Knowledge catalogue
arXiv:2604.26255v1 Announce Type: new Abstract: Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep
arXiv:2604.26353v1 Announce Type: new Abstract: While large models demonstrate the strong representational power of vanilla attention, this core mechanism cannot be directly applied to Dense Object Tr
arXiv:2604.26519v1 Announce Type: new Abstract: The rapid evolution of deepfake technology poses an unprecedented threat to the authenticity of Graphics Interchange Format (GIF) imagery, which serves
arXiv:2601.13942v2 Announce Type: replace-cross Abstract: Large Multimodal Models (LMMs) have achieved remarkable success in visual understanding, yet they struggle with knowledge-intensive queries in
arXiv:2601.21459v4 Announce Type: replace-cross Abstract: LLM role-playing, i.e., using LLMs to simulate specific personas, has emerged as a key capability in various applications, such as companionsh
arXiv:2604.26279v1 Announce Type: new Abstract: Recently, Hyperspectral Image (HSI) classification has attracted increasing attention in remote sensing. However, HSI data are inherently high-dimension
arXiv:2604.26139v1 Announce Type: new Abstract: Diffusion large language models generate text through multi-step denoising, where hallucination signals may emerge throughout the trajectory rather than
arXiv:2401.00761v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) like ChatGPT are foundational in various applications due to their extensive knowledge from pre-training and fine
arXiv:2604.25927v1 Announce Type: new Abstract: Information extraction from semi-structured business documents remains a critical challenge for enterprise management. This study evaluates the capabili
arXiv:2503.23818v3 Announce Type: replace-cross Abstract: Structured state-space models (SSMs) have recently emerged as a powerful architecture at the intersection of machine learning and control, fea
arXiv:2604.26673v1 Announce Type: cross Abstract: Uncertainty estimation is essential for robust decision-making in the presence of ambiguous or out-of-distribution inputs. Gaussian Processes (GPs) ar
arXiv:2604.25960v1 Announce Type: cross Abstract: Large language models have transformed AI-assisted software engineering, but current research remains biased toward high-resource languages such as Py
arXiv:2604.26932v1 Announce Type: cross Abstract: The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depen
arXiv:2409.00557v4 Announce Type: replace-cross Abstract: Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of task
arXiv:2602.20426v2 Announce Type: replace Abstract: While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agen
arXiv:2507.01449v3 Announce Type: replace Abstract: Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in para
arXiv:2604.26516v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavi
arXiv:2604.26591v1 Announce Type: cross Abstract: Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimizati
arXiv:2604.26774v1 Announce Type: cross Abstract: Open-vocabulary change detection aims to identify semantic changes in bi-temporal remote sensing images without predefined categories. Recent methods
arXiv:2604.26138v1 Announce Type: new Abstract: Over the past decade, hyperspectral image (HSI) classification has drawn considerable interest due to HSIs' ability to effectively distinguish terrestri
arXiv:2604.26261v1 Announce Type: new Abstract: Zero-shot 3D Visual Grounding (3DVG) is a critical capability for open-world embodied AI. However, existing methods are fundamentally bottlenecked by th
arXiv:2604.26456v1 Announce Type: cross Abstract: The digitisation of classical Sanskrit literature is impeded by a scarcity of annotated resources, particularly for Named Entity Recognition. While re
arXiv:2602.03169v2 Announce Type: replace-cross Abstract: Clustering functional data in the presence of phase variation is challenging, as temporal misalignment can obscure intrinsic shape differences
arXiv:2604.04135v2 Announce Type: replace Abstract: This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and
arXiv:2604.26622v1 Announce Type: new Abstract: Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended h
arXiv:2604.26211v1 Announce Type: new Abstract: In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that
arXiv:2604.26091v1 Announce Type: new Abstract: We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX
arXiv:2603.05959v3 Announce Type: replace Abstract: Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve im
arXiv:2604.26573v1 Announce Type: new Abstract: Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the to
arXiv:2604.06061v2 Announce Type: replace Abstract: Text-to-image generation has progressed rapidly, but faithfully generating complex scenes requires extensive trial-and-error to find the exact promp
arXiv:2604.26834v1 Announce Type: cross Abstract: We present a quantum feature-selection framework based on a higher-order unconstrained binary optimization (HUBO) formulation that explicitly incorpor
arXiv:2604.26435v1 Announce Type: cross Abstract: The rapid advancement of object detection architectures has positioned single stage detectors as the dominant solution for real-time visual perception
arXiv:2604.26067v1 Announce Type: new Abstract: We present RADIO-ViPE (Reduce All Domains Into One -- Video Pose Engine), an online semantic SLAM system that enables geometry-aware open-vocabulary gro
arXiv:2604.26830v1 Announce Type: cross Abstract: I propose the Random Cloud method, a training-free approach to neural architecture search that discovers minimal feedforward network topologies throug
arXiv:2507.21420v3 Announce Type: replace-cross Abstract: The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing effici
resharing this note, find it helpful given all the great open evals work + teams building vertical agents Evals are a proxy for the behavior we want our agent to exhibit in production Model+Harness pu
arXiv:2604.25975v1 Announce Type: cross Abstract: Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generatio
arXiv:2604.05190v2 Announce Type: replace-cross Abstract: Screening patients for enrollment is a well-known, labor-intensive bottleneck that leads to under-enrollment and, ultimately, trial failures.
arXiv:2508.12672v4 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wh
arXiv:2601.04389v2 Announce Type: replace-cross Abstract: Current safety evaluations of large language models (LLMs) create a dangerous illusion of universal protection by aggregating harms under gene
arXiv:2604.26394v1 Announce Type: cross Abstract: Recent advances in large language models and agentic frameworks have enabled virtual customer assistants (VCAs) for complex support. We present SecMat
arXiv:2604.26221v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) in remote sensing images is a promising task that employs textual descriptions for identifying undefined
arXiv:2604.26940v1 Announce Type: new Abstract: Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their
arXiv:2511.13285v2 Announce Type: replace Abstract: Artistic design, particularly poster design, often demands rapid yet precise modification of textual content while preserving visual harmony and typ
arXiv:2604.26620v1 Announce Type: new Abstract: Depth ambiguity and joint uncertainty are the two main obstacles in obtaining accurate human pose predictions by 2D-to-3D lifting methods proposed in th
arXiv:2604.26409v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) have demonstrated significant success in interpreting Large Language Models (LLMs) by decomposing dense representations into
arXiv:2604.26341v1 Announce Type: new Abstract: Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image
arXiv:2604.26388v1 Announce Type: cross Abstract: Federated Split Learning has been identified as an efficient approach to address the computational resource constraints of clients in classical federa
arXiv:2604.26500v1 Announce Type: new Abstract: LLMs and speech assistants are increasingly used for task-oriented interactions, yet their evaluation often relies on controlled scenarios that fail to
arXiv:2511.07689v2 Announce Type: replace-cross Abstract: Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where c
arXiv:2604.26157v1 Announce Type: cross Abstract: Structural generalization in semantic parsing requires systems to apply learned compositional rules to novel structural combinations. Existing approac
arXiv:2604.26102v1 Announce Type: cross Abstract: Large language model agents have achieved remarkable progress on software engineering tasks, yet current approaches suffer from a fundamental context
arXiv:2511.20032v3 Announce Type: replace Abstract: Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability ofte
arXiv:2604.26167v1 Announce Type: cross Abstract: Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that sati
arXiv:2604.26317v1 Announce Type: new Abstract: The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of
arXiv:2602.11731v2 Announce Type: replace Abstract: Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision para
arXiv:2603.08182v2 Announce Type: replace-cross Abstract: Large language models often underperform in many European languages due to the dominance of English and a few high-resource languages in train
arXiv:2505.24867v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. Howeve
arXiv:2409.01115v5 Announce Type: replace Abstract: This article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches
arXiv:2604.26247v1 Announce Type: cross Abstract: Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user inte