Knowledge catalogue
I shipped something I've been building for the last few weeks : phantom-kv , a refusal-removal system for large language models that doesn't touch a single weight. Instead of editing the model, it loa
arXiv:2609.19928v1 Announce Type: new Abstract: Per-user LLM inference on transaction histories binds the inference budget linearly to user count, which becomes prohibitive at applied scale. We re-cas
arXiv:2609.17042v1 Announce Type: new Abstract: Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented
arXiv:2608.30556v1 Announce Type: new Abstract: Path-finding over knowledge graphs has become an effective way to ground LLM reasoning on multi-hop questions. However, biomedical QA introduces two dis
Introduction Beginning in 2024 Mandiant investigated a string of compromises affecting Brazilian financial services, retail, and eCommerce organizations. Google Threat Intelligence Group (GTIG) tracks
arXiv:2607.13683v2 Announce Type: replace Abstract: Large Language Models (LLMs) have enabled capable agents across diverse applications. Beyond the foundation model, the performance of an agent is go
arXiv:2601.15297v3 Announce Type: replace Abstract: Reliable question answering over long institutional documents requires more than topical retrieval: a system must localize the exact passage that su
Email security startup AegisAI Inc. today said it has raised 36 million in new funding to counter a fast-growing class of artificial intelligence-generated email attacks that no amount of employee tra
arXiv:2607.12397v1 Announce Type: new Abstract: LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste i
Oratomic Inc., a quantum computing startup, has raised 300 million in early-stage funding to scale its quantum hardware and accelerate its path to fault tolerance and error correction, creating the ne
This post likely critiques the SpaceX IPO process, suggesting that only major financial institutions acting as underwriters benefit substantially from the offering while retail investors and others ar
arXiv:2606.06363v1 Announce Type: new Abstract: Urban green-space extraction from ultra-high-resolution (UHR) imagery is commonly performed patch by patch, which limits semantic reuse among spatially
arXiv:2404.07977v4 Announce Type: replace Abstract: We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-
arXiv:2601.03728v3 Announce Type: replace-cross Abstract: Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text, offering substant
arXiv:2605.01393v1 Announce Type: new Abstract: Motion forecasting often requires trading interpretability for predictive accuracy. Standard anchor-based architectures rely on opaque latent queries th
Enterprise customer experience platform provider Netomi Inc. today announced it has raised 110 million in new funding to expand its agentic artificial intelligence platform and accelerate deployment a
arXiv:2604.22067v1 Announce Type: cross Abstract: Psychiatric intake is a sequential, high-stakes information-gathering process in which clinicians must decide what to ask, in what order, and how to i
Jagmeet Singh / TechCrunch: Truecaller faces mounting pressure as growth slows in India, its largest market, while telcos, Apple, and Google roll out caller ID and spam-blocking features — Truecaller
arXiv:2610.09517v1 Announce Type: new Abstract: Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describing d
CrowdStrike report: https://www.crowdstrike.com/en-us/blog/unknown-threat-actor-uses-artex-to-target-south-korean-finance/ From: Andrew Curran on 𝕏: https://x.com/AndrewCurran_/status/2108108695876092
arXiv:2609.39820v1 Announce Type: cross Abstract: Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with
In March, Janice Malone began getting calls about suspicious activity from her nonprofit organization, Vivian's Door. Vivian's Door, headquartered in Alabama, typically provided training, resources, a
arXiv:2609.31314v1 Announce Type: new Abstract: Cytopathology detection requires open-vocabulary recognition because cellular categories are fine-grained, long-tailed, and continuously evolving across
In this post, we walk through how Huntington built a scalable AWS solution to detect and redact Personally Identifiable Information (PII) and Payment Card Industry (PCI) data from over 400 million doc
arXiv:2605.27843v1 Announce Type: new Abstract: An important challenge in texture recognition is the limited amount of data for training frequently found in real-world applications. In computer vision
arXiv:2605.09038v1 Announce Type: new Abstract: Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especia
This post discusses Graph RAG, an approach that uses local LLMs with Ollama to build graph-based knowledge indexes from source documents by deriving entity knowledge graphs and pregenerating community
In support of our mission to accelerate the developer journey on Google Cloud, we built Dev Signal: a multi-agent system designed to transform raw community signals into reliable technical guidance by
Protecting capital in today's markets requires immense speed and precision. A financial analyst preparing a deal memo works across licensed market data, internal models, and confidential client files.
arXiv:2608.22610v1 Announce Type: new Abstract: Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for
arXiv:2608.22526v1 Announce Type: new Abstract: We introduce RS^3-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmen
arXiv:2608.21572v1 Announce Type: new Abstract: Consider a typical test of a robot system: one observes a sequence of outcomes concerning some aspect of interest (crash or no crash, tracking error, ti
In support of our mission to accelerate the developer journey on Google Cloud, we built Dev Signal: a multi-agent system designed to transform raw community signals into reliable technical guidance by
Qonto uses Claude through Bedrock in customer-facing financial agents; Anthropic reports faster transfers and invoice creation.
arXiv:2609.02074v1 Announce Type: new Abstract: Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based
Let’s review the ChatGPT Finance feature👀 TLDR - I don’t think most people need this in its current state. Example financial institutions you can connect into via Plaid: - American Express - Bank of A
BBVA reported 11,000 ChatGPT Enterprise licences in May 2025, with 83% daily usage and self-reported 2.8 hours saved weekly.
The financial services industry (FSI) operates under a unique set of non-negotiable requirements: the need for strict regulatory compliance, sub-millisecond transactional speeds, and security that ver
arXiv:2606.30067v1 Announce Type: cross Abstract: We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces. Instead of treating
This guide addresses updated regulatory requirements for model risk management in banking institutions, likely covering the 2026 revisions to interagency guidance issued by banking regulators. It prov
Aroon Deep / The Hindu: Source: Meta has a system in India to “automatically restrict content, at scale” to meet local law, massively expanding the country's censorship powers — India is now part of a
arXiv:2609.29709v1 Announce Type: cross Abstract: An LLM judge scores a bank of responses against a rubric, and the reliability comes back at 0.52. What has been measured? Judge evaluation has begun b
arXiv:2609.27452v1 Announce Type: cross Abstract: AI agents are beginning to make real payments. Current approaches let an agent pay by relying on a credential provider that, in the approaches deploye
arXiv:2609.13667v1 Announce Type: new Abstract: Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings,
arXiv:2609.04775v1 Announce Type: new Abstract: Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency and inference efficiency. Traditional sampling algorith
arXiv:2603.18718v2 Announce Type: replace Abstract: Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrie
arXiv:2608.02880v1 Announce Type: cross Abstract: As lifelong learning agents accumulate lifelong growing skill banks, retrieving the correct skill becomes an increasingly important bottleneck. Most c
arXiv:2607.21673v1 Announce Type: cross Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynam
arXiv:2607.21731v1 Announce Type: new Abstract: Transformers are widely used across many domains, including natural language processing, computer vision, web search, and DNA sequence analysis. Given t
Tecban deployed Copilot to business and engineering teams. Tecban reported 5,808 hours saved per year through AI in 11 cases, in a Microsoft customer story.
arXiv:2610.12602v1 Announce Type: cross Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part
Auto-generated synthesis of 3157 entries about techmeme
arXiv:2610.00544v1 Announce Type: new Abstract: Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits requires training samples that capt
Hugging Face Inc. is exploring a sale that could value the artificial intelligence model repository at 13 billion or more, Business Insider reported today. The company has brought in a bank to sound o
arXiv:2608.14029v1 Announce Type: new Abstract: Multimodal dialogue retrieval aims to retrieve dialogues from multimodal dialogue banks that are similar to a target dialogue in terms of both textual s
arXiv:2608.08958v1 Announce Type: cross Abstract: Tree Search-based test-time scaling of LLMs is a powerful tool for automated scientific coding. However, pure Tree Search sometimes struggles with sys
arXiv:2607.26060v1 Announce Type: new Abstract: LLM-based chatbots are transforming customer service in regulated domains such as banking, but scalable and cost-effective validation remains a critical
arXiv:2607.01935v1 Announce Type: new Abstract: Long term memory lets LLM agents act as persistent assistants, but user facts change. A useful memory system must know what is true now, what used to be
arXiv:2601.16632v4 Announce Type: replace-cross Abstract: Time series forecasting has witnessed significant progress with deep learning. While prevailing approaches enhance forecasting performance by
arXiv:2606.25007v1 Announce Type: new Abstract: Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams -- transactions, login sessions, risk signals