Knowledge catalogue
arXiv:2605.19360v1 Announce Type: new Abstract: The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing
arXiv:2503.19877v2 Announce Type: replace Abstract: As language model (LM) outputs get more and more natural, it is becoming more difficult than ever to evaluate their quality. Simultaneously, increas
This article discusses how Applied Compute leverages Modal's infrastructure to scale reinforcement learning workloads, likely covering the technical implementation of distributed RL training, computat
arXiv:2503.06310v4 Announce Type: replace Abstract: Generating coherent long-form video sequences from discrete text prompts remains challenging due to difficulties in maintaining temporal coherence,
arXiv:2605.19587v1 Announce Type: new Abstract: Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only w
arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchm
arXiv:2605.19357v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabiliti
arXiv:2503.12172v4 Announce Type: replace-cross Abstract: Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distin
arXiv:2510.18821v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on w
MiniMax Speech 2.8 Turbo is a text-to-speech model available through Together AI's voice finder tool at voicefinder.together.ai, allowing users to preview and test different voice options directly. Th
arXiv:2605.19340v1 Announce Type: new Abstract: Vision foundation models (VFMs) have achieved strong performance across various vision tasks. However, it still remains challenging to apply VFMs for cr
arXiv:2605.19431v1 Announce Type: new Abstract: Multirotor aerial robots excel at maneuvering in three-dimensional space, and recent advances enable nimble navigation in cluttered and confined environ
arXiv:2605.19554v1 Announce Type: new Abstract: Instilling creativity in text-to-image (T2I) generation presents a significant challenge, as it requires synthesized images to exhibit not only visual n
arXiv:2510.05431v4 Announce Type: replace Abstract: Organizing large-scale patent corpora according to classification schemes is a core information management task that determines the accuracy and eff
Self-improving AI is a big deal! As a first step, I've been exploring how much of the post-training can be automated. Here is a first post on how I am using @FireworksAI_HQ Agent to automate LLM fine-
arXiv:2605.19342v1 Announce Type: new Abstract: Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. Howev
arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on h
arXiv:2605.19830v1 Announce Type: new Abstract: Conventional treatment policies map patient covariates to a single recommended intervention in order to maximize expected clinical outcomes. Although a
arXiv:2605.20110v1 Announce Type: new Abstract: Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-categ
arXiv:2512.07068v3 Announce Type: replace Abstract: Uniform Meaning Representation (UMR) is a novel graph-based semantic representation which captures the core meaning of a text, with flexibility inco
arXiv:2605.18971v1 Announce Type: cross Abstract: What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost
arXiv:2408.12385v3 Announce Type: replace-cross Abstract: We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. This
arXiv:2605.19219v1 Announce Type: new Abstract: A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistica
arXiv:2605.18797v1 Announce Type: cross Abstract: Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same
arXiv:2605.19355v1 Announce Type: cross Abstract: Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, re
arXiv:2505.17726v3 Announce Type: replace-cross Abstract: Recently, multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence. In particular,
arXiv:2507.18902v2 Announce Type: replace Abstract: There are more than 7,000 languages around the world, and current Large Language Models (LLMs) only support hundreds of languages. Dictionary-based
arXiv:2605.19213v1 Announce Type: new Abstract: Circular sample plots are a cornerstone of forest inventory, yet accurate measurement of tree diameter at breast height (DBH) and spatial location withi
arXiv:2605.20069v1 Announce Type: new Abstract: Competitive selection processes, from scientific funding to admissions and hiring, use evaluations to score candidates, and eventually choose a subset o
arXiv:2605.19823v1 Announce Type: cross Abstract: Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently contin
Dina Bass / Bloomberg: Socket, which helps companies safeguard open-source code against hackers, raised 60M led by Thrive Capital at a 1B valuation — Socket, a cybersecurity startup that sells technol
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