Knowledge catalogue
arXiv:2503.04872v3 Announce Type: replace-cross Abstract: The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. Howev
Today we’re releasing Qwen-Scope 🔭, an open suite of sparse autoencoders for the Qwen model family. It turns SAE features into practical tools： 🎯 Inference — Steer model outputs by directly manipulati
arXiv:2510.14703v2 Announce Type: replace Abstract: Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an in
arXiv:2604.26951v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters f
arXiv:2604.26836v1 Announce Type: new Abstract: Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploratio
arXiv:2604.26694v1 Announce Type: cross Abstract: We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruc
arXiv:2505.22897v2 Announce Type: replace Abstract: While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less atten
arXiv:2603.07080v3 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time de
arXiv:2510.14438v2 Announce Type: replace Abstract: The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent
Editor’s note: Want to keep up with the latest from Google Cloud? Check back here for a monthly recap of our latest updates, announcements, resources, events, learning opportunities, and more. We host
arXiv:2604.26644v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-t
arXiv:2604.03260v2 Announce Type: replace-cross Abstract: Standard attention scales quadratically with sequence length. Efficient attention methods reduce this O(n^2) cost, but when retrofitted into p
arXiv:2604.24810v1 Announce Type: new Abstract: Edge computing environments impose strict constraints on energy consumption and latency, making the deployment of deep neural networks a significant cha
arXiv:2604.24822v1 Announce Type: cross Abstract: Context: Software vulnerabilities pose significant security threats to software systems, especially as software is increasingly used across many areas
arXiv:2604.25489v1 Announce Type: cross Abstract: Coherent transition radiation (CTR) spectroscopy is a critical diagnostic for characterizing the longitudinal structure of relativistic electron bunch
arXiv:2604.24940v1 Announce Type: new Abstract: Word embeddings are fundamental to natural language processing, yet traditional approaches represent each word with a single vector, creating representa
arXiv:2604.24919v1 Announce Type: new Abstract: Earth Observation (EO) is moving beyond static prediction toward multi-step analytical workflows that require coordinated reasoning over data, tools, an
arXiv:2604.25850v1 Announce Type: new Abstract: Harnesses have become a central determinant of coding-agent performance, shaping how models interact with repositories, tools, and execution environment
As AI models grow larger and more capable, the computational cost and time required to evaluate them has become a significant limiting factor in development, potentially surpassing training compute as
arXiv:2604.25053v1 Announce Type: new Abstract: While large language models (LLMs) are increasingly being explored for mental health applications, recent studies reveal that they can exhibit stigma to
arXiv:2604.24775v1 Announce Type: cross Abstract: We present a Mixture-of-Experts-based foundation model applied to the GlueX DIRC detector at Jefferson Lab, demonstrating its utility as a unified fra
arXiv:2410.24214v3 Announce Type: replace-cross Abstract: Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustne
arXiv:2604.24916v1 Announce Type: new Abstract: We introduce asRoBallet, to the best of our knowledge, the first successful deployment of reinforcement learning (RL) on a humanoid ballbot hardware. Hi
arXiv:2604.25702v1 Announce Type: new Abstract: Contemporary neural machine translation (NMT) systems are almost exclusively built by training on supervised parallel data. Despite the tremendous progr
arXiv:2604.24999v1 Announce Type: new Abstract: Thoracic Computed Tomography (CT) scans offer detailed insights into the intricate branching network of the airway tree, which is essential for understa
arXiv:2512.12087v3 Announce Type: replace Abstract: The growing demand for long-context inference capabilities in Large Language Models (LLMs) has intensified the computational and memory bottlenecks
arXiv:2604.25580v1 Announce Type: new Abstract: The closure of Perspective API at the end of 2026 discards what has functioned as the de facto standard for automated toxicity measurement in NLP, CSS,
arXiv:2505.14174v2 Announce Type: replace Abstract: LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM t
arXiv:2510.20303v3 Announce Type: replace Abstract: Citations from LLM-based RAG systems are supposed to simplify response verification. However, this goal is undermined in cases of citation failure,
arXiv:2604.25273v1 Announce Type: new Abstract: Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus
arXiv:2604.25676v1 Announce Type: new Abstract: Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or m
arXiv:2604.24959v1 Announce Type: new Abstract: Learning matrix-valued distributions from high-dimensional and possibly incomplete training data is challenging: ambient-space generative modeling is co
arXiv:2602.01433v2 Announce Type: replace Abstract: Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-te
arXiv:2604.25477v1 Announce Type: new Abstract: Recent image editing models have achieved strong visual fidelity but often struggle with tasks requiring complex reasoning. To investigate and enhance t
arXiv:2506.05199v3 Announce Type: replace Abstract: A core task in embodied intelligence is ego-centric 3D visual grounding. Existing methods typically adopt two-stage, heterogeneous pipelines that pa
arXiv:2512.08323v2 Announce Type: replace Abstract: Teeth landmark detection is a key task in modern orthodontics, supporting advanced diagnosis, personalized treatment planning, and effective monitor
arXiv:2604.25259v1 Announce Type: new Abstract: Traffic signal control (TSC) plays a central role in reducing congestion and maintaining urban mobility. This dissertation introduces DGLight, a critic-
arXiv:2603.29844v2 Announce Type: replace-cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). Howeve
arXiv:2510.19669v4 Announce Type: replace Abstract: Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility
arXiv:2604.25209v1 Announce Type: new Abstract: Dimensionality reduction methods such as UMAP and t-SNE are central tools for visualising high-dimensional data, but their local-neighborhood objectives
arXiv:2604.25050v1 Announce Type: new Abstract: Unlike chatbots, physical AI must act while the world keeps evolving. Therefore, the inter-chunk pause of synchronous executors are fatal for dynamic ta
arXiv:2604.25794v1 Announce Type: cross Abstract: Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in
arXiv:2604.25098v1 Announce Type: cross Abstract: While current Large Language Models (LLMs) exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), their massive parameter
arXiv:2604.24978v1 Announce Type: new Abstract: Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We
arXiv:2604.24997v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation requires assigning pixel-level semantic labels while supporting an open and unrestricted set of categories. Traini
arXiv:2604.24972v1 Announce Type: new Abstract: Clinical abnormality grounding for rare diseases is often hindered by data scarcity, making supervised fine-tuning impractical and single-pass inference
arXiv:2604.25554v1 Announce Type: cross Abstract: Collision-free motion is often aided by tactile and proximity sensors distributed on the body of the robot due to their resistance to occlusion as opp
arXiv:2603.16877v2 Announce Type: replace Abstract: Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a
arXiv:2604.24876v1 Announce Type: new Abstract: Text guided 3D medical image segmentation offers a flexible alternative to class based and spatial prompt based models by allowing users to specify regi
arXiv:2604.25499v1 Announce Type: new Abstract: Time series classification is an important analytical task across diverse domains. However, its practical application is often hindered by the scarcity
arXiv:2604.25885v1 Announce Type: cross Abstract: Graph neural networks such as ParticleNet and transformer based networks on point clouds such as ParticleTransformer achieve state-of-the-art performa
arXiv:2601.22154v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However
arXiv:2604.25135v1 Announce Type: new Abstract: Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environme
arXiv:2410.02082v4 Announce Type: replace Abstract: We introduce Functional Group-Aware Representations for Small Molecules (FARM), a novel foundation model designed to bridge the gap between SMILES,
arXiv:2604.25847v1 Announce Type: cross Abstract: Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problem
arXiv:2604.25866v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, yet little is known about how emotion recognition is
arXiv:2604.25853v1 Announce Type: new Abstract: Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language
arXiv:2604.25466v1 Announce Type: new Abstract: Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing
arXiv:2604.25390v1 Announce Type: cross Abstract: Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity.
arXiv:2604.25314v1 Announce Type: new Abstract: Compositional text-to-image (T2I) generation requires a model to honour multiple sub-prompts that describe distinct image regions. Recent work shows tha