Knowledge catalogue
arXiv:2605.02900v1 Announce Type: cross Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, saf
arXiv:2605.03706v1 Announce Type: new Abstract: Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large l
arXiv:2503.06917v5 Announce Type: replace Abstract: We study zeroth-order optimization where solutions must minimize a cost d(s) while maintaining high probability under a complex generative prior L(s
arXiv:2605.03788v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time
Jen Judson / Bloomberg: Scale AI wins a 500M DOD contract through the Chief Digital and AI Office to help sift data and assist in decision-making, after receiving a 100M deal in 2025 — The Pentagon aw
arXiv:2601.04809v5 Announce Type: replace Abstract: Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on
arXiv:2510.09768v2 Announce Type: replace Abstract: We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger scales;
arXiv:2510.08150v3 Announce Type: replace Abstract: Unsupervised multi-source domain adaptation (UMDA) leverages labeled data from multiple source domains to generalize to an unlabeled target. While f
arXiv:2605.02617v2 Announce Type: new Abstract: Capturing semantic consistency among nodes is crucial for effective graph representation learning. Existing approaches typically rely on k-nearest neigh
arXiv:2605.01055v1 Announce Type: cross Abstract: Object caches underpin cloud and edge services, but production workloads are heterogeneous, nonstationary, and throughput-constrained. Recent simple n
arXiv:2604.06573v2 Announce Type: replace Abstract: A Grammatical Error Correction (GEC) system produces a sequence of edits to correct an erroneous sentence. The quality of these edits is typically e
arXiv:2605.02819v1 Announce Type: new Abstract: Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide st
arXiv:2602.03548v3 Announce Type: replace Abstract: Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in
Vercel introduced a security feature allowing marketplace credentials to be restricted to production-only access, preventing their use in development or preview environments. This enhancement helps pr
Scott Calvert / Wall Street Journal: Security camera companies are embracing AI to give customers detailed descriptions of surveillance footage that are often spot on but can also be wildly wrong — AI
Security training platform startup Herd Security Inc. today announced that it has raised 3 million in new funding to expand product development across new training categories in human resources and ar
Boris Cherny posted a casual message on X indicating he would see people the following day, likely referring to an upcoming event, meeting, or gathering he was planning to attend. Without additional c
This OpenAI social media post highlights how young builders and developers are leveraging AI tools to create projects and applications now that AI development has become more accessible to non-experts
arXiv:2605.00964v1 Announce Type: cross Abstract: Much research on LLMs has focused on increasing benchmark performance. However, the evaluation of such models in real-world collaborative human-AI wor
arXiv:2605.03723v1 Announce Type: new Abstract: The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity a
arXiv:2605.03226v1 Announce Type: new Abstract: Safety fine-tuning of language models typically requires a curated adversarial dataset. We take a different approach: score each candidate prompt's diff
arXiv:2605.03092v1 Announce Type: new Abstract: While sentiment analysis is the staple of financial NLP, capturing the nuances of 'why' behind that sentiment remains a challenge. There have been attem
SenseNova U1 is an open-source unified multimodal model that integrates understanding, reasoning, and generation within a single architecture, with particular strength in creating complex infographics
arXiv:2605.03666v1 Announce Type: new Abstract: This work proposes a novel control and estimation approach for aerial manipulation of a cable-suspended load using Unmanned Aerial Vehicles (UAVs). Comm
arXiv:2605.03443v1 Announce Type: new Abstract: This paper benchmarks classical machine learning and deep learning approaches for three-class sentiment classification of Indonesian Spotify reviews. Us
arXiv:2605.03189v1 Announce Type: new Abstract: Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While sev
arXiv:2605.00827v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP).
arXiv:2605.03701v1 Announce Type: new Abstract: Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Larg
arXiv:2605.02526v1 Announce Type: cross Abstract: Barrier certificates are scalar functions over the state space of dynamical systems that separate all unsafe states from all reachable states. The exi
arXiv:2605.01879v1 Announce Type: new Abstract: The challenge of engineering autonomous agents capable of navigating the stochastic and adversarial nature of the physical world has historically reside
arXiv:2605.03301v1 Announce Type: new Abstract: De-identification of clinical text remains essential for secondary use of electronic health records (EHRs), yet public benchmarks such as i2b2 2006/2014
arXiv:2507.00994v4 Announce Type: replace Abstract: Learning high-quality text representations is fundamental to a wide range of NLP tasks. While encoder pretraining has traditionally relied on Masked
arXiv:2605.03846v1 Announce Type: new Abstract: Designing an open-world quadrupedal loco-manipulation system is highly challenging. Traditional reinforcement learning frameworks utilizing exteroceptio
arXiv:2601.04025v2 Announce Type: replace Abstract: Advances in large language models (LLMs) enable many new innovations in education. However, evaluating the effectiveness of new technology requires
Singular Bank leverages OpenAI's ChatGPT and Codex to accelerate banking operations and developer productivity. The integration enables bankers and software engineers to streamline workflows, automate
arXiv:2512.16504v3 Announce Type: replace Abstract: The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition usin
small workflow note that adds up. /staged-pr is a skill (via slash command) i run when wrapping up a PR. it takes my staged code changes and drafts a concise PR title & description, based on my prefer
arXiv:2508.18983v3 Announce Type: replace Abstract: The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts pe
Jonathan Vanian / CNBC: Snap reports Q1 revenue up 12% YoY to 1.53B, in line with est., and says it ended its 400M Perplexity deal announced in November; SNAP drops 4%+ after hours — Snap shares dropp
so cute! It's pretty magical how kids interact with tech. They just expect it to work for them. Here's mine talking to Reachy Mini via Gemini Live API. I didn't tell them how, they just did it. That's
Elon Musk posted a statement expressing amazement at the vastness of space, reflecting on the immense scale and distances involved in the cosmos. The post likely emphasizes how difficult it is for hum
arXiv:2605.03842v1 Announce Type: cross Abstract: Robotic Mobile Fulfillment Systems (RMFS) rely on mobile robots for automated inventory transportation, coordinating order allocation and robot schedu
arXiv:2605.03371v1 Announce Type: new Abstract: Cross-scene hyperspectral image (HSI) classification stands as a fundamental research topic in remote sensing, with extensive applications spanning vari
arXiv:2604.04328v3 Announce Type: replace-cross Abstract: The evaluation of general-purpose artificial agents, particularly those based on LLMs, presents a significant challenge due to the non-transit
This post discusses practical frameworks for working with AI models, covering how context serves as infrastructure, taste functions as configuration, verification enables autonomous systems, and deleg
The Information: Source: Alphabet is in talks with Blackstone, KKR, and EQT to give their portfolio companies AI model access, after OpenAI's and Anthropic's JVs with PE firms — Private equity firms B
Rafe Rosner-Uddin / Financial Times: Sources: Blue Origin outlines a new employee stock plan to quell staff unrest and make its incentives more competitive with SpaceX — Rocket maker hopes to quell em
Bloomberg: Sources: Microsoft is considering delaying or dropping its 2030 goal of matching its hourly power use with renewable energy purchases, amid the data center boom — Microsoft Corp. may shelve
Lingling Wei / Wall Street Journal: Sources: the US and China are considering recurring talks on the security risks posed by AI models, with Scott Bessent leading the American side — Washington and Be
Enterprises are entering a new phase of cloud adoption where flexibility, control and performance are no longer trade-offs but requirements. As AI workloads become more distributed and data-intensive,
SpaceX is transitioning from the highly successful Falcon 9 rocket program toward the next generation as the Starship program enters its operational phase. SpaceX is preparing Starship V3, a larger an
SpaceX achieved a historic milestone by successfully landing Falcon rocket boosters 268 consecutive times, setting a new record for the longest streak of successful booster landings in the company's h
xAI: SpaceX signs an agreement with Anthropic to provide access to Colossus 1, and says Anthropic expressed interest in partnering for orbital compute capacity — SpaceXAI has signed an agreement with
SpaceX's Super Heavy Booster 19 was transported to the launch site for testing purposes, as documented in a post by Elon Musk on X. This represents progress in SpaceX's development of the Starship lau
SpaceX and xAI are exploring the concept of orbital datacenters positioned in space, which could potentially offer advantages such as reduced cooling requirements, proximity to satellite infrastructur
SpaceX's AI division (xAI) and Anthropic have expressed interest in partnering to develop orbital AI compute capacity at the gigawatt scale. This collaboration would involve deploying computational in
SpaceXAI will provide @AnthropicAI with access to Colossus 1, one of the world’s largest and fastest-deployed AI supercomputers, to provide additional capacity for Claude → http://x.ai/news/anthropic-
arXiv:2601.10931v2 Announce Type: replace Abstract: Tree canopy detection from aerial imagery is an important task for environmental monitoring, urban planning, and ecosystem analysis. Simulating real
arXiv:2605.03229v1 Announce Type: new Abstract: Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Spar
arXiv:2605.03874v1 Announce Type: new Abstract: Classification of EEG signals using shallow Convolutional Neural Networks (CNNs) is a prevalent and successful approach across a variety of fields. Most