Knowledge catalogue
arXiv:2605.07970v1 Announce Type: cross Abstract: We define susceptibilities as a measure of the response of an observable quantity of a parameterized statistical model to a perturbation of the data f
In April 2026, researchers disclosed CVE-2026-31431 ('Copy Fail'), a highly reliable local privilege escalation vulnerability allowing unprivileged attackers to escalate to root across virtually all m
arXiv:2605.07505v1 Announce Type: new Abstract: Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device
arXiv:2605.07640v1 Announce Type: cross Abstract: Remote sensing lithology interpretation is fundamental to geological surveys, mineral exploration, and regional geological mapping. Unlike general lan
arXiv:2605.06676v1 Announce Type: cross Abstract: Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compress
arXiv:2508.16571v4 Announce Type: replace Abstract: In this paper, we describe and benchmark a competitor-discovery component used within an agentic AI system for fast drug asset due diligence. A comp
arXiv:2605.06839v1 Announce Type: cross Abstract: Autonomous experimentation has transformed microscopy and materials discovery by enabling closed-loop optimization including imaging and spectroscopy
arXiv:2605.07723v1 Announce Type: cross Abstract: Large language models (LLMs) are known to generate plausible but false information across a wide range of contexts, yet the real-world magnitude and c
arXiv:2605.06915v1 Announce Type: new Abstract: Modern AI systems are being deployed in complex domains such as medicine, science, and law, where it is important that they not only produce correct ans
arXiv:2605.08083v1 Announce Type: new Abstract: Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during infe
// LLMs Improving LLMs // Interesting progress the past of couple of weeks around self-improving AI agents. If autoresearch was interesting, you will like this read. (bookmark it) We've been hand-tuni
arXiv:2605.05615v2 Announce Type: replace Abstract: Large language models (LLMs) impose rapidly growing energy demands, creating an emerging energy and carbon crisis driven by large-scale inference. S
Local open-weight AI on a laptop has been improving more than twice as fast as Moore's Law! Between May 2024 and May 2026, the most expensive MacBook Pro you could buy stayed at 128 GB of unified memo
arXiv:2605.06959v1 Announce Type: cross Abstract: This paper presents a parametric solution to piecewise linear regression through the Adaptive Block Gradient Descent (ABGD) algorithm. The heart of th
arXiv:2605.07213v1 Announce Type: new Abstract: Infrared small target detection (IRSTD) remains challenging due to the scarcity of useful target cues and the presence of severe background clutter. Mos
Reachy Mini Wireless is a new robotic product announcement, likely featuring wireless connectivity capabilities and representing an advancement in the Reachy robot line. The announcement was made by C
arXiv:2605.06809v1 Announce Type: new Abstract: Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are
arXiv:2601.21424v3 Announce Type: replace-cross Abstract: Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and in
lowkey the funniest videos of the batch. thinky has some comedians!! congrats to @thinkymachines on reviving the omnimodel dream that others could not Today we're sharing our work on interaction model
arXiv:2603.12647v2 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. H
LTX-2.3 is a multimodal video generation model released by Lightricks in March 2026, available in four checkpoint variants including a distilled variant that completes generation in as few as 8 denois
arXiv:2605.05225v2 Announce Type: replace-cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP)
arXiv:2605.07342v1 Announce Type: cross Abstract: Compile-pass rate is the dominant evaluation signal for LLM code generation, yet for multi-component domain-specific artifacts it can be actively misl
arXiv:2605.06933v1 Announce Type: new Abstract: Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in quantum compu
arXiv:2603.06811v3 Announce Type: replace Abstract: With many organizations struggling to gain value from AI deployments, pressure to evaluate AI in an informed manner has intensified. Status quo AI e
arXiv:2602.03797v2 Announce Type: replace Abstract: We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general manifolds. Th
In this post, we build a multimodal retrieval system for aerospace manufacturing documents using Amazon Nova Multimodal Embeddings on Amazon Bedrock and Amazon S3 Vectors. We evaluate the system on 26
arXiv:2605.07835v1 Announce Type: new Abstract: Multi-robot systems in automated warehouses must manage continuous streams of pickup-and-delivery tasks while ensuring efficiency and safety. Prior work
arXiv:2507.21183v5 Announce Type: replace-cross Abstract: As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with
arXiv:2605.05949v2 Announce Type: replace Abstract: Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's
arXiv:2605.07280v1 Announce Type: cross Abstract: Leveraging deep learning for causal discovery in time series remains challenging because existing neural methods predominantly rely on component-wise
arXiv:2605.07178v1 Announce Type: new Abstract: Remote sensing change detection is pivotal for urban monitoring, disaster assessment, and environmental resource management. Yet, unimodal deep learning
arXiv:2605.06623v1 Announce Type: cross Abstract: Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orch
arXiv:2602.20974v2 Announce Type: replace Abstract: In engineering design and scientific computing, computational cost and predictive accuracy are intrinsically coupled. High-fidelity simulations prov
arXiv:2605.07600v1 Announce Type: cross Abstract: Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, canno
arXiv:2605.07147v1 Announce Type: cross Abstract: The ecosystem of Lean and Mathlib has become the de facto standard for large language model (LLM) assisted formal reasoning with remarkable successes
arXiv:2605.07841v1 Announce Type: cross Abstract: Decentralized machine learning often relies on outsourcing computations, such as gradient evaluations, to untrusted worker nodes. Existing robust aggr
arXiv:2605.07850v1 Announce Type: cross Abstract: With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to depl
arXiv:2605.07646v1 Announce Type: cross Abstract: While explicit reasoning trajectories enhance model interpretability, existing paradigms often rely on monolithic chains that lack intermediate verifi
Maye Musk on Elon: He wants to leave the world in a better place than he found it “People often misunderstand Elon. He’s not motivated by money or fame—he’s motivated by the idea of improving humanity
arXiv:2605.06894v1 Announce Type: cross Abstract: Machine learning (ML) in real-world systems must contend with concept drift, adversarial actors, and a spectrum of potential features with varying cos
arXiv:2605.06169v1 Announce Type: cross Abstract: Scaling Diffusion Transformers (DiTs) to hundreds of layers introduces a structural vulnerability: networks can enter a silent, mean-dominated collaps
arXiv:2605.07345v1 Announce Type: new Abstract: Mean-pooled cosine similarity is the default metric for comparing neural representations across languages, modalities, and tasks. We establish that this
arXiv:2605.07847v1 Announce Type: new Abstract: As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behav
arXiv:2509.03738v4 Announce Type: replace-cross Abstract: We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fix
arXiv:2605.07305v1 Announce Type: cross Abstract: Most existing LLM diagnoses are evaluated on static, single-turn settings where complete patient information is provided upfront, an oversimplificatio
arXiv:2605.07058v1 Announce Type: cross Abstract: Real-world clinical diagnosis is a complex process in which the doctor is required to obtain information from both interaction with the patient and co
arXiv:2605.06727v1 Announce Type: new Abstract: We introduce a hybrid quantum-classical pipeline, based on neutral-atom reservoir computing, for medical image classification, focusing on the binary cl
arXiv:2605.07919v1 Announce Type: new Abstract: Medical vision--language models (VLMs) are usually evaluated on intact image--question pairs, but trustworthy clinical use requires a stronger property:
Replit's Parallel Agents feature enables users to run up to 10 agents simultaneously, with each agent operating on its own independent copy of an application to accelerate development and task complet
Managing a modern database fleet is both a scale and cognitive problem. As database estates grow, the effort required to monitor, troubleshoot, and optimize them often outpaces teams’ capacity, who fi
arXiv:2605.06903v1 Announce Type: cross Abstract: Large language models are now embedded in everyday writing workflows, making reliable AI-generated text detection important for academic integrity, co
arXiv:2605.07877v1 Announce Type: new Abstract: Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating
arXiv:2605.07594v1 Announce Type: new Abstract: Existing memory systems for embodied agents typically inject retrieved memory as static context at episode start, a paradigm we term Ahead-of-time Monol
arXiv:2605.07242v1 Announce Type: new Abstract: Agentic memory evolves across tasks into durable derived artifacts: summaries, cached outputs, embeddings, learned skills, and executable tool procedure
arXiv:2605.07721v1 Announce Type: cross Abstract: Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space
arXiv:2511.02805v2 Announce Type: replace-cross Abstract: LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compu
Michael Burry urged investors to scale back exposure to surging technology stocks, saying the current market environment has reached historically dangerous extremes reminiscent of prior speculative bu
arXiv:2602.06523v2 Announce Type: replace Abstract: Human Activity Recognition (HAR) on resource constrained wearables requires models that balance accuracy against strict memory and computational bud
arXiv:2605.06797v1 Announce Type: new Abstract: We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Frechet I