Knowledge catalogue
ITBench-AA is a new benchmark developed by Artificial Analysis and IBM that evaluates frontier AI models on agentic enterprise IT tasks, with results showing that current leading models score below 50
Boston Tech Week featured a session hosted by Mason Dry and Sydney Runkle with the Blitzy AI team focused on building deep agents. The event was promoted via Luma Events and appears to be an education
It's crazy that this is even possible today. It inspired me to build my own self-improving coding agent with simple read, write, bash,... I already used the coding agent to build an entire production-
arXiv:2605.27288v1 Announce Type: cross Abstract: Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behav
arXiv:2605.26731v1 Announce Type: new Abstract: A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models n
arXiv:2605.26409v1 Announce Type: cross Abstract: Evaluating and mitigating a generative system's susceptibility to jailbreak attacks is critical to its safe deployment. Given the number of deployable
Nikkei Asia: Jensen Huang says Nvidia is spending 100B-150B annually on its Taiwan supply chain, up from 10B-15B four years ago, and will boost its Taiwan staff to 4,000 — TAIPEI — Nvidia is now spend
jesus, qwen3-tts is FANTASTIC. going for full local stt/tts/llm with parakeet, qwen3-tts, and gemma 4 via llama.cpp for my little robot. excite, excite! https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B
arXiv:2605.26636v1 Announce Type: cross Abstract: We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention
arXiv:2605.27102v1 Announce Type: new Abstract: Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predictin
arXiv:2605.26329v1 Announce Type: new Abstract: Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluat
arXiv:2605.26725v1 Announce Type: new Abstract: Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments.
arXiv:2605.26370v1 Announce Type: new Abstract: We present a method for jointly predicting instance-level roof segment masks together with three continuous geometric attributes -- building height, roo
arXiv:2605.26955v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed to users around the world, they are integrated into everyday tasks across diverse cultural c
arXiv:2605.27259v1 Announce Type: new Abstract: We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is t
arXiv:2511.14993v3 Announce Type: replace-cross Abstract: This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis.
arXiv:2605.26738v1 Announce Type: new Abstract: Human communication depends on implicit social signals where effectiveness is shaped by tone, context, and conversational norms rather than semantic con
arXiv:2605.26874v1 Announce Type: cross Abstract: LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes
KREA 2 Image, KREA's foundational image generation model trained from scratch with adjustable creativity and style parameters, has been integrated as a partner node within ComfyUI. This integration al
Krea is now built in to Hermes Agent as an image generation API provider, allowing your agent to use Krea 2: a new foundation model trained from scratch to balance aesthetic quality and fine control,
arXiv:2605.26947v1 Announce Type: new Abstract: Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt datase
arXiv:2605.26648v1 Announce Type: new Abstract: This paper presents L-Learning, a novel data-driven control framework for robotics that integrates Lyapunov stability theory with Lagrangian mechanics t
arXiv:2605.26717v1 Announce Type: cross Abstract: Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferen
arXiv:2509.18384v2 Announce Type: replace Abstract: Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other do
arXiv:2511.02360v4 Announce Type: replace-cross Abstract: Chain of Thought (CoT) reasoning enhances logical performance by decomposing complex tasks, yet its multimodal extension faces a trade-off. Th
arXiv:2605.27066v1 Announce Type: new Abstract: Understanding how events evolve over time is essential for search engines handling queries about trending news. We present QDET (Query-Driven Event Time
This newsletter episode covers major AI developments including Elon Musk's legal loss against OpenAI, updates announced at Google's I/O conference, and OpenAI's achievement in solving the Erdős discre
arXiv:2605.26797v1 Announce Type: cross Abstract: We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden st
latent space pod is still very underrated, especially on the applied side of things glad that they have kept it very high signal one of the few pods i listen to while working out and I always find mys
arXiv:2605.26612v1 Announce Type: new Abstract: Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization meth
arXiv:2603.03711v3 Announce Type: replace Abstract: Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source
arXiv:2505.21285v4 Announce Type: replace Abstract: This work proposes a framework LGKDE that learns kernel density estimation for graphs. The key challenge in graph density estimation lies in effecti
arXiv:2605.26168v1 Announce Type: cross Abstract: Linux is the foundation of the digital age, accounting for the majority of the cloud and mobile OS markets. Any device that runs Linux uses the Linux
arXiv:2605.26828v1 Announce Type: new Abstract: Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated
arXiv:2605.27063v1 Announce Type: new Abstract: The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node f
arXiv:2605.26850v1 Announce Type: new Abstract: Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matc
arXiv:2509.21552v2 Announce Type: replace-cross Abstract: Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task -- given a natural language instruction, generate
arXiv:2605.26271v1 Announce Type: cross Abstract: We study a nonlinear factor model in which observed responses depend on low-rank latent factors through an unknown monotone link function. This settin
arXiv:2605.26729v1 Announce Type: new Abstract: We present HICNet, a reference-guided exposure correction framework. A lightweight, content-agnostic encoder distills each image into a compact illumina
arXiv:2605.27209v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning,
arXiv:2605.26924v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Amo
arXiv:2605.27046v1 Announce Type: new Abstract: Motor thermal management is often overlooked in the context of electrically-actuated robots, particularly legged robots, but motor overheating is a key
arXiv:2601.03079v4 Announce Type: replace Abstract: Moral sensitivity is the most fundamental capability underlying human moral competence. Although many approaches aim to align large language models
arXiv:2605.27073v1 Announce Type: new Abstract: Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coord
arXiv:2603.27146v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals re
arXiv:2510.23486v2 Announce Type: replace Abstract: Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential de
arXiv:2605.27190v1 Announce Type: cross Abstract: Recent advances in Large Audio-Language Models (LALMs) have made real-time, streaming spoken interaction increasingly practical. In this setting, reas
arXiv:2512.01556v3 Announce Type: replace Abstract: Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs
arXiv:2601.12809v2 Announce Type: replace-cross Abstract: Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired,
arXiv:2605.26956v1 Announce Type: new Abstract: Entity linking is a key component of many downstream NLP systems, yet existing approaches are often tied to the specific target knowledge bases and doma
arXiv:2605.27028v1 Announce Type: cross Abstract: On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rol
arXiv:2605.27042v1 Announce Type: cross Abstract: As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of
arXiv:2605.26933v1 Announce Type: new Abstract: Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotatio
arXiv:2605.27136v1 Announce Type: new Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment.
arXiv:2506.11253v2 Announce Type: replace Abstract: Machine unlearning removes certain training data points and their influence from AI models (e.g., when a data owner revokes their consent to allow m
arXiv:2512.09700v3 Announce Type: replace Abstract: General-purpose object detectors face fundamental structural limitations when applied to ship detection in satellite imagery, where the ship scale d
arXiv:2605.26554v1 Announce Type: cross Abstract: Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in recommender systems and large languag
Lipdub (by Lightricks) Input a text prompt dialogue to dub/translate a characters speech. https://links.comfy.org/4v8Tr00 Obscura Remova (by WepeNerd) Used as occlusion removal, haze cleanup, foregrou
arXiv:2412.20505v2 Announce Type: replace Abstract: Participatory Urban Planning (PUP) is increasingly supported by LLM-based agents, yet existing methods largely rely on static preference elicitation
LiteParse 🤝 Rust🦀 We refactored the LiteParse library and CLI porting it to Rust, and here's what that means for you: ⚡ Parsing up to 100X faster, with sub-second processing for documents as large as