Fast KV Compaction via Attention Matching
arXiv:2602.16284v2 Announce Type: replace Abstract: Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typi
Knowledge catalogue
arXiv:2602.16284v2 Announce Type: replace Abstract: Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typi
arXiv:2512.16483v2 Announce Type: replace Abstract: Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale pr
arXiv:2605.27432v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has emerged as a paradigm for grounding large language models in external knowledge, yet most existing RAG system
arXiv:2605.27892v1 Announce Type: new Abstract: Synthetic Electronic Health Record (EHR) generation provides a promising avenue for data augmentation and cross-hospital modeling in privacy-constrained
arXiv:2605.28501v1 Announce Type: new Abstract: Fitting an unknown number of hyperplanes to data is a fundamental yet challenging problem in machine learning, characterized by its non-convexity, non-d
arXiv:2605.21832v2 Announce Type: replace Abstract: Modern recommender systems rely heavily on ID-based collaborative filtering: each item is represented by a unique ID embedding that accumulates coll
arXiv:2605.27590v1 Announce Type: new Abstract: Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological
arXiv:2605.27387v1 Announce Type: cross Abstract: Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autor
arXiv:2605.27384v1 Announce Type: cross Abstract: This position paper reflects empirical data collected during my PhD from a large-scale within-subjects study (N = 90). The study compared a highly hum
arXiv:2605.28359v1 Announce Type: new Abstract: Evaluating whether large language model (LLM) agents can profit in capital markets is increasingly framed as end-to-end trading: place an agent in a his
arXiv:2605.28820v1 Announce Type: new Abstract: Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular frame
arXiv:2605.27944v1 Announce Type: new Abstract: With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepf
arXiv:2605.28548v1 Announce Type: new Abstract: Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Acti
arXiv:2405.09689v2 Announce Type: replace-cross Abstract: Hyperdimensional Computing (HDC) is a computationally and data-efficient paradigm that acts as a bridge between connectionist and symbolic app
arXiv:2605.27934v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards,
arXiv:2605.27499v1 Announce Type: new Abstract: Flow and diffusion generative models have established themselves as widely adopted density estimators for simulation-based inference (SBI), extending na
arXiv:2605.28200v1 Announce Type: new Abstract: Single-cell RNA sequencing (scRNA-seq) profiles large numbers of cells but loses spatial context, whereas spatial transcriptomics (ST) preserves partial
arXiv:2605.28643v1 Announce Type: new Abstract: Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another cru
arXiv:2605.28645v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Grap
arXiv:2605.28520v1 Announce Type: new Abstract: Accurately forecasting the impact of salient financial events on markets is critical for investors and policymakers. However, existing multimodal time-s
arXiv:2605.28308v1 Announce Type: new Abstract: Entity Alignment (EA) is essential for knowledge graph (KG) fusion, but existing benchmarks often allow models to exploit name overlap rather than relat
arXiv:2605.27703v1 Announce Type: new Abstract: Large Language Models are increasingly deployed inside agentic systems, where they must follow structured protocols, adapt to evolving states, and opera
arXiv:2504.10079v4 Announce Type: replace Abstract: Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level repres
arXiv:2508.15130v2 Announce Type: replace Abstract: Despite significant progress in no-reference image quality assessment (NR-IQA), dataset biases and reliance on subjective labels continue to hinder
arXiv:2605.28684v1 Announce Type: new Abstract: Reduced-order models (ROMs) can accelerate high-dimensional dynamical simulations, but their accuracy often deteriorates when online dynamics leave the
arXiv:2605.28302v1 Announce Type: cross Abstract: Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-leve
arXiv:2605.28398v1 Announce Type: new Abstract: Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality agai
arXiv:2510.06928v2 Announce Type: replace Abstract: Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of vis
arXiv:2605.27374v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, pers
arXiv:2605.27523v1 Announce Type: cross Abstract: Deep generative models offer powerful tools for multivariate data analysis, but their black-box architectures are often unidentified and difficult to
arXiv:2601.04716v3 Announce Type: replace Abstract: While Large Language Model (LLM) role-playing agents have advanced rapidly, it remains unclear which profile elements genuinely drive role-playing q
arXiv:2605.27373v1 Announce Type: new Abstract: As intelligent systems become more autonomous, the scientific community focuses on creating decision-making mechanisms that include ethical and moral co
arXiv:2605.28320v1 Announce Type: cross Abstract: This paper addresses the problem of identifying parsimonious explicit piece-wise polynomial relationships that might involve a relatively large number
arXiv:2605.27397v1 Announce Type: new Abstract: In wireless sensor networks (WSNs), data augmentation is a novel method to improve sampling-frequency decision performance, thereby enabling energy opti
arXiv:2605.28353v1 Announce Type: cross Abstract: Cartesian Genetic Programming has traditionally been using mutation as its main and often sole genetic operator to drive evolutionary search. Despite
arXiv:2510.15859v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has driven recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be compute
arXiv:2605.27583v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are widely used non-invasive measurements of cardiac activity and play a central role in clinical diagnosis. Recent multimodal
arXiv:2605.28006v1 Announce Type: cross Abstract: Understanding how LLMs reason is hindered by a practical asymmetry: while their generated outputs are observable, the underlying reasoning patterns re
arXiv:2605.28654v1 Announce Type: new Abstract: Uncrewed aerial vehicles (UAVs) are increasingly used for exploration-driven monitoring in hazardous environments such as disaster zones, contaminated s
arXiv:2603.16985v2 Announce Type: replace Abstract: Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibil
arXiv:2605.27628v1 Announce Type: new Abstract: As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remai
arXiv:2605.28605v1 Announce Type: new Abstract: Self-supervised low-light image enhancement (LLIE) is highly appealing as it eliminates the reliance on external paired data. However, the lack of exter
arXiv:2605.28649v1 Announce Type: cross Abstract: LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forg
arXiv:2605.28714v1 Announce Type: cross Abstract: An Initial Public Offering (IPO) filing is a document released when a private firm goes public, allowing individual (retail) investors to purchase its
arXiv:2512.00814v3 Announce Type: replace Abstract: Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration met
arXiv:2605.27946v1 Announce Type: cross Abstract: Backpropagation is the default learning rule for artificial neural networks and is often treated as the settled approach whenever differentiability is
arXiv:2605.28495v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors (A and B), creating
arXiv:2605.28427v1 Announce Type: new Abstract: Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space an
arXiv:2605.27375v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous interaction with the environment can lead to in-context
arXiv:2605.28775v1 Announce Type: cross Abstract: Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive.
arXiv:2605.27391v1 Announce Type: cross Abstract: This paper examines whether students are entering the generative AI era with sufficiently strong educational foundations, focusing on the relationship
arXiv:2507.06999v2 Announce Type: replace-cross Abstract: Reasoning is essential for large language models (LLMs), especially in complex tasks such as mathematical problem solving. However, multimodal
arXiv:2605.28162v1 Announce Type: cross Abstract: Logical operations are essential for quantum computation within quantum error-correcting codes. However, discovering their physical realizations is ch
arXiv:2605.28513v1 Announce Type: cross Abstract: Variance reduction (VR) methods employ stochastic gradients with decreasing variance, and they have been widely applied to solve large-scale optimizat
arXiv:2605.27999v1 Announce Type: cross Abstract: We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the
arXiv:2605.28120v1 Announce Type: cross Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more co
arXiv:2605.27413v1 Announce Type: cross Abstract: Proteins perform their biological functions through three-dimensional structures encoded by amino acid sequences, and ligand-binding protein co-design
arXiv:2506.08928v2 Announce Type: replace Abstract: Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning models due to their prediction performance and comp
arXiv:2605.27786v1 Announce Type: cross Abstract: Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving
arXiv:2605.28170v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly integrated into high-stakes decision-making, the ability to reliably quantify uncertainty has become a