Knowledge catalogue
arXiv:2606.00133v1 Announce Type: new Abstract: World models, internal simulators that learn the structure and dynamics of an environment, have emerged as a central paradigm in the pursuit of artifici
arXiv:2606.00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with
arXiv:2509.10114v2 Announce Type: replace Abstract: Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world envi
arXiv:2605.31080v1 Announce Type: cross Abstract: Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy
arXiv:2605.30989v1 Announce Type: new Abstract: Robot teleoperation enables safe, non-contact task execution in hazardous environments where direct human access is difficult, and its application has e
When you build agentic AI solutions, you face unique operational challenges. Agents make unpredictable decisions, costs spiral unexpectedly, and debugging non-deterministic failures seems impossible.
arXiv:2605.30604v1 Announce Type: cross Abstract: Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope across retrieval, tool calls, memory, findings, repo
arXiv:2605.30804v1 Announce Type: new Abstract: We audit six large language models (LLMs) for gender stereotyping across English, Korean, Chinese, and Japanese. Three were developed primarily for Engl
arXiv:2605.31256v1 Announce Type: new Abstract: Embodied Large Language Models (LLMs) are increasingly used as reasoning modules in robotic control pipelines to improve human-robot interaction, but th
Enterprise AI adoption at scale requires moving beyond large language models to implement agent logic systems that can handle complex reasoning, planning, and decision-making autonomously. Agent-based
arXiv:2501.04661v3 Announce Type: replace-cross Abstract: The web-scale of pretraining data has created an important evaluation challenge: to disentangle linguistic competence on cases well-represente
arXiv:2605.31264v1 Announce Type: new Abstract: LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and in
arXiv:2605.30842v1 Announce Type: new Abstract: Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this p
Connecting agents directly to Snowflake, Slack, or BigQuery via MCP/CLIs is a multi-token disaster. They default to brute-force exploration, firing 20-30 tool calls just to rediscover context on every
arXiv:2605.31494v1 Announce Type: new Abstract: Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by
NVIDIA Cosmos 3 is a frontier foundation model for physical AI that combines physical reasoning, world generation, and action generation within a single open model. The model uses a Mixture-of-Transfo
arXiv:2605.31149v1 Announce Type: cross Abstract: This study investigates how UX research (UXR) principles, combined with Large Language Model (LLM)-supported analysis, can be used to improve the qual
arXiv:2602.01267v2 Announce Type: replace Abstract: Kronecker adapters have emerged as a promising approach for fine-tuning large-scale models, enabling high-rank updates through tunable component str
arXiv:2605.31377v1 Announce Type: cross Abstract: Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods
arXiv:2510.17700v2 Announce Type: replace Abstract: Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deploym
arXiv:2605.30521v1 Announce Type: new Abstract: Large language models must frequently process untrusted inputs, such as judging an answer from another model or running tasks like spam and harm classif
arXiv:2605.31534v1 Announce Type: cross Abstract: Three-dimensional scene reconstruction depends on local image evidence that is both visually discriminative and geometrically useful. Fixed feature th
arXiv:2605.31064v1 Announce Type: cross Abstract: Large Language Models (LLMs) have significantly advanced online data services, particularly in the domain of financial question answering (FinQA). How
arXiv:2605.31277v1 Announce Type: cross Abstract: Traditional traffic analysis is being fundamentally challenged by the rapid adoption of encryption, tunnelling, and privacy-preserving protocols, whic
arXiv:2605.31352v1 Announce Type: new Abstract: Robotics manipulation usually assumes that the shape and pose of the object are known to the robot prior to motion planning. However, precise geometric
DeepAgents are AI systems designed to handle complex tasks through advanced reasoning and planning capabilities. The post outlines the key features that enable DeepAgents to excel at complicated probl
Nous Research announced native support for Hermes Agent on Windows, expanding the availability of their Hermes model to Windows-based systems. This development enables Windows users to run Hermes Agen
arXiv:2605.30745v1 Announce Type: new Abstract: Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. Howe
arXiv:2605.30917v1 Announce Type: cross Abstract: As large-scale visual-document corpora such as arXiv papers and enterprise PDFs continue to grow, visual-document retrieval has gained increasing atte
Intel Corp. today announced that more than 130 design engagements for its Series 3 processor family for edge artificial intelligence and edge computing designs and also unveiled a new open-source fram
arXiv:2605.30677v1 Announce Type: cross Abstract: Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files. This r
arXiv:2605.31343v1 Announce Type: new Abstract: Legged manipulators integrate exceptional terrain adaptability along with mobile manipulation capabilities, which make them highly promising for deploym
arXiv:2605.31167v1 Announce Type: new Abstract: Assessing whether Large Language Models outputs are factually grounded, epistemically calibrated, and methodologically reproducible is a prerequisite fo
arXiv:2507.16362v3 Announce Type: replace Abstract: Chinese License Plate Recognition (CLPR) faces numerous challenges in unconstrained and complex environments, particularly due to perspective distor
arXiv:2603.02630v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone
arXiv:2605.30794v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they re
arXiv:2605.30571v1 Announce Type: cross Abstract: Physical AI systems, including robots, autonomous vehicles, embodied agents and edge copilots, often run a different inference workload from cloud LLM
Nemotron 3 Ultra is NVIDIA's latest language model featuring significant improvements in speed (5X faster) and cost efficiency (30% cheaper) compared to previous versions, positioning it as a frontier
arXiv:2605.31116v1 Announce Type: new Abstract: Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compa
arXiv:2605.30544v1 Announce Type: new Abstract: Visual monitoring systems that rely on cloud-based AI inference expose raw image data to external services, creating fundamental tensions with the data-
arXiv:2605.31460v1 Announce Type: new Abstract: Reasoning-based robotic policies using large language and vision-language models achieve strong semantic planning capabilities but mostly suffer from a
arXiv:2605.31558v1 Announce Type: cross Abstract: Transformer-based language models are widespread in today's society. As such, understanding the mechanisms by which they solve structured tasks and pr
arXiv:2605.31196v1 Announce Type: cross Abstract: Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already co
arXiv:2605.31048v1 Announce Type: new Abstract: Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, a
arXiv:2511.03100v2 Announce Type: replace-cross Abstract: The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performa
arXiv:2605.30593v1 Announce Type: cross Abstract: Engine Health Management (EHM) depends on reliable forecasting of Remaining Useful Life (RUL) and on tracking thermal indicators such as turbine gas t
arXiv:2605.30698v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spo
arXiv:2605.31067v1 Announce Type: new Abstract: Open-set task execution can significantly benefit from seamlessly switching between coarse and fine scene representations depending on the context and t
arXiv:2603.20253v2 Announce Type: replace-cross Abstract: Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental reso
arXiv:2605.31075v1 Announce Type: new Abstract: Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, c
arXiv:2605.30628v1 Announce Type: cross Abstract: Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, n
arXiv:2602.01186v2 Announce Type: replace-cross Abstract: Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high
arXiv:2603.00068v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) systems impose substantial and growing environmental costs, yet transparency about these impacts has declined eve
arXiv:2602.02459v2 Announce Type: replace Abstract: Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action
arXiv:2605.30877v1 Announce Type: new Abstract: Large-scale Vision-Language-Action (VLA) pretraining is increasingly adopted as the foundation for robot policies, yet the evidence for pretrained VLAs
arXiv:2506.00175v5 Announce Type: replace-cross Abstract: Modern AI systems are typically developed through multiple stages-pretraining, fine-tuning rounds, and subsequent adaptation or alignment, whe
As artificial intelligence agents begin to proliferate across information technology infrastructure, IT leaders are moving away from asking, “How do we monitor every alert?” to “How do we design infra
arXiv:2605.29063v1 Announce Type: cross Abstract: The recursive quad-tree partitioning in High Efficiency Video Coding (HEVC) incurs considerable computational overhead, with exhaustive rate-distortio
arXiv:2605.28829v1 Announce Type: cross Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understan
arXiv:2605.29004v1 Announce Type: new Abstract: Reported retrieval scores for training-free shape descriptors conflate local signal design, normalization, aggregation, codebook fitting, and metric cho