Knowledge catalogue
arXiv:2605.19374v1 Announce Type: cross Abstract: Vision-language alignment using chest X-rays and radiology reports has emerged as an advanced paradigm for zero-shot classification and grounding of c
arXiv:2605.19373v1 Announce Type: cross Abstract: All 26 neural network merge strategies we tested including weight averaging, SLERP, TIES, DARE, Fisher merging, and evolutionary approaches -- fail th
arXiv:2605.19418v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM ag
arXiv:2605.19024v1 Announce Type: cross Abstract: Split conformal prediction provides finite-sample marginal coverage under exchangeability, but this guarantee averages over the random calibration sam
arXiv:2512.14700v2 Announce Type: replace-cross Abstract: Online harassment is a widespread social and public health concern, yet most computational approaches for detecting and addressing harassment
Context compression isn't new in RAG. Our contribution is making it query-aware, citation-preserving, and fast enough for orchestration. Read the full research blog: https://research.perplexity.ai/art
arXiv:2603.11673v2 Announce Type: replace Abstract: Many physical systems exhibit a low-dimensional structure that varies with external parameters: link lengths in a robot, forcing constants in a flui
arXiv:2605.19314v1 Announce Type: cross Abstract: Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become s
arXiv:2605.19735v1 Announce Type: cross Abstract: Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on larg
arXiv:2602.03454v3 Announce Type: replace Abstract: Despite recent progress in vision-language models (VLMs), existing approaches often fail to generate personalized responses based on the user's spec
arXiv:2603.17305v2 Announce Type: replace Abstract: We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness aga
arXiv:2605.19667v1 Announce Type: cross Abstract: In this paper, we study a consensus-based optimization method for nonconvex bi-level optimization, where the objective is to minimize an upper-level f
arXiv:2102.11840v2 Announce Type: replace Abstract: In recent years, artificial neural networks have developed into a powerful tool for addressing a multitude of problems for which classical solution
arXiv:2605.20075v1 Announce Type: cross Abstract: Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm
arXiv:2605.19120v1 Announce Type: new Abstract: We present CosFly, a box-structured planning and multimodal simulation pipeline for aerial tracking, together with CosFly-Track, a large-scale UAV datas
‼️ Could large language models turn out to be the tech industry’s Vietnam? All In’s @jason notes below that today’s students are speaking out against AI, just as students in the 60s and 70s spoke out
arXiv:2605.19092v1 Announce Type: cross Abstract: Reasoning systems increasingly separate intermediate computation into private and public channels, creating evaluation cases that look similar in tran
arXiv:2605.18916v1 Announce Type: cross Abstract: We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining
arXiv:2605.19750v1 Announce Type: new Abstract: Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation. Despite their strong generative capabili
arXiv:2605.19075v1 Announce Type: cross Abstract: Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video arc
arXiv:2605.19665v1 Announce Type: cross Abstract: Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond
arXiv:2505.11628v4 Announce Type: replace Abstract: Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed fo
arXiv:2510.13293v3 Announce Type: replace Abstract: While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degra
arXiv:2605.19299v1 Announce Type: new Abstract: The exponential growth of big data has intensified the need for efficient and interpretable machine learning models that can handle diverse data charact
arXiv:2605.18897v1 Announce Type: cross Abstract: Intracranial EEG (iEEG) provides high-fidelity neural recordings essential for clinical and brain-computer interface applications, but acquiring these
arXiv:2605.19666v1 Announce Type: cross Abstract: Accurate cardiac output (CO) estimation from photoplethysmography (PPG) is promising for unobtrusive hemodynamic monitoring, but remains difficult sin
arXiv:2605.19656v1 Announce Type: new Abstract: We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by sat
arXiv:2605.06501v2 Announce Type: replace-cross Abstract: Since its introduction in 2017, the Transformer has become one of the most widely adopted architectures in modern deep learning. Despite exten
Curated AI ecosystems are becoming the defining architecture of enterprise AI. The shift does not announce itself with spectacle. It shows up in procurement decisions, architecture diagrams and the sl
current agent systems coordinate through conversations and workflows. Active Graph explores what happens when agents coordinate through evolving shared state instead this proposal suggests that long-r
arXiv:2605.19484v1 Announce Type: cross Abstract: While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workfl
arXiv:2605.19690v1 Announce Type: new Abstract: Navigation Foundation Models (NFMs) trained on large cross-embodied datasets have demonstrated powerful generalizability in various scenarios. Adopting
arXiv:2605.19210v1 Announce Type: new Abstract: Convexity is a fundamental geometric prior that underlies many natural and man-made structures, yet remains challenging to impose effectively in end-to-
arXiv:2605.18810v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffus
arXiv:2605.20036v1 Announce Type: new Abstract: Ride-hailing platforms like DiDi Chuxing operate in highly dynamic environments where balancing driver supply and passenger demand is critical. Although
arXiv:2605.19887v1 Announce Type: cross Abstract: Current Physical AI (PAI) relies heavily on closed-loop visual-servoing pipelines, whose perception and planning stages may become computationally int
arXiv:2605.18868v1 Announce Type: cross Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversari
Data centers aren’t stealing your water. Even if the total water draw of data centers triples by 2030, they’d require just 8% of the water consumed by American golf courses. @dodgeblake interviewed @A
arXiv:2602.09259v2 Announce Type: replace Abstract: In robot-assisted minimally invasive surgery (RMIS), reduced haptic feedback and depth cues increase reliance on expert visual perception, motivatin
arXiv:2511.13588v2 Announce Type: replace-cross Abstract: Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data
arXiv:2511.12158v3 Announce Type: replace Abstract: Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audi
arXiv:2605.18892v1 Announce Type: cross Abstract: Federated learning (FL) enables collaborative learning of computer vision models, where privacy and regulatory constraints prevent centralizing data a
Databricks partnered with the Good and Virtue Foundation to leverage data and technology solutions that connect medical volunteers with critical health services across 72 countries. The collaboration
Bot and agent trust management company DataDome SAS today launched Priority Protect, a virtual waiting room product designed to sort human shoppers, authorized artificial intelligence agents and malic
Release: datasette-agent-charts 0.1a1 More color! Bar and waffle charts without a color column are shaded by magnitude with a sequential color scheme; color columns holding text values use the observa
arXiv:2605.19605v1 Announce Type: new Abstract: Forests worldwide are increasingly threatened by climate change and disturbances such as fire, pests, and pathogens, creating an urgent need for scalabl
arXiv:2605.18773v1 Announce Type: cross Abstract: Traditional facility management often relies on centralized decision-making structures that limit stakeholder participation, leading to misalignment w
arXiv:2605.19737v1 Announce Type: cross Abstract: Digital Twin (DT) technology holds immense potential for surgical planning and personalized medicine. However, generating interactive, patient-specifi
arXiv:2605.19099v1 Announce Type: new Abstract: We introduce DecisionBench, a benchmark substrate for emergent delegation in long-horizon agentic workflows. The substrate fixes a task suite (GAIA, tau
arXiv:2601.12707v2 Announce Type: replace Abstract: Estimating the unknown reward functions driving agents' behaviors is of central interest in inverse reinforcement learning and game theory. To tackl
arXiv:2605.19270v1 Announce Type: new Abstract: Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such
arXiv:2603.29382v2 Announce Type: replace-cross Abstract: Lightweight cryptographic primitives are widely deployed in resource-constrained environments, particularly in Internet of Things (IoT) device
arXiv:2105.00933v3 Announce Type: replace-cross Abstract: The task of efficient automatic music classification is of vital importance and forms the basis for various advanced applications of AI in the
arXiv:2605.19021v1 Announce Type: new Abstract: Deep Graph Neural Networks (GNNs) are essential for capturing complex dependencies in graph-structured data. However, scaling GNNs to depth remains chal
arXiv:2605.19892v1 Announce Type: cross Abstract: Dramatic cost reductions driven by private sector innovations have led to a rapid increase in the number of satellites in orbit and a corresponding su
deepagents v0.6 ships w/ support for code interpreters! these are the perfect happy medium between pure tool execution and heavyweight sandboxes they give your agent an environment where it can... → k
arXiv:2605.19294v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while
arXiv:2605.18855v1 Announce Type: cross Abstract: Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cros
arXiv:2605.19557v1 Announce Type: cross Abstract: We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under
arXiv:2602.00545v2 Announce Type: replace Abstract: The eigenvalue distribution of the Hessian matrix plays a crucial role in understanding the optimization landscape of deep neural networks. Prior wo