Knowledge catalogue
arXiv:2604.18831v1 Announce Type: new Abstract: Frame-wise semantic segmentation of indoor lidar scans is a fundamental step toward higher-level 3D scene understanding and mapping applications. Howeve
arXiv:2604.19259v1 Announce Type: new Abstract: Multi-class defect detection constitutes a critical yet challenging task in industrial quality inspection, where existing approaches typically suffer fr
For real agentic workloads (North), short-context calibration wasn't enough. We calibrated AWQ on long internal agentic traces (up to 64k tokens) and added token masking in llm-compressor to exclude r
arXiv:2604.19314v1 Announce Type: new Abstract: Recovering corrupted images is one of the most challenging problems in image processing. Among various restoration tasks, blind image deblurring has bee
arXiv:2604.18867v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their
Highlights: 👉 80.2% SWE-Bench Verified and 89.6% LiveCodeBench v6 👉 Agent Swarm executes up to 4,000 coordinated steps 👉 Native text, image, and video input with 79.4% MMMU-Pro 👉 Production-ready on t
INT3 compression with fused Metal kernels enables large language models to compute attention operations directly on compressed (INT3/INT4) key-value cache representations using custom GPU kernels that
In the early days of generative AI, building safe and reliable business tools took massive engineering effort and a high tolerance for trial and error. We helped solve that with Vertex AI, our trusted
arXiv:2601.11632v2 Announce Type: replace Abstract: Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insuff
arXiv:2604.19043v1 Announce Type: new Abstract: Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensi
arXiv:2604.19234v1 Announce Type: new Abstract: Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generativ
arXiv:2604.19292v1 Announce Type: cross Abstract: Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of b
arXiv:2604.19405v1 Announce Type: new Abstract: Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their gr
arXiv:2604.19404v1 Announce Type: cross Abstract: Traditional policy learning methods in cooperative pursuit face fundamental challenges in biomimetic underwater robots, where long-horizon decision ma
arXiv:2604.18970v1 Announce Type: new Abstract: We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produce
arXiv:2510.08145v2 Announce Type: replace Abstract: Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach p
arXiv:1902.07683v1 Announce Type: cross Abstract: Over the past 15 years, the volume, richness and quality of data collected from the combined social networking platforms has increased beyond all expe
arXiv:2604.19567v1 Announce Type: new Abstract: Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However,
arXiv:2604.18827v1 Announce Type: cross Abstract: Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to mode
arXiv:2510.16822v3 Announce Type: replace-cross Abstract: Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated mon
arXiv:2601.18027v2 Announce Type: replace Abstract: LLM agents are increasingly used for social simulation, yet emotion is often treated as a transient cue, causing emotional amnesia and weak long-hor
Will Dunham / Reuters: Sony AI says its autonomous ping pong robot is the first robot to attain expert-level performance in a physical sport after beating some top-level human players — An autonomous
arXiv:2604.19372v1 Announce Type: cross Abstract: Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downs
arXiv:2604.19245v1 Announce Type: cross Abstract: Repair, an important resource for resolving trouble in human-human conversation, remains underexplored in human-LLM interaction. In this study, we inv
arXiv:2604.18718v1 Announce Type: cross Abstract: Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear w
Kimi K2.6 is now available for use on Together AI's cloud platform, which offers AI model deployment and inference services. This announcement indicates the model has been added to Together AI's roste
arXiv:2604.19221v1 Announce Type: new Abstract: Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like
arXiv:2604.18627v1 Announce Type: new Abstract: Ensuring human safety is of paramount importance in warehouse environments that feature mixed traffic of human workers and autonomous mobile robots (AMR
arXiv:2604.19270v1 Announce Type: new Abstract: As groups of robots increasingly collaborate with humans, understanding how humans perceive them is critical for designing effective human-robot teams.
Succeeding in the agentic era requires a transformation in your data strategy: moving from human-scale to agent-first workloads, evolving from reactive intelligence to proactive action, and shifting f
arXiv:2604.19206v1 Announce Type: new Abstract: The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely ha
Ads Advisor is an agentic conversational experience built with Gemini in Google Ads designed to help maximize performance based on business goals. The tool can help users get personalized answers, und
arXiv:2604.01798v2 Announce Type: replace Abstract: Breast cancer is a highly heterogeneous disease with diverse molecular profiles. The PAM50 gene signature is widely recognized as a standard for cla
arXiv:2604.17258v1 Announce Type: new Abstract: Deploying a humanoid robot to manipulate a new object has traditionally required one to two days of effort: data collection, manual annotation, 3D model
arXiv:2604.17046v1 Announce Type: new Abstract: Collisions between cyclists and pedestrians at urban intersections remain a persistent source of injuries, yet few systems attempt real-time warnings to
This guide from Databricks covers data transformation techniques and best practices essential for preparing data for AI/ML projects, addressing workflows that both data engineers and data scientists e
arXiv:2604.18562v1 Announce Type: new Abstract: Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single
arXiv:2604.16675v1 Announce Type: new Abstract: Action recognition is a fundamental ability for social species. Yet, its underlying computations are not well understood. Classical psychophysical studi
arXiv:2604.05983v2 Announce Type: replace-cross Abstract: We present Arch (AI-native Register-transfer Clocked Hardware), a hardware description language for micro-architecture specification and AI-as
arXiv:2604.17439v1 Announce Type: new Abstract: Recently computer vision has seen advancements mainly thanks to Transformer-based models. However many non-Transformer methods are still doing well bein
arXiv:2604.18194v1 Announce Type: cross Abstract: Drifting Models [Deng et al., 2026] train a one-step generator by evolving samples under a kernel-based drift field, avoiding ODE integration at infer
arXiv:2604.17020v1 Announce Type: new Abstract: Static benchmarks for harmful content detection face limitations in scalability and diversity, and may also be affected by contamination from web-scale
arXiv:2604.16370v1 Announce Type: new Abstract: Decoding natural language from non-invasive electroencephalography (EEG) remains fundamentally limited by low signal-to-noise ratio and restricted infor
arXiv:2604.17927v1 Announce Type: new Abstract: Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, curr
arXiv:2604.17959v1 Announce Type: new Abstract: Expressive Human Pose and Shape Estimation (EHPS) plays a crucial role in various AR/VR applications and has witnessed significant progress in recent ye
arXiv:2604.18076v1 Announce Type: new Abstract: Diffusion-based image synthesis has emerged as a promising source of synthetic training data for AI-based object detection and classification. In this w
arXiv:2604.16364v1 Announce Type: cross Abstract: Health systems are rapidly deploying large language models (LLMs) that use clinical notes for clinical decision support applications. However, modern
arXiv:2604.16892v1 Announce Type: new Abstract: Domain generalization (DG) aims to maintain performance under domain shift, which in computer vision appears primarily as stylistic variations that caus
arXiv:2604.16742v1 Announce Type: cross Abstract: Scientists have long sought to accurately predict outcomes of real-world events before they happen. Can AI systems do so more reliably? We study this
arXiv:2604.18122v1 Announce Type: new Abstract: Decision-making is a cognitively intensive task that requires synthesizing relevant information from multiple unstructured sources, weighing competing f
arXiv:2604.16459v1 Announce Type: cross Abstract: Fault intensity diagnosis (FID) plays a pivotal role in intelligent manufacturing while neglecting dependencies among target classes hinders its pract
arXiv:2604.18201v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for a wide range of vision tasks, including text-guided image generation and editing. In this work, we e
arXiv:2604.17718v1 Announce Type: new Abstract: Many benchmarks show that large language models can answer direct questions about culture. We study a different question: do they also change how they s
arXiv:2604.18508v1 Announce Type: cross Abstract: Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying
arXiv:2503.14324v3 Announce Type: replace-cross Abstract: The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressi
arXiv:2604.17211v1 Announce Type: new Abstract: We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied av
arXiv:2511.14846v2 Announce Type: replace-cross Abstract: Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and ver
arXiv:2511.17171v4 Announce Type: replace Abstract: Predicting wildfire risk is a reasoning-intensive spatial problem that requires the integration of visual, climatic, and geographic factors to infer
arXiv:2603.07690v2 Announce Type: replace Abstract: Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams,
arXiv:2604.16758v1 Announce Type: new Abstract: We present a system for automated detection, localization, and scoring of arrow punctures on 40,cm indoor archery target faces, trained on only 48 annot