Few-Shot Personalized Age Estimation
arXiv:2604.09125v1 Announce Type: new Abstract: Existing age estimation methods treat each face as an independent sample, learning a global mapping from appearance to age. This ignores a well-document
Knowledge catalogue
arXiv:2604.09125v1 Announce Type: new Abstract: Existing age estimation methods treat each face as an independent sample, learning a global mapping from appearance to age. This ignores a well-document
arXiv:2604.09051v1 Announce Type: new Abstract: Fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy requires frame-level recognition of visually similar suturing
arXiv:2603.13842v3 Announce Type: replace-cross Abstract: End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demo
arXiv:2604.08850v1 Announce Type: new Abstract: Independent Component Analysis (ICA) is a fundamental unsupervised learning technique foruncovering latent structure in data by separating mixed signals
arXiv:2604.09114v1 Announce Type: new Abstract: Composed image retrieval (CIR) aims to retrieve a target image that depicts a reference image modified by a textual description. While recent vision-lan
arXiv:2603.02417v3 Announce Type: replace-cross Abstract: Classical stochastic-approximation analyses treat the covariance of stochastic gradients as an exogenous modeling input. We show that under ex
arXiv:2410.15001v5 Announce Type: replace Abstract: Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation
arXiv:2512.20033v2 Announce Type: replace Abstract: We present FlashLips, a two-stage, mask-free lip-sync system that decouples lips control from rendering and achieves real-time performance, with our
arXiv:2604.08586v1 Announce Type: cross Abstract: Computational fluid dynamics (CFD) provides high-fidelity simulations of fluid flows but remains computationally expensive for many-query applications
arXiv:2601.18150v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence
arXiv:2604.09063v1 Announce Type: cross Abstract: Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiven
arXiv:2604.08603v1 Announce Type: new Abstract: Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how ac
arXiv:2604.08591v1 Announce Type: cross Abstract: Hallucinations in large ASR models present a critical safety risk. In this work, we propose the extit{Spectral Sensitivity Theorem}, which predicts a
arXiv:2604.09327v1 Announce Type: new Abstract: Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations.
arXiv:2512.02826v3 Announce Type: replace-cross Abstract: Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memoriz
arXiv:2604.04089v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate code rapidly but remain unreliable for scientific algorithms whose correctness depends on structural
arXiv:2604.09459v1 Announce Type: new Abstract: Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions withi
arXiv:2604.08617v1 Announce Type: cross Abstract: Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representat
arXiv:2604.08581v1 Announce Type: new Abstract: This paper presents a fully autonomous Tiny Machine Learning (TinyML) Z-Score-based anomaly detection system deployed on a low-power microcontroller for
arXiv:2604.08576v1 Announce Type: cross Abstract: Sixth-generation (6G) wireless networks must support heterogeneous services: enhanced Mobile Broadband (eMBB) requiring 1 Tbps data rates, massive Mac
arXiv:2604.06014v2 Announce Type: replace Abstract: We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhat
arXiv:2604.08894v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficienci
arXiv:2506.04676v2 Announce Type: replace-cross Abstract: The data scarcity, label noise, and long-tailed category imbalance remain important and unresolved challenges in many computer vision tasks, s
arXiv:2604.09175v1 Announce Type: cross Abstract: We develop a theory of generalization and scaling for Mixture-of-Experts (MoE) Transformers that cleanly separates active per-input capacity from rout
arXiv:2604.08664v1 Announce Type: new Abstract: Developing autonomous physical human-robot interaction (pHRI) systems is limited by the scarcity of large-scale training data to learn robust robot beha
arXiv:2510.24718v3 Announce Type: replace Abstract: Autoregressive video diffusion models are capable of long rollouts that are stable and consistent with history, but they are unable to guide the cur
arXiv:2604.08661v1 Announce Type: cross Abstract: Neural Quantum States based on autoregressive recurrent neural network (RNN) wave functions enable efficient sampling without Markov-chain autocorrela
arXiv:2604.09142v1 Announce Type: new Abstract: Despite remarkable advances in image-driven stereo matching over the past decade, Synthetic-to-Realistic Zero-Shot (Syn-to-Real) generalization remains
arXiv:2604.08896v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have accelerated progress in domain-oriented AI, yet their development in geoscience and rem
arXiv:2604.09095v1 Announce Type: new Abstract: Automated algorithm selection in continuous black-box optimisation typically relies on fixed landscape descriptors computed under a limited probing budg
arXiv:2604.09304v1 Announce Type: new Abstract: For decades, Physically-Based Rendering (PBR) is the fundation of synthesizing photorealisitic images, and therefore sometimes roughly referred as Photo
arXiv:2506.03074v5 Announce Type: replace-cross Abstract: We present `GL-LowPopArt`, a novel Catoni-style estimator for generalized low-rank trace regression. Building on `LowPopArt` (Jang et al., 202
arXiv:2604.09199v1 Announce Type: new Abstract: We solve the problem of determining the pose of known shapes in R^3 from their unoccluded silhouettes. The pose is determined up to global optimality us
arXiv:2604.08553v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong performance on text-attributed graphs (TAGs) due to their superior semantic understanding ability on te
arXiv:2403.08462v3 Announce Type: replace Abstract: Authorship Verification (AV) is a key area of research in digital text forensics, which addresses the fundamental question of whether two texts were
arXiv:2501.11568v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification
arXiv:2604.08879v1 Announce Type: new Abstract: Moving beyond the traditional binary classification paradigm of Multimodal Sarcasm Detection, Multimodal Sarcasm Target Identification (MSTI) presents a
arXiv:2604.09222v1 Announce Type: cross Abstract: Audio large language models (ALLMs) enable rich speech-text interaction, but they also introduce jailbreak vulnerabilities in the audio modality. Exis
arXiv:2404.10976v4 Announce Type: replace-cross Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying rel
arXiv:2503.14075v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) have demonstrated remarkable capabilities in open-world multimodal understanding, yet their high computati
arXiv:2602.05407v2 Announce Type: replace Abstract: Hospital administration departments handle a wide range of operational tasks and, in large hospitals, process over 10,000 requests per day, driving
arXiv:2604.06165v2 Announce Type: replace Abstract: Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation s
arXiv:2604.08877v1 Announce Type: new Abstract: In this paper, we study the text-based person search, which is to retrieve the person of interest via natural language description. Prevailing methods u
arXiv:2603.27222v2 Announce Type: replace Abstract: High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forwa
arXiv:2604.08863v1 Announce Type: new Abstract: Recovering analytical solutions of physical fields from visual observations is a fundamental yet underexplored capability for AI-assisted scientific rea
arXiv:2604.09075v1 Announce Type: new Abstract: Large language models increasingly operate under multiple instructions from heterogeneous sources with different authority levels, including system poli
arXiv:2604.09336v1 Announce Type: new Abstract: Accurate prediction of intersection turning movements is essential for adaptive signal control but remains difficult due to the high volatility of direc
arXiv:2604.08829v1 Announce Type: new Abstract: The Hierarchical Kernel Transformer (HKT) is a multi-scale attention mechanism that processes sequences at L resolution levels via trainable causal down
arXiv:2604.05072v2 Announce Type: replace Abstract: Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, ex
arXiv:2604.08826v1 Announce Type: cross Abstract: Large foundation models have become central to modern machine learning, with performance scaling predictably with model size and data. However, traini
arXiv:2604.08648v1 Announce Type: cross Abstract: We motivate the use of differentiable probabilistic programming techniques in order to account for the large model-space inherent to astrophysical gam
arXiv:2604.09408v1 Announce Type: new Abstract: Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is n
arXiv:2604.09231v1 Announce Type: new Abstract: Although recent advances have improved the quality of 3D texture generation, existing methods still struggle with incomplete texture coverage, cross-vie
arXiv:2604.08884v1 Announce Type: cross Abstract: While multimodal large language models (MLLMs) have made significant strides in natural image understanding, their ability to perceive and reason over
arXiv:2604.08872v1 Announce Type: new Abstract: Many language tasks can be modeled as classification problems where a large language model (LLM) is given a prompt and selects one among many possible a
arXiv:2511.16136v2 Announce Type: replace Abstract: The rapid advancement of generative models has made real and synthetic images increasingly indistinguishable. Although extensive efforts have been d
arXiv:2604.08966v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have advanced Video Temporal Grounding (VTG), existing methods often couple output paradigms with differe
arXiv:2510.26899v5 Announce Type: replace-cross Abstract: The launch of Grokipedia, an AI-generated encyclopedia developed by Elon Musk's xAI, was presented as a response to perceived ideological and
arXiv:2604.08883v1 Announce Type: cross Abstract: Inspired by the general Vision-and-Language Navigation (VLN) task, aerial VLN has attracted widespread attention, owing to its significant practical v
arXiv:2604.09001v1 Announce Type: new Abstract: Enumerating Minimal Unsatisfiable Subsets (MUSes) is a fundamental task in constraint satisfaction problems (CSPs). Its major challenge is the exponenti