Knowledge catalogue
arXiv:2604.23036v1 Announce Type: cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fra
Safe tokenization is a security feature that helps prevent prompt injection attacks by ensuring that user inputs are properly processed and isolated from system instructions. Fireworks AI discusses ho
arXiv:2604.24356v1 Announce Type: cross Abstract: What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate o
arXiv:2604.24517v1 Announce Type: new Abstract: Robust forecast aggregation combines the predictions of multiple information sources to perform well in the worst case across all possible information s
arXiv:2604.23514v1 Announce Type: cross Abstract: The health condition of components in civil infrastructures can be described by various discrete states according to their performance degradation. In
arXiv:2602.11079v3 Announce Type: replace-cross Abstract: We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datap
arXiv:2604.24642v1 Announce Type: new Abstract: The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to rel
arXiv:2604.22868v1 Announce Type: cross Abstract: Visual planning represents a crucial facet of human intelligence, especially in tasks that require complex spatial reasoning and navigation. Yet, in m
Enterprise AI orchestration has become the defining challenge of the agentic era — not because the models aren’t ready, but because most enterprises aren’t. The whole software stack is being reimagine
arXiv:2604.23333v1 Announce Type: cross Abstract: Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability
arXiv:2604.23099v1 Announce Type: cross Abstract: Evaluating generative AI models is increasingly resource-intensive due to slow inference, expensive raters, and a rapidly growing landscape of models
arXiv:2604.24154v1 Announce Type: cross Abstract: The Universal Approximation Theorem (UAT) guarantees universal function approximation but does not explain how residual models distribute approximatio
arXiv:2604.24295v1 Announce Type: new Abstract: Inefficient driving behaviors, such as overly conservative yielding, remain a key obstacle to deployment of autonomous vehicles (AVs). Instantaneous dri
arXiv:2604.23974v1 Announce Type: new Abstract: Fake news generally refers to false information that is spread deliberately to deceive people, which has detrimental social effects. Existing fake news
arXiv:2604.23238v1 Announce Type: cross Abstract: Frontier models push the boundaries of what is learnable at extreme computational costs, yet distillation via sampling reasoning traces exposes closed
arXiv:2604.24126v1 Announce Type: new Abstract: Automatic depression detection from conversational interactions holds significant promise for scalable screening but remains hindered by severe data sca
arXiv:2604.24674v1 Announce Type: new Abstract: Radar offers unique advantages for localization in unstructured environments, including robustness to weather, lighting, and airborne particulates. Whil
arXiv:2604.23407v1 Announce Type: cross Abstract: Large vision-language models (VLMs) can recognize extit{what} happens in video but fail to count extit{how many} times. We introduce extbf{PushupBench
NASA officially delayed Artemis III to no earlier than 2027 in December 2024 , with the launch currently targeted for Q2 2027 . The mission will launch crew on the Space Launch System (SLS) rocket car
In an indication of how rapidly the world of artificial intelligence is evolving, Amazon Web Services Inc. today unveiled an expanded portfolio of offerings designed to move agentic AI up the software
Lenny Rachitsky / Lenny's Newsletter: Q&A with Evan Spiegel on why distribution is the most important moat in consumer tech, investing in Specs, 2026 as a “crucible” moment for Snap, and more — Snap's
Ben Thompson / Stratechery: Q&A with Sam Altman and AWS CEO Matt Garman about OpenAI's new partnership with AWS, Bedrock Managed Agents, Trainium chips, and more — As I noted yesterday, today's Strate
Open-source vector database startup Qdrant Solutions GmbH today announced three new enterprise-grade capabilities on its cloud service to address performance, availability and compliance requirements
arXiv:2604.24021v1 Announce Type: new Abstract: We explore a central question in AI for mathematics: can AI systems produce original, nontrivial proofs for open research problems? Despite strong bench
arXiv:2604.24052v1 Announce Type: cross Abstract: Video-to-text summarization remains underexplored in terms of comprehensive evaluation methods. Traditional n-gram overlap-based metrics and recent la
arXiv:2503.05587v3 Announce Type: replace-cross Abstract: Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustne
arXiv:2604.22891v1 Announce Type: cross Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, qu
arXiv:2604.22760v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly operate as autonomous agents that reason over external APIs to perform complex tasks. However, their reliabi
arXiv:2604.24597v1 Announce Type: cross Abstract: We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using qua
arXiv:2604.23972v1 Announce Type: cross Abstract: Knowledge graphs (KGs) are increasingly used to support large lan guage model (LLM) reasoning, but standard triplet-based KGs treat each relation as g
arXiv:2604.23720v1 Announce Type: new Abstract: Metanetworks are neural architectures designed to operate directly on pretrained weights to perform downstream tasks. However, the parameter space serve
arXiv:2604.23922v1 Announce Type: cross Abstract: In this paper, we introduce the Quasi-Quadratic Gradient (QQG), a novel search direction designed to accelerate the BFGS method within the quasi-Newto
arXiv:2604.23816v1 Announce Type: cross Abstract: Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand compl
arXiv:2510.11541v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge so
arXiv:2604.23702v1 Announce Type: new Abstract: Humanoid robots operating in human-centered environments (e.g., homes, hospitals, and offices) must mitigate foot--ground impact transients, as impact-i
Five months in, I think I've decided that I don't want to vibecode — I want professionally managed software companies to use AI coding assistance to make more/better/cheaper software products that the
Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query. — OpenAI Codex base_instruct
arXiv:2604.24543v1 Announce Type: new Abstract: RGB-Thermal (T) crowd counting aims to integrate visible-spectrum and thermal infrared information to improve the robustness of crowd density estimation
arXiv:2603.19670v3 Announce Type: replace Abstract: Nonasymptotic diffusion analyses often decompose sampling error into score estimation, continuous reverse-time propagation, discretization, and term
arXiv:2604.22755v1 Announce Type: cross Abstract: Reliable decision support in nuclear engineering requires traceable, domain-grounded knowledge retrieval, yet safety and risk analysis workflows remai
arXiv:2604.24230v1 Announce Type: new Abstract: Skull-base meningiomas are often characterized by favorable long-term prognosis, yet their anatomical complexity and proximity to critical neurovascular
arXiv:2604.23681v1 Announce Type: cross Abstract: A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers,
arXiv:2604.24278v1 Announce Type: cross Abstract: Automatic speech recognition systems often produce confident yet incorrect transcriptions under noisy or ambiguous conditions, which can be misleading
arXiv:2604.23190v1 Announce Type: cross Abstract: Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of config
arXiv:2604.23644v1 Announce Type: cross Abstract: Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as
arXiv:2604.22800v1 Announce Type: cross Abstract: Motivation: Structural Biologists have contributed more than 245,000 experimentally determined three-dimensional structures of biological macromolecul
Together AI announced the availability of NVIDIA Nemotron-3 Nano Omni models to developers on day zero of release, enabling early access to these multimodal AI models through their platform. The annou
ComfyUI has announced the arrival of ComfyStudio, a new development or feature release for their platform. This announcement was shared via a Substack blog post and promoted through their official X (
arXiv:2604.23685v1 Announce Type: new Abstract: Accurate text recognition in low-light environments is essential for intelligent systems in applications ranging from autonomous vehicles to smart surve
Replit, a collaborative coding platform, is promoting weekend coding projects or hackathons to encourage developers to build applications. The post likely invites users to engage with Replit's tools a
arXiv:2604.23696v1 Announce Type: new Abstract: Haptic feedback has been a long-missed feature in robotic-assisted surgery, one that would allow surgeons to perceive tissue properties and apply contro
arXiv:2604.24628v1 Announce Type: new Abstract: Proprietary design in commercial windrow-detection systems restricts transparency and limits progress in open autonomous forage-harvesting research. We
arXiv:2602.07096v2 Announce Type: replace-cross Abstract: Reliable financial reasoning requires knowing not only how to answer, but also when an answer cannot be justified. In real financial practice,
arXiv:2603.18563v2 Announce Type: replace Abstract: As autonomous AI agents increasingly mediate online platform markets, a fundamental question emerges: do these markets generate stable strategic out
arXiv:2408.00923v2 Announce Type: replace-cross Abstract: This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by fram
arXiv:2604.22898v1 Announce Type: cross Abstract: Autonomous systems increasingly operate under partial observability where execution-relevant state is never fully accessible. Existing governance mech
arXiv:2604.22911v1 Announce Type: new Abstract: Humanoid robots operating in unstructured environments must recover from unexpected disturbances-a capability that remains challenging for end-to-end co
arXiv:2604.22758v1 Announce Type: cross Abstract: Recently, at Xiaohongshu, the rapid expansion of e-commerce and advertising demands real-time business analytics with high accuracy and low latency. T
arXiv:2604.24334v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation (RAG) chunking methods often create excessive redundancy, increasing storage costs and slowing retrieval. This s
arXiv:2604.24218v1 Announce Type: cross Abstract: As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models