Knowledge catalogue
arXiv:2408.05086v3 Announce Type: replace Abstract: Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and more broa
In the enterprise landscape, data is often highly fragmented across multiple source systems. Data curation is the process of organizing, cleaning, and enriching raw data to transform it into high-qual
arXiv:2511.20162v2 Announce Type: replace Abstract: Large multi-modal models (LMMs) show increasing performance in realistic visual tasks for images and, more recently, for videos. For example, given
arXiv:2601.10587v2 Announce Type: replace Abstract: The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise
arXiv:2405.16240v3 Announce Type: replace Abstract: In this paper, we introduce analytic federated learning (AFL), a new training paradigm that brings analytical (i.e., closed-form) solutions to the f
Agent skills are great. I wanted to share some of my favorites from Jesse Vincent's 'Superpowers' skill pack 𝚠𝚛𝚒𝚝𝚒𝚗𝚐-𝚙𝚕𝚊𝚗𝚜 skill produces much better plans than any harness' built in plan mode that I'
The specific tweet (status ID 2042726390617764234) could not be retrieved directly, as it does not appear in available search results and X/Twitter requires authentication to access individual post...
arXiv:2604.08479v1 Announce Type: new Abstract: Recent research shows that greater numbers of people are turning to Large Language Models (LLMs) for emotional support, and that people rate LLM respons
arXiv:2604.08133v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models due to their sparse activation mechanism. However, the s
arXiv:2505.20662v3 Announce Type: replace Abstract: Efficient reproduction of research papers is pivotal to accelerating scientific progress. However, the increasing complexity of proposed methods oft
arXiv:2601.05529v5 Announce Type: replace Abstract: High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap,
The OpenAI Academy 'Brainstorming with ChatGPT' tutorial is part of OpenAI Academy's library of tutorials and resources designed to help users leverage ChatGPT for idea generation and creative prob...
arXiv:2604.06036v3 Announce Type: replace-cross Abstract: Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalabilit
arXiv:2510.12184v2 Announce Type: replace Abstract: Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity,
arXiv:2604.06616v1 Announce Type: cross Abstract: Hybrid queries combining high-dimensional vector similarity search with spatio-temporal filters are increasingly critical for modern retrieval-augment
arXiv:2604.07892v1 Announce Type: new Abstract: Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsiste
arXiv:2604.08261v1 Announce Type: new Abstract: The complex and dynamic real-world clinical environment demands reliable deep learning (DL) systems. Out-of-distribution (OOD) detection plays a critica
arXiv:2604.04507v2 Announce Type: replace-cross Abstract: The rapid adoption of low-precision arithmetic in artificial intelligence and edge computing has created a strong demand for energy-efficient
arXiv:2604.07723v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that exis
arXiv:2604.08284v1 Announce Type: new Abstract: Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, an
arXiv:2604.06210v2 Announce Type: cross Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks fac
arXiv:2509.01986v4 Announce Type: replace-cross Abstract: In recent years, integrating multimodal understanding and generation into a single unified model has emerged as a promising paradigm. While th
arXiv:2604.06515v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While
arXiv:2604.07729v1 Announce Type: cross Abstract: Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore imp
arXiv:2604.08456v1 Announce Type: cross Abstract: Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread acros
arXiv:2603.11703v2 Announce Type: replace Abstract: We introduce EvoFlows, a variable-length protein sequence-to-sequence modeling approach designed for protein engineering. Existing protein language
arXiv:2603.02070v2 Announce Type: replace-cross Abstract: When automating plan generation for a real-world sequential decision problem, the goal is often not to replace the human planner, but to facil
arXiv:2601.21708v2 Announce Type: replace Abstract: Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing accelerat
arXiv:2604.07812v1 Announce Type: new Abstract: In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making th
Healthcare IT finds itself at a critical intersection where significant data opportunities are colliding with escalating cybersecurity threats. Rural and community hospitals, in particular, are facing
arXiv:2604.08118v1 Announce Type: new Abstract: Additive quantization enables extreme LLM compression with O(1) lookup-table dequantization, making it attractive for edge deployment. Yet at 2-bit prec
arXiv:2604.03815v2 Announce Type: replace-cross Abstract: Graph transformers have shown promise in overcoming limitations of traditional graph neural networks, such as oversquashing and difficulties i
LiteParse hit 4K+ GitHub stars in 3 weeks. ~500 pages in 2 seconds. No GPU. No API keys. 50+ file formats. Now @LoganMarkewich, our Head of Open Source, will show you how to build with it. Live worksh
Love this new podcast format ❤️ super insightful! 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeof
arXiv:2601.11471v3 Announce Type: replace Abstract: The key-value (KV) cache is a primary memory bottleneck in Transformers. We propose Low-Rank Key-Value (LRKV) attention, which reduces KV cache memo
Max volume for Max Agency 📣🗣️ 🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeoffs, evals, and every
arXiv:2604.07877v1 Announce Type: new Abstract: Long-term memory is fundamental for personalized and autonomous agents, yet populating it remains a bottleneck. Existing systems treat memory extraction
arXiv:2604.06473v1 Announce Type: new Abstract: Multivariate forecasting with Transformers faces a core scalability challenge: modeling cross-channel dependencies via attention compounds attention's q
arXiv:2511.08605v3 Announce Type: replace Abstract: Bangladesh's low-income population faces major barriers to affordable legal advice due to complex legal language, procedural opacity, and high costs
arXiv:2604.07085v1 Announce Type: new Abstract: In electronic health records (EHRs), clustering patients and distinguishing disease subtypes are key tasks to elucidate pathophysiology and aid clinical
arXiv:2412.20718v2 Announce Type: replace Abstract: The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alig
arXiv:2604.06798v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs) offer strong performance but suffer from high memory and computation costs. Weight binariz
arXiv:2603.20654v4 Announce Type: replace-cross Abstract: Classical Amdahl's Law conceptualized the limit of speedup for an era of fixed serial-parallel decomposition and homogeneous replication. Mode
arXiv:2603.28253v2 Announce Type: replace-cross Abstract: Time series forecasting is vital across many domains, yet existing models struggle with fixed-length inputs and inadequate multi-scale modelin
arXiv:2406.13086v2 Announce Type: replace Abstract: Lightweight autonomous unmanned aerial vehicles (UAV) are emerging as a central component of a broad range of applications. However, autonomous navi
arXiv:2602.16005v2 Announce Type: replace-cross Abstract: We introduce ODYN, a novel all-shifted primal-dual non-interior-point quadratic programming (QP) solver designed to efficiently handle challen
arXiv:2604.06814v1 Announce Type: cross Abstract: While traditional tree-based ensemble methods have long dominated tabular tasks, deep neural networks and emerging foundation models have challenged t
arXiv:2603.25898v2 Announce Type: replace-cross Abstract: LLM-assisted modeling holds the potential to rapidly build executable Digital Twins of complex systems from only coarse descriptions and senso
arXiv:2512.03532v2 Announce Type: replace Abstract: Generalizing open-vocabulary 3D instance segmentation (OV-3DIS) to diverse, unstructured, and mesh-free environments is crucial for robotics and AR/
arXiv:2602.06912v2 Announce Type: replace Abstract: Unsupervised segmentation from self-supervised ViT patches holds promise but lacks robustness: multi-object scenes confound saliency cues, and low-s
arXiv:2604.08000v1 Announce Type: cross Abstract: Proactivity is a core expectation for AGI. Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive age
arXiv:2604.07059v1 Announce Type: new Abstract: Electronic Control Units (ECUs) have played a pivotal role in transforming motorcars of yore into the modern vehicles we see on our roads today. They ac
arXiv:2604.04988v1 Announce Type: cross Abstract: Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parame
arXiv:2508.07299v2 Announce Type: replace-cross Abstract: The effectiveness of unlabeled data in Semi/Self-Supervised Learning (SSL) depends on appropriate assumptions for specific scenarios, thereby
The rapid evolution of AI is redefining industries, while also exposing organizations to new risks. At Google Cloud, we believe that modern cloud defense should have AI protection built in and accessi
arXiv:2604.07562v1 Announce Type: new Abstract: Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redund
arXiv:2604.06663v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to simulate social attitudes and behaviors, offering scalable 'silicon samples' that can approximat
arXiv:2604.07963v1 Announce Type: new Abstract: Data mixing strategy is essential for large language model (LLM) training. Empirical evidence shows that inappropriate strategies can significantly redu
arXiv:2510.19225v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows i
arXiv:2604.07774v1 Announce Type: cross Abstract: This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accompli