Knowledge catalogue
arXiv:2606.02548v1 Announce Type: new Abstract: Word Error Rate (WER) is the dominant metric for automatic speech recognition (ASR), but it can overestimate errors when references and hypotheses encod
In the era of artificial intelligence, some companies have struggled to adopt artificial intelligence and others have pivoted to an AI framework that has yielded positive results. Snowflake Inc. this
This research note is based on four primary inputs: 1) An assessment of Snowflake Inc.’s announcements at this year’s Summit; 2) Information captured in private analyst and journalist sessions with Sn
arXiv:2606.00397v1 Announce Type: new Abstract: Soft wearable robotic systems have emerged as a promising solution for assisting individuals with reduced hand function. This paper presents SoFiE, a mo
arXiv:2606.01101v1 Announce Type: cross Abstract: The quadratic complexity of self-attention remains a bottleneck for Large Language Models (LLMs) processing ultra-long contexts. The Naive Bayes Cogni
Some of the most iconic consumer products -- Tide Pods, M&Ms, etc -- were born out of user research studies. LLMs democratize deep user research to every decision. Synthetic audiences will go even fur
Some of the most unhinged hate that I receive comes from other academics. The soldiers, the corrections officers, the truckers, and all those from the muscular classes (to borrow @VDHanson's term) see
ComfyUI, a node-based UI for Stable Diffusion, has announced an upcoming release or feature announcement scheduled for the following day, though specific details are not disclosed in the post title. T
arXiv:2606.00738v1 Announce Type: cross Abstract: Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-s
arXiv:2606.00015v1 Announce Type: cross Abstract: Operating Systems (OS) courses are among the most challenging in computer science education due to the complexity of internal structures and the diver
Gowri Gurumurthy / Bloomberg: Source: a CoreWeave-tied data center raised 900M via five-year junk bonds, priced at par to yield 7.5%, as the sector increasingly turns to high-yield bonds — A data cent
Jason Koebler / 404 Media: Source: Google asked Google Play app devs to join a “confidential content offer pilot”, offering to pay for access to codebases to use them to train AI tools — Google is try
Gary Marcus discusses the disconnect between venture capital hype surrounding AI's trillion-dollar potential and the practical realities of AI development and market viability. The article likely exam
Echo Wang / Reuters: Source: SpaceX plans to raise 75B in its IPO by selling 555.6M shares at 135 each, an unusual move since most companies set a price range before the roadshow — SpaceX plans to rai
Bloomberg: Sources: a Broadcom-backed portion of Apollo and Blackstone's $36B debt deal to buy TPUs for Anthropic to lease may yield ~5.75% vs. 8%-9% for a riskier portion — Broadcom Inc.'s promise to
Wired: Sources: after Trump nixed an AI EO on May 21, US officials are navigating internal strife and chaotic talks; early model access was the most contentious issue — Donald Trump killed an executiv
Cristina Criddle / Financial Times: Sources: Google DeepMind, Anthropic, and Meta have recently hired experts in psychology, ethics, and philosophy as they expand machine consciousness research — Goog
Bloomberg: Sources: the EU's €20B investment plan for five AI data centers is floundering, with delays and funding issues alienating some potential partners — SoftBank Announces €75 Bln AI Data Center
Southampton, England (June 1) — Henry Nowak’s father read a statement after his son’s killer was sentenced to 21 years in prison. Henry was arrested as he told police he had been stabbed & couldn’t br
Impulse Space Inc. today announced that it has closed a 500 million late-stage investment led by 137 Ventures and BANNER VC. The Series D round brings the company’s outside funding to over 1 billion.
arXiv:2512.04069v2 Announce Type: replace Abstract: Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required f
SpaceX has joined three other industry groups in calling on the FCC to adopt a nationwide policy to automatically unlock phones tied to a carrier’s network 180 days after activation. “Automatic mobile
arXiv:2606.02380v1 Announce Type: cross Abstract: As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment. However, in practical applications,
arXiv:2606.00593v1 Announce Type: cross Abstract: Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has imp
arXiv:2606.01479v1 Announce Type: new Abstract: Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet interpretable emotional control remai
arXiv:2601.00672v2 Announce Type: replace-cross Abstract: In this paper, we study the finite element operator network (FEONet), an operator-learning method for parametric problems, originally introduc
arXiv:2606.02374v1 Announce Type: new Abstract: Earth Observation (EO) has fundamentally transformed the monitoring of environmental processes and human activities up to planetary scale. Recent advanc
arXiv:2606.02441v1 Announce Type: new Abstract: Identity-preserving video generation (IPVG) aims to synthesize high-fidelity videos that follow text prompts while faithfully preserving a reference ide
arXiv:2606.01446v1 Announce Type: cross Abstract: Radio frequency spectrum awareness requires the ability to detect, localize, and characterize emitters in dense and contested wireless environments. I
arXiv:2606.01701v1 Announce Type: new Abstract: Geometric partitioning has attracted increasing attention by its remarkable motion field description capability in the hybrid video coding framework. Ho
arXiv:2606.01526v1 Announce Type: new Abstract: In multi-robot systems, maintaining persistent communication graph connectivity is often overly restrictive, especially when robots have limited communi
arXiv:2606.00572v1 Announce Type: new Abstract: Passenger count data from public transit systems reveals urban mobility patterns and is essential for planning, operation, and optimisation. However, no
arXiv:2606.00584v1 Announce Type: cross Abstract: This paper proposes Spectra-Guided Neural Tucker Factorization (SG-NTF) for High-Dimensional and Incomplete (HDI) tensor completion. Circumventing dis
arXiv:2606.02427v1 Announce Type: cross Abstract: Existing evaluations of neural operators and in-context operator learning rely primarily on prediction error, but accurate output prediction does not
arXiv:2606.02455v1 Announce Type: new Abstract: Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems. However, MD is inherently serial, which makes it difficul
arXiv:2512.00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to coll
arXiv:2605.25144v2 Announce Type: replace Abstract: Deformable medical image registration aligns anatomical structures across images but remains computationally dense at 3D resolution. Spiking neural
arXiv:2606.00120v1 Announce Type: cross Abstract: This paper proposes SpikeWFM, a novel hybrid architecture that integrates spiking neural networks (SNNs) with conventional artificial neural network (
arXiv:2606.01493v1 Announce Type: new Abstract: Reconstructing a photorealistic 3D face avatar from a single unconstrained photograph is challenging: feed-forward 3D Gaussian Splatting (3DGS) models d
arXiv:2606.00962v1 Announce Type: cross Abstract: Foundational agent interoperability standards, notably the Agent-to-Agent (A2A) protocol and the Model Context Protocol (MCP), have advanced multi-age
arXiv:2301.06308v2 Announce Type: replace-cross Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art perform
arXiv:2603.00963v2 Announce Type: replace-cross Abstract: While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unsta
arXiv:2602.05435v2 Announce Type: replace Abstract: While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimi
arXiv:2606.01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-va
arXiv:2606.01126v1 Announce Type: cross Abstract: Pruning is a process designed to reduce the number of weights in a large neural network. This can substantially speed up inference but might cause a c
// State-Externalizing Harnesses // A new paradigm is emerging on how to effectively build agents and harnesses. If there is a state that the environment can maintain reliably, it probably doesn't bel
arXiv:2606.00867v1 Announce Type: cross Abstract: Recent publications have suggested using the Shap- ley value for sensor anomaly/attack localization. We study the performance of such an approach by u
arXiv:2602.03970v3 Announce Type: replace-cross Abstract: We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. T
arXiv:2606.00758v1 Announce Type: cross Abstract: In recent years, graph signal processing has emerged as a powerful framework at the intersection of signal processing and graph theory, providing tool
arXiv:2606.00762v1 Announce Type: new Abstract: Autonomous target search is crucial for deploying Micro Aerial Vehicles (MAVs) in emergency response and rescue missions. Existing approaches either foc
arXiv:2606.00148v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often know the rule but pick the wrong answer: on abstract visual reasoning (AVR) tasks, a model can describe
Step-3.7-Flash is a compact language model from StepFun AI that reportedly achieves top-tier performance among models under 500 billion parameters on Hugging Face leaderboards, despite receiving limit
arXiv:2603.03031v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning
arXiv:2606.01787v1 Announce Type: new Abstract: A new class of asynchronous adaptive first-order optimization methods is introduced, comprising asynchronous variants of several popular algorithms. Ver
arXiv:2606.00312v1 Announce Type: cross Abstract: Over the past half-dozen years, stochastic rounding (SR) has regained significant attention as a quantization scheme for low-precision floating-point
arXiv:2410.02511v2 Announce Type: replace Abstract: With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing
arXiv:2602.06925v2 Announce Type: replace Abstract: Autonomous drone racing pushes the boundaries of high-speed motion planning and multi-agent strategic decision-making. Success in this domain requir
Nous Research announced improvements to token streaming functionality for the Hermes Agent on Telegram, enhancing the smoothness and performance of real-time token generation. This update likely addre
arXiv:2510.09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-i
arXiv:2606.00267v1 Announce Type: cross Abstract: Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot