Knowledge catalogue
arXiv:2605.21282v1 Announce Type: new Abstract: Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and hav
arXiv:2508.02291v3 Announce Type: replace Abstract: Structured pruning is a standard tool for compressing deep neural networks, but its practical performance depends on how sparsity is allocated acros
FAL ASSETSSSS! It's been so fun building this out and being able to experiment on what the best way to reference previous generations, define characters, and search through all requests semantically l
arXiv:2605.21325v1 Announce Type: new Abstract: Linear attention has emerged as a cornerstone for efficient long-context architectures, as evidenced by its integration into state-of-the-art open-sourc
arXiv:2605.20514v1 Announce Type: new Abstract: We introduce FLASH-MAX, a shallow, exact-by-construction neural network architecture for predicting homogeneous electromagnetic fields from sparse point
arXiv:2605.20551v1 Announce Type: new Abstract: Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art meth
arXiv:2605.20561v1 Announce Type: new Abstract: Isoperimetric robotic trusses can adapt to different tasks and environments because they have a high strength-to-weight ratio, can change their own shap
arXiv:2605.20256v1 Announce Type: new Abstract: Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training l
arXiv:2603.16513v3 Announce Type: replace Abstract: Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation
arXiv:2605.21264v1 Announce Type: new Abstract: Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving distributed learning. However, existing FL methods face a fundamental
arXiv:2605.21418v1 Announce Type: cross Abstract: In sixth-generation (6G) ultra-dense networks, aggressive frequency reuse amplifies inter-cell interference (ICI), making multi-cell orthogonal freque
Reuters: Federal records: Grok was utilized in only 3 of 400+ publicly identified federal AI use cases in 2025, behind 234 for ChatGPT, 33 for Gemini, 26 for Claude — SpaceX's initial public offering
arXiv:2602.13485v2 Announce Type: replace Abstract: Networks of modern industrial systems are increasingly monitored by distributed sensors, where each system comprises multiple subsystems generating
arXiv:2605.21217v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA
arXiv:2605.20965v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still p
arXiv:2605.20787v1 Announce Type: new Abstract: The rapid advancements in generative AI technologies, such as Stable Diffusion, DALL-E, and Midjourney, have significantly transformed the creation of s
arXiv:2605.20761v1 Announce Type: new Abstract: The rapid proliferation of AI-generated text has introduced significant challenges in maintaining the integrity of digital content. Advanced generative
arXiv:2605.21369v1 Announce Type: new Abstract: This paper describes the fifth edition of the Shared Task on Multilingual Coreference Resolution, held in conjunction with the CODI-CRAC 2026 workshop.
arXiv:2605.21071v1 Announce Type: new Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs
Fine-tuning used to mean a team, a GPU cluster, and weeks of iteration. Now it's just a CLI command, ~10 min of GPU time, a few cents of compute. You walk away owning the weights. Open models off the
arXiv:2510.17269v2 Announce Type: replace Abstract: The advancement of vision-language models (VLMs) is hampered by a fragmented landscape of inconsistent and contaminated public datasets. We introduc
arXiv:2605.20854v1 Announce Type: new Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@k and max@k
Nvidia Corp.‘s latest results are remarkable even by its own high bar. Revenue set new records, driven by a 90%-plus surge in data center demand and what management described as “parabolic” demand as
Mark Tyson / Tom's Hardware: Flipper unveils the Flipper One, a pocketable open Arm Linux computer with similar performance to a Raspberry Pi 5, and welcomes feedback to get it market-ready — But the
arXiv:2602.16813v3 Announce Type: replace Abstract: Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive
arXiv:2605.20199v1 Announce Type: new Abstract: We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the c
arXiv:2605.20910v1 Announce Type: new Abstract: Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free app
arXiv:2503.19708v2 Announce Type: replace-cross Abstract: Urban microclimate, encompassing wind and temperature fields shaped by building geometry, significantly impacts energy consumption, pedestrian
arXiv:2605.20950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existin
For anyone who isn't sure, this is how you release a model and talk about the performance. Not 3-5 cherry-picked benchmarks. Performance：Qwen3.7-Max performs strongly across benchmarks in coding agent
arXiv:2605.20911v1 Announce Type: cross Abstract: Fighting games such as Street Fighter II present unique challenges to reinforcement learning (RL) agents due to their fast-paced, real-time nature. In
arXiv:2510.14737v3 Announce Type: replace Abstract: Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the
AI service management has arrived, and the enterprises keeping pace didn’t wait for perfect conditions — they consolidated their data first. Of course, that urgency is creating an opening for companie
arXiv:2605.21303v1 Announce Type: new Abstract: Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimen
This Databricks article discusses how organizations can leverage data and analytics to transition from simply tracking and reporting carbon emissions to making strategic decarbonization decisions. It
arXiv:2605.21398v1 Announce Type: new Abstract: Accurate registration between a prior model and the real scene is essential for high-precision robotic manipulation, yet optical methods suffer from lon
This Databricks blog post discusses the evolution from descriptive analytics (analyzing past events) to predictive analytics (forecasting future outcomes), likely exploring how modern data platforms e
arXiv:2605.21312v1 Announce Type: cross Abstract: Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimi
arXiv:2605.20892v1 Announce Type: new Abstract: Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-qu
arXiv:2603.01712v2 Announce Type: replace-cross Abstract: Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, an
arXiv:2605.21171v1 Announce Type: new Abstract: Ternary Vision Transformers offer substantial model compression, however state-of-the-art methods only ternarize the encoder layers, leaving patch embed
Full interview with Sundar is now live! https://x.com/rowancheung/status/2057491344697012384?s=20 Google just revealed Omni, personalized cross-device intelligence, and Spark agents at I/O 2025. I sat
arXiv:2605.20316v1 Announce Type: new Abstract: Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified visi
arXiv:2605.21439v1 Announce Type: cross Abstract: This paper presents a low-complexity, model-free, output-feedback controller for a class of unknown time-varying nonlinear systems with unknown input
arXiv:2605.20287v1 Announce Type: cross Abstract: Standard cells form the building blocks of digital circuits, so their delay and power critically influence chip-level performance; yet characterizatio
FWIW, I think this moves up my AI timelines a bit. I think the next milestone will be 'Artificial *Grothendieck* Intelligence' (AGrI): defining new general mathematical structures to solve the hardest
arXiv:2605.20727v1 Announce Type: new Abstract: Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels, primarily due to overfitting on mislabeled data
Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Gated DeltaNet-2 outperforms KDA and Mamba-3, the latest and best recurrent architectures, hea
Gated DeltaNet has been one of my favorite 'hybrid attention' newcomers in the good old transformer stack. Excited to see Gated DeltaNet-2. Adding it to my reading stack. In the meantime, I have a pri
arXiv:2602.10408v2 Announce Type: replace-cross Abstract: Normalization layers are standard in transformers, but it is not clear whether their sample-dependent computations are necessary throughout bo
arXiv:2605.21435v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited f
arXiv:2605.20752v1 Announce Type: new Abstract: Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-lan
arXiv:2605.20651v1 Announce Type: new Abstract: Existing deep learning frameworks for Optical Coherence Tomography Angiography (OCTA) vessel segmentation are largely derived from the U-Net architectur
arXiv:2605.20896v1 Announce Type: cross Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft in
arXiv:2605.20267v1 Announce Type: new Abstract: Synthetic PET images are valuable for quantitative imaging workflow development, scalable virtual imaging trials, and deep learning model training, but
arXiv:2512.03671v2 Announce Type: replace Abstract: The rise of generative AI (GenAI) chatbots accessible via conversational interfaces is transforming digital interactions and holds economic promise.
arXiv:2605.21055v1 Announce Type: cross Abstract: A recent trend is to leverage machine learning models to improve the evolutionary design and optimization process. We propose a novel transformer-base
arXiv:2605.20241v1 Announce Type: cross Abstract: Prompt-level safety probes for large language models use hidden-state representations to separate safe from unsafe prompts, but strong average detecti
arXiv:2602.20399v2 Announce Type: replace Abstract: Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-f
George Blankenship got really emotional telling the story of early Tesla And it shows why Tesla’s survival story is one of the wildest in startup history The Model S wasn’t just another car. It was Te