Knowledge catalogue
What a week! Here’s everything we shipped: — Gemini 3.1 Flash TTS, our latest text-to-speech model, featuring native multi-speaker dialogue and improved controllability and audio tags for more natural
arXiv:2604.14732v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for building embodied agents that ground perception and language into action.
arXiv:2604.14846v1 Announce Type: new Abstract: Retail theft costs the global economy over 100 billion annually, yet existing AI-based detection systems require expensive custom model training on prop
arXiv:2604.13448v1 Announce Type: new Abstract: Human-object interaction (HOI) detection aims to detect interactions between humans and objects in images. While recent advances have improved performan
arXiv:2604.13991v1 Announce Type: new Abstract: Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty es
Google Research uses AI models to turn microscope images into accurate 3D neuron shapes , and generating synthetic neuron geometries helps AI learn to better classify neurons by their shape, speeding
arXiv:2310.02540v2 Announce Type: replace Abstract: Classical machine learning models, such as linear models and tree-based models, are widely used in industry. These models are sensitive to data dist
arXiv:2604.13068v1 Announce Type: new Abstract: When do large language models decide to hallucinate? Despite serious consequences in healthcare, law, and finance, few formal answers exist. Recent work
arXiv:2506.20083v4 Announce Type: replace Abstract: Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, com
arXiv:2604.13634v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from fre
Yes, Ollama models can be used with the Codex app on Windows. Ollama supports all major operating systems, including Windows , and open models can be used with OpenAI's Codex CLI through Ollama — Code
arXiv:2405.19088v3 Announce Type: replace Abstract: Recent advancements in large multimodal language models have demonstrated remarkable proficiency across a wide range of tasks. Yet, these models sti
arXiv:2604.13413v1 Announce Type: new Abstract: Diffusion language models (DLMs) have emerged as a promising paradigm for large language models (LLMs), yet the non-deterministic behavior of DLMs remai
arXiv:2604.14044v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hinde
Introduction Advances in AI model-powered exploitation have demonstrated that general-purpose AI models can excel at vulnerability discovery, even without being purpose-built for the task. Eventually,
arXiv:2603.00192v2 Announce Type: replace Abstract: In healthcare, predictive models increasingly inform patient-level decisions, yet little attention is paid to the variability in individual risk est
arXiv:2604.13076v1 Announce Type: new Abstract: We investigate the robustness of value alignment via finetuning with synthetic documents, using animal compassion as a value that is both important in i
arXiv:2604.13271v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly applied to complex telecommunications tasks, including 3GPP specification analysis and O-RAN network troub
arXiv:2604.13071v1 Announce Type: new Abstract: We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Int
arXiv:2509.18847v3 Announce Type: replace-cross Abstract: Tool-augmented large language models (LLMs) are usually trained with supervised imitation or coarse-grained reinforcement learning that optimi
arXiv:2505.12600v3 Announce Type: replace-cross Abstract: We study the densest subgraph problem and its NP-hard densest at-most-k subgraph variant through the lens of learning-augmented algorithms. We
arXiv:2508.08791v3 Announce Type: replace Abstract: Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of eff
arXiv:2509.16445v2 Announce Type: replace Abstract: Enabling robotic assistants to navigate complex environments and locate objects described in free-form language is a critical capability for real-wo
arXiv:2509.25549v2 Announce Type: replace Abstract: Choroidal nevi are common benign pigmented lesions in the eye, with a small risk of transforming into melanoma. Early detection is critical to impro
Ethan Mollick reported that requesting Claude Opus 4.7 to write sestinas—a complex poetic form with strict structural requirements—frequently triggers the model's safety guardrails, suggesting the AI
arXiv:2512.01773v2 Announce Type: replace Abstract: The rise of generalist robotic policies has created an exponential demand for large-scale training data. However, on-robot data collection is labor-
arXiv:2604.13484v1 Announce Type: cross Abstract: Clustering and dimensionality reduction have been crucial topics in machine learning and computer vision. Clustering high-dimensional data has been ch
arXiv:2604.13733v1 Announce Type: new Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imper
arXiv:2604.13058v1 Announce Type: new Abstract: We introduce KMMMU, a native Korean benchmark for evaluating multimodal understanding in Korean cultural and institutional settings. KMMMU contains 3,46
arXiv:2604.13479v1 Announce Type: cross Abstract: Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly
LM Performance：Qwen3.6-35B-A3B outperforms the dense 27B-param Qwen3.5-27B on several key coding benchmarks and dramatically surpasses its direct predecessor Qwen3.5-35B-A3B, especially on agentic cod
The AI boom has hit across industries, and public sector organizations are facing pressure to accelerate adoption. At the same time, government institutions face distinct constraints around security,
⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agentic coding on par with models 10x its active size 📷 Strong multimodal perception an
arXiv:2604.14004v1 Announce Type: cross Abstract: Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization
arXiv:2601.15170v2 Announce Type: replace Abstract: The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult t
arXiv:2604.13328v1 Announce Type: new Abstract: Pathology reports serve as the definitive record for breast cancer staging, yet their unstructured format impedes large-scale data curation. While Large
arXiv:2604.13828v1 Announce Type: new Abstract: User simulators are essential for the scalable training and evaluation of interactive AI systems. However, existing approaches often rely on shallow use
arXiv:2510.07019v3 Announce Type: replace Abstract: Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recal
arXiv:2604.13206v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical instability has eme
arXiv:2604.13073v1 Announce Type: new Abstract: Modern multimodal large language models (MLLMs) generate fluent responses from interleaved text, image, audio, and video inputs. However, identifying wh
arXiv:2604.13175v1 Announce Type: new Abstract: Large language models can be aligned with human preferences through offline reinforcement learning (RL) on small labeled datasets. While single-objectiv
Qwen 3.6 is here, and open-source! Run it locally with improved agentic coding capabilities. Try it with Claude Code: ollama launch claude --model qwen3.6 Try it with OpenClaw: ollama launch openclaw
Qwen 3.6 Plus Preview is Alibaba's next-generation large language model released on March 30-31, 2026 , and the first open-weight variant was released following the February Qwen 3.5 series, prioritiz
انتهت حجة 'ما عندي كرت شاشة قوي عشان أشغل ذكاء اصطناعي محلي'. علي بابا نزلت موديل Qwen3.6 بهندسة MoE. حجمه الكلي 35B (يعطيك ذكاء عالي جداً)، لكن وقت الـ Inference يستهلك 3B فقط! يعني أداء Enterprise ع
arXiv:2604.05096v2 Announce Type: replace Abstract: Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptati
arXiv:2604.13213v1 Announce Type: cross Abstract: Rare events such as conformational changes in biomolecules, phase transitions, and chemical reactions are central to the behavior of many physical sys
arXiv:2604.13549v1 Announce Type: new Abstract: The conversion of 2D freehand sketches into 3D models remains a pivotal challenge in computer vision, bridging the gap between human creativity and digi
arXiv:2512.10696v2 Announce Type: replace-cross Abstract: Procedural memory enables large language model (LLM) agents to internalize 'how-to' knowledge, theoretically reducing redundant trial-and-erro
arXiv:2604.13602v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multi
arXiv:2604.13515v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) is a common post-training recipe. We conduct a controlled ablation ov
arXiv:2604.13861v1 Announce Type: new Abstract: This paper develops a unified Markov Decision Process (MDP) framework for optimising two recurring in-match decisions in T20 cricket namely batting orde
Sorry for the long wait, everyone! As I said, Qwen is going to keep open-sourcing! ⚡ Meet Qwen3.6-35B-A3B：Now Open-Source！🚀🚀 A sparse MoE model, 35B total params, 3B active. Apache 2.0 license. 🔥 Agen
arXiv:2604.13051v1 Announce Type: new Abstract: There is debate about whether LLMs can be conscious. We investigate a distinct question: if a model claims to be conscious, how does this affect its dow
arXiv:2604.13519v1 Announce Type: new Abstract: Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM
arXiv:2603.15620v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap prim
arXiv:2603.08639v2 Announce Type: replace Abstract: Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet moder
What you need to know about Opus 4.7 * Takes instructions literally * Better vision means improved computer use and producing slides and other visual artifacts * Optimized for large-scale real-world a
arXiv:2604.13349v1 Announce Type: new Abstract: Communication in Large Language Model (LLM)-based multi-agent systems is moving beyond discrete tokens to preserve richer context. Recent work such as L
arXiv:2604.13403v1 Announce Type: new Abstract: In-context learning (ICL) enables models to adapt to new tasks via inference-time demonstrations. Despite its success in large language models, the exte
1/5 When we saw our Reducer (=LLM judge component in Maestro, our agentic framework, that selects the best output from parallel agent runs) consistently picking gold patches, we were sure Claude Opus