Where are they looking in the operating room?
arXiv:2604.20574v1 Announce Type: new Abstract: Purpose: Gaze-following, the task of inferring where individuals are looking, has been widely studied in computer vision, advancing research in visual a
Knowledge catalogue
arXiv:2604.20574v1 Announce Type: new Abstract: Purpose: Gaze-following, the task of inferring where individuals are looking, has been widely studied in computer vision, advancing research in visual a
arXiv:2604.20564v1 Announce Type: new Abstract: While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logical deduction, where a single transition error can propa
arXiv:2601.14249v4 Announce Type: replace Abstract: Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior
arXiv:2507.08540v5 Announce Type: replace-cross Abstract: The proliferation of software vulnerabilities presents a significant challenge to cybersecurity, necessitating more effective detection method
arXiv:2604.20131v1 Announce Type: new Abstract: Increasingly, studies are exploring using Large Language Models (LLMs) for accelerated or scaled qualitative analysis of text data. While we can compare
arXiv:2603.23146v2 Announce Type: replace-cross Abstract: The widespread adoption of Large Language Models (LLMs) has made the detection of AI-Generated text a pressing and complex challenge. Although
arXiv:2604.20190v1 Announce Type: new Abstract: Wildfire monitoring requires timely, actionable situational awareness from airborne platforms, yet existing aerial visual question answering (VQA) bench
arXiv:2508.16676v2 Announce Type: replace-cross Abstract: Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language mode
arXiv:2604.19756v1 Announce Type: cross Abstract: Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse p
arXiv:2604.20789v1 Announce Type: cross Abstract: We investigate the integration of human-like working memory constraints into the Transformer architecture and implement several cognitively inspired a
arXiv:2604.20289v1 Announce Type: new Abstract: Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Rec
arXiv:2511.08277v2 Announce Type: replace-cross Abstract: Learning-based inertial odometry has achieved remarkable progress in pedestrian navigation. However, extending these methods to quadruped robo
arXiv:2604.20350v1 Announce Type: new Abstract: Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely u
arXiv:2502.02779v3 Announce Type: replace-cross Abstract: Head computed tomography (CT) imaging is a widely-used imaging modality with multitudes of medical indications, particularly in assessing path
arXiv:2604.19584v1 Announce Type: new Abstract: The growing interest of Natural Language Processing (NLP) in minority languages has not yet bridged the gap in the preservation of oral linguistic herit
arXiv:2604.18721v1 Announce Type: cross Abstract: Visual state-space models (SSMs) are increasingly promoted as efficient alternatives to Vision Transformers, yet their practical advantages remain unc
arXiv:2604.19653v1 Announce Type: new Abstract: Human mobility data are used in numerous applications, ranging from public health to urban planning. Human mobility is inherently sensitive, as it can c
arXiv:2508.15832v2 Announce Type: replace-cross Abstract: Web agents have shown great promise in performing many tasks on ecommerce website. To assess their capabilities, several benchmarks have been
arXiv:2604.19643v1 Announce Type: new Abstract: AcoustoBots are mobile acoustophoretic robots capable of delivering mid-air haptics, directional audio, and acoustic levitation, but existing implementa
arXiv:2603.22885v4 Announce Type: replace Abstract: BACKGROUND: General aviation fleet expansion demands intelligent health monitoring under computational constraints. Real-world aircraft health diagn
arXiv:2604.19689v1 Announce Type: new Abstract: Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large
arXiv:2604.18944v1 Announce Type: new Abstract: Named Entity Recognition (NER) models trained on clean, high-resource corpora exhibit catastrophic performance collapse when deployed on noisy, sparse U
arXiv:2604.18988v1 Announce Type: new Abstract: Multimodal empathetic response generation (MERG) aims to generate emotionally engaging and empathetic responses based on users' multimodal contexts. Exi
arXiv:2604.19715v1 Announce Type: new Abstract: Distribution networks with high penetration of Distributed Energy Resources (DERs) increasingly rely on communication networks to coordinate grid-intera
arXiv:2604.19465v1 Announce Type: cross Abstract: Understanding how complex systems respond to perturbations, such as whether they will remain stable or what their most sensitive patterns are, is a fu
arXiv:2604.18806v1 Announce Type: new Abstract: 3D-IC netlist partitioning is commonly optimized using proxy objectives, while final PPA is treated as a costly evaluation rather than an optimization s
arXiv:2604.18881v1 Announce Type: cross Abstract: Supervised learning with Earth observation inputs is often limited by the sparsity of high-quality labeled or in-situ measured data to use as training
arXiv:2604.19572v1 Announce Type: new Abstract: As model capabilities advance, research has increasingly shifted toward long-horizon, multi-turn terminal-centric agentic tasks, where raw environment f
arXiv:2507.09861v2 Announce Type: replace-cross Abstract: Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents tha
arXiv:2604.19606v1 Announce Type: new Abstract: Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are
arXiv:2604.18889v1 Announce Type: new Abstract: We present AC-SINDy, a compositional extension of the Sparse Identification of Nonlinear Dynamics (SINDy) framework that replaces explicit feature libra
arXiv:2604.19518v1 Announce Type: new Abstract: Decentralized optimization enables multiple devices to learn a global machine learning model while each individual device only has access to its local d
arXiv:2604.19011v1 Announce Type: new Abstract: Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is
arXiv:2604.19374v1 Announce Type: new Abstract: Achieving truly fluid interaction with robots with speech interfaces remains a hard problem, and the experience of current Human-Robot Interaction (HRI)
arXiv:2603.13779v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform
arXiv:2604.18980v1 Announce Type: new Abstract: Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs. How
arXiv:2603.11729v2 Announce Type: replace-cross Abstract: In recent years, RAPTOR based algorithms have been considered the state-of-the-art for path-finding with unlimited transfers without preproces
arXiv:2510.14630v2 Announce Type: replace Abstract: We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obta
arXiv:2604.19722v1 Announce Type: cross Abstract: The discretization of continuous numerical attributes remains a persistent computational bottleneck in the induction of decision trees, particularly a
arXiv:2602.04713v2 Announce Type: replace-cross Abstract: Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model i
arXiv:2604.19233v1 Announce Type: new Abstract: Deep learning-based object detectors have achieved remarkable success across numerous computer vision applications, yet they continue to struggle with s
arXiv:2601.07056v2 Announce Type: replace-cross Abstract: Medical hyperspectral imaging (MHSI) has shown strong potential for disease diagnosis by capturing spectral-spatial information of tissues. Wh
arXiv:2604.08404v2 Announce Type: replace Abstract: Out-of-distribution (OoD) generalization occurs when representation learning encounters a distribution shift. This occurs frequently in practice whe
arXiv:2604.19059v1 Announce Type: new Abstract: Language-guided unmanned aerial vehicles (UAVs) often fail not from bad reasoning or perception, but from execution mismatch: the gap between a planned
arXiv:2604.19066v1 Announce Type: new Abstract: Physical activity (PA) is widely recognized as protective against mental distress, yet whether this benefit varies systematically across population subg
arXiv:2604.18612v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thou
arXiv:2504.09662v3 Announce Type: replace-cross Abstract: Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up
arXiv:2604.18576v2 Announce Type: replace Abstract: We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the Forecast
arXiv:2602.04983v2 Announce Type: replace-cross Abstract: Purpose: To investigate whether an AI-based method can detect subtle inter-fraction changes in MR-Linac images acquired during radiotherapy an
arXiv:2604.18961v1 Announce Type: cross Abstract: This paper presents an AI-enabled cascaded hybrid vision/force control framework for tendon-driven aerial continuum manipulators based on constant-str
arXiv:2604.18805v1 Announce Type: new Abstract: Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to t
arXiv:2604.19386v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrai
arXiv:2604.18713v1 Announce Type: new Abstract: Automated 3D segmentation of prostate lesions from biparametric MRI (bp-MRI) is essential for reliable algorithmic analysis, but achieving high precisio
arXiv:2604.19016v1 Announce Type: new Abstract: Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, model
arXiv:2406.18344v2 Announce Type: replace Abstract: We study the intriguing connection between visual data, deep networks, and the brain. Our method creates a universal channel alignment by using brai
arXiv:2604.19238v1 Announce Type: new Abstract: Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors of large-scale diffusion and flow-based
arXiv:2604.19657v1 Announce Type: cross Abstract: AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., pers
arXiv:2604.19685v1 Announce Type: new Abstract: Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and
arXiv:2604.19592v1 Announce Type: new Abstract: We give a Gordon-Greenwald-Marks (GGM) style black-box reduction from online learning to online multicalibration. Concretely, we show that to achieve hi
arXiv:2604.18775v1 Announce Type: new Abstract: Detecting jailbreak behaviour in large language models remains challenging, particularly when strongly aligned models produce harmful outputs only rarel