Knowledge catalogue
arXiv:2510.05057v2 Announce Type: replace-cross Abstract: A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and d
arXiv:2604.09737v1 Announce Type: cross Abstract: Structured prediction requires models to generate ontology-constrained labels, grounded evidence, and valid structure under ambiguity, label skew, and
Starburst Data Inc. today introduced an artificial intelligence capability designed to let business users query and analyze enterprise data using natural language, positioning the offering as a shift
arXiv:2604.10286v1 Announce Type: new Abstract: Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability s
Cursor offers a pre-built automation template in its marketplace that helps developers investigate Sentry issues more efficiently. The template, accessible at cursor.com/marketplace/automations/invest
arXiv:2604.11757v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents. However, the VLA landsc
arXiv:2604.09839v1 Announce Type: new Abstract: Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in output behavior. It has als
arXiv:2604.10910v1 Announce Type: new Abstract: 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-ag
Manifest is a tool or platform that has added support for Ollama Cloud, enabling users to route AI model inference to cloud-hosted Ollama instances rather than relying solely on local GPU resources. T
arXiv:2604.05549v2 Announce Type: replace Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team
arXiv:2604.10527v1 Announce Type: cross Abstract: Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or refer
arXiv:2604.09562v1 Announce Type: cross Abstract: Efficient LLM serving must balance throughput and latency across diverse, bursty workloads. We introduce StreamServe, a disaggregated prefill decode s
arXiv:2601.15671v2 Announce Type: replace-cross Abstract: Designing cycling infrastructure requires balancing the competing needs of diverse user groups, yet designers often struggle to anticipate how
The Supabase blog post covers how Supabase developed and open-sourced the Stripe Sync Engine — an open-source tool that uses Stripe webhooks to keep a Postgres database of billing data in sync with St
arXiv:2604.11479v1 Announce Type: new Abstract: As global political tensions rise and the anticipation of additional tariffs from the United States on international trade increases, the issues of econ
arXiv:2604.10371v1 Announce Type: new Abstract: This study proposes Structural Gating and Effect-aligned Discovery for Temporal Causal Discovery (SGED-TCD), a novel and general framework for lag-resol
arXiv:2604.10516v1 Announce Type: new Abstract: Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-
arXiv:2604.04415v2 Announce Type: replace Abstract: Human understanding of video dynamics is typically grounded in a structured mental representation of entities, actions, and temporal relations, rath
arXiv:2604.11089v1 Announce Type: new Abstract: Image tokenizers are central to modern vision models as they often operate in latent spaces. An ideal latent space must be simultaneously compact and ge
arXiv:2604.11637v1 Announce Type: new Abstract: 4D point cloud videos capture rich spatial and temporal dynamics of scenes which possess unique values in various 4D understanding tasks. However, most
arXiv:2506.18831v2 Announce Type: replace Abstract: Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and re
arXiv:2509.20868v2 Announce Type: replace-cross Abstract: Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and cont
Sub-32B open weights models now offer GPT-5 level intelligence with Qwen3.5 27B (Reasoning) matching GPT-5 (medium) at 42 and Gemma 4 31B (Reasoning) matching GPT-5 (low) at 39 on the Artificial Analy
arXiv:2601.12038v3 Announce Type: replace Abstract: Dung's abstract argumentation frameworks model acceptability solely in terms of an attack relation, thereby conflating two conceptually distinct asp
arXiv:2603.21942v2 Announce Type: replace-cross Abstract: We introduce Suiren-1.0, a family of molecular foundation models for the accurate modeling of diverse organic systems. Suiren-1.0 comprising t
arXiv:2604.09759v1 Announce Type: cross Abstract: Transformers achieve state-of-the-art performance in natural language processing, vision, and scientific computing, but demand high computation and me
arXiv:2604.11530v1 Announce Type: cross Abstract: Vision-Language Models (VLM) have revolutionized multimodal learning by jointly processing visual and textual information. Yet, they face significant
arXiv:2604.10228v1 Announce Type: new Abstract: Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this
arXiv:2604.11716v1 Announce Type: new Abstract: Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep an
arXiv:2604.10000v1 Announce Type: new Abstract: Precise medical image segmentation is fundamental for enabling computer aided diagnosis and effective treatment planning. Traditional models that rely s
arXiv:2511.17925v3 Announce Type: replace-cross Abstract: Recent advances in whole-body robot control have enabled humanoid and legged robots to perform increasingly agile and coordinated motions. How
arXiv:2501.07773v3 Announce Type: replace Abstract: Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The existing g
arXiv:2604.03723v2 Announce Type: replace Abstract: Controlling both camera motion and object dynamics is essential for coherent and expressive video generation, yet current methods typically handle o
arXiv:2604.11797v1 Announce Type: new Abstract: We present SyncFix, a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. SyncFix formulates r
arXiv:2511.06101v3 Announce Type: replace-cross Abstract: Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored
arXiv:2604.11563v1 Announce Type: cross Abstract: Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- s
arXiv:2603.01420v2 Announce Type: replace Abstract: This work presents a finite element-guied physics-informed learning framework for multiphysics problems with coupled partial differential equations
arXiv:2508.02204v4 Announce Type: replace Abstract: Adept manipulation of articulated objects is essential for robots to operate successfully in human environments. Such manipulation requires both eff
arXiv:2604.09693v1 Announce Type: cross Abstract: Falls are a major cause of injury and mortality among older adults, yet most incidents occur in private indoor environments where monitoring must bala
arXiv:2604.11498v1 Announce Type: new Abstract: Fine-grained human action recognition (FHAR) is challenging because visually similar actions differ by subtle spatio-temporal cues. Many recent systems
arXiv:2604.10727v1 Announce Type: cross Abstract: Classical information-theoretic generalization bounds typically control the generalization gap through KL-based mutual information and therefore rely
arXiv:2604.11184v1 Announce Type: cross Abstract: Context: Software engineering (SE) researchers increasingly study Generative AI (GenAI) while also incorporating it into their own research practices.
arXiv:2509.04123v2 Announce Type: replace Abstract: Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods stru
arXiv:2604.10912v1 Announce Type: new Abstract: Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise,
arXiv:2604.10582v1 Announce Type: new Abstract: Tracking-Any-Point (TAP) models aim to track any point through a video which is a crucial task in AR/XR and robotics applications. The recently introduc
arXiv:2504.04099v2 Announce Type: replace-cross Abstract: Large Vision-Language Models have demonstrated remarkable capabilities, yet they suffer from hallucinations that limit practical deployment. W
arXiv:2604.10849v1 Announce Type: cross Abstract: Federated learning (FL) performance is highly sensitive to heterogeneity across clients, yet practitioners lack reliable methods to anticipate how a f
arXiv:2511.05782v2 Announce Type: replace Abstract: Unsupervised domain adaptation for medical image segmentation remains a significant challenge due to substantial domain shifts across imaging modali
arXiv:2604.10720v1 Announce Type: new Abstract: Artificial models that simulate how learners act and respond within educational systems are a promising tool for evaluating tutoring strategies and feed
arXiv:2604.10895v1 Announce Type: cross Abstract: For a robot to be called socially intelligent, it must be able to infer users internal states from their current behaviour, predict the users future b
arXiv:2507.22767v3 Announce Type: replace-cross Abstract: Obtaining human-readable symbolic formulas via genetic programming-based symbolic distillation of a deep neural network trained on a target da
arXiv:2305.14299v3 Announce Type: replace-cross Abstract: Learning high quality sentence embeddings from dialogues has drawn increasing attentions as it is essential to solve a variety of dialogue-ori
arXiv:2501.06786v2 Announce Type: replace Abstract: With the rapid growth of dynamic vision sensor (DVS) data, constructing a low-energy, efficient data retrieval system has become an urgent task. Has
arXiv:2604.11529v1 Announce Type: new Abstract: Foundation models have transformed natural language processing and computer vision, and a rapidly growing literature on time-series foundation models (T
Tencent's HunyuanWorld is an open-source multimodal 3D world generation model from the Tencent Hunyuan team, featuring 360° immersive experiences via panoramic world proxies, mesh export capabilities
arXiv:2603.28287v2 Announce Type: replace Abstract: Despite the growing need for data of more and more sophisticated 3D reconstruction pipelines, we can still observe a scarcity of suitable public dat
Tesla Insurance update With the latest version of Safety Score (v3.0), every mile you drive with FSD Supervised enabled will receive a score of 100. This allows you to maintain a higher average safety
arXiv:2604.10180v1 Announce Type: cross Abstract: Disaggregation maps parts of an AI workload to different types of GPUs, offering a path to utilize modern heterogeneous GPU clusters. However, existin
arXiv:2604.11025v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have begun to support Thinking with Images by invoking visual tools such as zooming and cropping during
arXiv:2604.09781v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit strong visual reasoning capabilities, yet they still struggle with 3D understanding. In particular, VLMs often fai