effective healthcare agent must be able to recall and reason over a patient's longitudinal medical history. However, the absence of datasets with r
arXiv:2603.12296v2 Announce Type: replace-cross Abstract: Deep learning has achieved transformative performance across diverse domains, largely driven by large-scale and high-quality training data. In
arXiv:2605.18979v1 Announce Type: new Abstract: We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) w
arXiv:2602.11910v2 Announce Type: replace-cross Abstract: Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remai
arXiv:2605.20068v1 Announce Type: cross Abstract: Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolat
arXiv:2605.20030v1 Announce Type: new Abstract: While optimal transport (OT) enforces a rigid constraint by requiring two measures to be matched exactly, partial optimal transport relaxes this require
arXiv:2601.20308v2 Announce Type: replace Abstract: Diffusion models have demonstrated exceptional success in video super-resolution (VSR), exhibiting powerful capabilities for generating fine-grained
arXiv:2605.19358v1 Announce Type: new Abstract: Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing
arXiv:2605.19727v1 Announce Type: new Abstract: Existing 3D foundation models typically align point clouds to frozen vision-language spaces like CLIP, which achieve strong cross-modal retrieval by com
arXiv:2603.29501v2 Announce Type: replace-cross Abstract: Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training.
arXiv:2605.19446v1 Announce Type: cross Abstract: Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to
arXiv:2603.07018v2 Announce Type: replace-cross Abstract: Treatment effects estimated from a randomized controlled trial are local not only to the study population but also to the time at which the tr