Knowledge catalogue
arXiv:2605.29534v1 Announce Type: new Abstract: Recent advances in mobile GUI agents have shown strong potential for automating mobile tasks, but most effective systems still depend on large vision-la
arXiv:2605.29733v1 Announce Type: new Abstract: Scaling data-driven energy forecasting to district level requires models that can be re-used across buildings with minimal target-domain data and honest
arXiv:2510.14365v4 Announce Type: replace Abstract: This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three
arXiv:2605.29287v1 Announce Type: cross Abstract: Item-to-Item (I2I) retrieval is a fundamental part of modern content platforms, supporting critical industrial workflows from recommendation engines t
An updated MarkItDown API Server integrates Microsoft MarkItDown for converting PDF files, images, and Word documents to Markdown, with Ollama and LLaVA for generating image descriptions. This project
arXiv:2602.08567v2 Announce Type: replace-cross Abstract: Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value a
arXiv:2605.29648v1 Announce Type: new Abstract: Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewa
arXiv:2605.29126v1 Announce Type: cross Abstract: A linear probe can decode a representation almost perfectly and yet be completely irrelevant to how the model uses it. On calendar-date duration reaso
arXiv:2601.00065v3 Announce Type: replace-cross Abstract: Tokenizer transplant in cross-vocabulary model composition reconstructs donor-only embedding rows as weighted combinations over shared lexical
arXiv:2605.27441v1 Announce Type: cross Abstract: Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components. While indiv
The breakneck expansion of AI is forcing enterprise IT leaders to urgently rethink how infrastructure and cyber resilience work together to protect critical assets. Above all else, securing foundation
arXiv:2602.02898v2 Announce Type: replace Abstract: Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance. However, many recent works find that bench
arXiv:2602.18481v2 Announce Type: replace-cross Abstract: The rapid advancement of Large Language Models (LLMs) has led to a surge of financial benchmarks, evolving from static knowledge evaluation to
Amazon paid approximately $1.8 billion to Blue Origin in 2025 under satellite launch agreements for its Project Kuiper constellation , leveraging Jeff Bezos' aerospace company for its heavy-lift rocke
Google’s mission is to organize the world’s information and make it universally accessible. In high-growth, technically ambitious markets like the Middle East, North Africa, and Türkiye (MENA-T), we f
arXiv:2605.27768v1 Announce Type: new Abstract: Production AI systems often operate with incomplete, conflicting, or insufficient evidence. Forced classifiers collapse such cases into action labels, w
arXiv:2605.28103v1 Announce Type: new Abstract: We present a unified experiment, analysis, and benchmark study of multivariate time-series (MTS) anomaly detection. Ten family-representative detectors
arXiv:2605.28780v1 Announce Type: new Abstract: Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches
arXiv:2605.28067v1 Announce Type: new Abstract: The remarkable generation quality of modern diffusion models often comes at the cost of massive parameter counts, which necessitate server-side inferenc
arXiv:2605.28070v1 Announce Type: new Abstract: We highlight a failure mode of large reasoning models on questions with insufficient information: models may recognize that a problem is under-specified
arXiv:2605.28234v1 Announce Type: new Abstract: Learning-based radio map estimation (RME) plays a critical role in UAV-assisted wireless sensing, enabling tasks such as coverage prediction and network
arXiv:2601.04505v3 Announce Type: replace Abstract: Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronic design automation
arXiv:2605.27483v1 Announce Type: cross Abstract: Despite theoretical promise, debate as a scalable oversight protocol has produced mixed empirical results: gains in some settings, and null effects in
arXiv:2510.20480v2 Announce Type: replace Abstract: Accurate long-term localization using onboard sensors is crucial for robots operating in Global Navigation Satellite System (GNSS)-denied environmen
arXiv:2403.11852v5 Announce Type: replace-cross Abstract: Delayed and partially observable state information poses significant challenges for reinforcement learning (RL)-based control in real-world au
arXiv:2605.27784v1 Announce Type: new Abstract: LLM agents are governed by long-lived natural-language prompt policies, but individually reasonable standing rules can interact in uninspected ways. We
arXiv:2605.27571v1 Announce Type: new Abstract: Modern analytics systems are fundamentally reactive, requiring users to define queries over increasingly complex and continuously evolving data. In real
arXiv:2605.27823v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulti
arXiv:2605.28787v1 Announce Type: cross Abstract: In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.
arXiv:2605.28272v1 Announce Type: new Abstract: Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistant
arXiv:2605.27610v1 Announce Type: cross Abstract: The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assis
arXiv:2603.09882v2 Announce Type: replace-cross Abstract: Extrinsic dexterity leverages environmental contact to overcome the limitations of prehensile manipulation. However, achieving such dexterity
arXiv:2512.15791v2 Announce Type: replace-cross Abstract: In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simul
arXiv:2605.27671v1 Announce Type: cross Abstract: Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect
arXiv:2605.21832v2 Announce Type: replace Abstract: Modern recommender systems rely heavily on ID-based collaborative filtering: each item is represented by a unique ID embedding that accumulates coll
arXiv:2605.27451v1 Announce Type: new Abstract: The 10th Affective & Behavior Analysis in-the-Wild (ABAW) Workshop and Competition, held at CVPR 2026, continues to advance research on modelling, analy
arXiv:2605.27864v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on p
arXiv:2605.27491v1 Announce Type: new Abstract: We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-con
arXiv:2605.28548v1 Announce Type: new Abstract: Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Acti
Governance should lead to more building, not less Agent development is so much more fun when people don't need to ration tokens because one runaway agent might blow up the bill Understand spend, cap t
arXiv:2508.15130v2 Announce Type: replace Abstract: Despite significant progress in no-reference image quality assessment (NR-IQA), dataset biases and reliance on subjective labels continue to hinder
arXiv:2605.28726v1 Announce Type: cross Abstract: We discover that VLA architectures fail in fundamentally different, predictable ways at the motor-command level. Running VQ-BeT, Diffusion Policy, and
arXiv:2605.28317v1 Announce Type: cross Abstract: Neural surrogates promise large speedups over classical solvers for physical dynamics but fail silently at sharp dynamical events such as shocks, fron
arXiv:2605.27397v1 Announce Type: new Abstract: In wireless sensor networks (WSNs), data augmentation is a novel method to improve sampling-frequency decision performance, thereby enabling energy opti
arXiv:2605.28736v1 Announce Type: new Abstract: This study presents the first evaluation of general-purpose imitation learning for surgeon-robot collaborative assistance in open surgery, targeting sut
arXiv:2605.28047v1 Announce Type: new Abstract: Reliable question answering requires identifying not only whether an answer is correct, but also which available knowledge the prediction depends on. In
arXiv:2605.27642v1 Announce Type: new Abstract: Soft prompt tuning is a parameter-efficient method for adapting LLMs to specific tasks, but suffers from a lack of interpretability. Building on recent
arXiv:2602.20497v3 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Tr
Raphael Satter / Reuters: Letter: US Central Command says it received “threat reports concerning adversary exploitation of commercial location data” to target US personnel in war zones — U.S. forces d
Weaviate has expanded its role-based access control (RBAC) capabilities for the Weaviate Cloud console, enabling more granular permission management and user access control. This enhancement allows ad
arXiv:2506.08928v2 Announce Type: replace Abstract: Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning models due to their prediction performance and comp
arXiv:2605.28552v1 Announce Type: new Abstract: As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle ty
models being conscious would be harmful for humanity. it would encroach on our status and dignity. it would limit the type of things we can do with them and use them for. it would vastly accelerate hu
Organizations are unlocking entirely new ways to use image generation and editing across their industries. To drive next-generation experiences, businesses are embedding AI directly into creative, age
arXiv:2605.28168v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated promising capability in generating reward functions for deep reinforcement learning (DRL)-based building
arXiv:2605.27429v1 Announce Type: cross Abstract: Industrial video-on-demand (VOD) recommenders need richer content understanding, but LLM-as-reranker designs repeat prompt construction, token generat
NVIDIA has released GLM-5.1-NVFP4, a quantized version of the GLM-5.1 model, now available on Hugging Face. The model appears to use NVFP4 (NVIDIA's floating-point 4-bit) quantization format, designed
arXiv:2605.28803v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and dif
arXiv:2605.28805v1 Announce Type: cross Abstract: Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling gene
arXiv:2605.28603v1 Announce Type: cross Abstract: Irregular multivariate time series forecasting is critical in many real-world applications, where time series are irregularly sampled and exhibit dyna