Knowledge catalogue
arXiv:2605.26333v1 Announce Type: new Abstract: Educational virtual laboratories can make experimental training more scala-ble, adaptive, and accessible, especially when students have limited access t
arXiv:2605.26782v1 Announce Type: new Abstract: Robotic haptic devices combined with virtual reality offer novel opportunities to train fine force generation, an essential yet overlooked component of
arXiv:2605.27246v1 Announce Type: cross Abstract: This position statement looks back on two decades of work on shallow embeddings of non-classical logics in classical higher-order logic (HOL), a line
arXiv:2605.27345v1 Announce Type: new Abstract: Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g.,
arXiv:2605.26741v1 Announce Type: cross Abstract: Inverse design of materials has significantly advanced target-driven formulation optimization, yet existing materials machine learning benchmarks rema
arXiv:2510.08932v2 Announce Type: replace Abstract: Recently, a growing body of research has focused on either optimizing CTR model architectures to better model feature interactions or refining train
arXiv:2605.26189v1 Announce Type: cross Abstract: Quantization-aware training (QAT) with low-bit floating-point formats enables efficient LLM deployment, yet introduces subtle failure modes invisible
arXiv:2605.26726v1 Announce Type: cross Abstract: Neural cellular automata (NCA) provide a lightweight alternative to encoder-decoder segmentation networks. However, it can be difficult to decide when
arXiv:2605.26343v1 Announce Type: new Abstract: Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recover
arXiv:2601.08267v3 Announce Type: replace Abstract: While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially
arXiv:2603.01131v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise in clinical diagnosis but remain limited by unreliable report generation, weak evidence ground
arXiv:2605.26567v1 Announce Type: new Abstract: Clinical practice guidelines (CPGs) encode evidence-based decision logic that clinicians apply by evaluating patient variables, conditional criteria, an
arXiv:2605.26621v1 Announce Type: cross Abstract: Volumetric Reasoning Segmentation (VRS) aims to segment a target region in a 3D medical scan from a free-form clinical query, where the referent is of
arXiv:2502.06567v2 Announce Type: replace-cross Abstract: Quantizing machine learning models has demonstrated its effectiveness in lowering memory and inference costs while maintaining performance lev
arXiv:2605.26667v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empiric
arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents
arXiv:2605.26394v1 Announce Type: new Abstract: Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench,
arXiv:2605.26676v1 Announce Type: new Abstract: Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfe
arXiv:2605.26959v1 Announce Type: cross Abstract: MerLean-Prover is an end-to-end Lean4 theorem prover that replaces sorry declarations with kernel-checkable proofs. It is built from three agent types
arXiv:2505.18728v2 Announce Type: replace-cross Abstract: The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph St
arXiv:2509.09544v3 Announce Type: replace Abstract: Financial NLP has evolved rapidly since late 2022, outpacing narrative surveys. We introduce MetaGraph, a methodology for extracting typed knowledge
arXiv:2601.18904v2 Announce Type: replace-cross Abstract: Auditory Large Language Models (LLMs) have demonstrated strong performance across a wide range of speech and audio understanding tasks. Nevert
arXiv:2605.26712v1 Announce Type: new Abstract: Benchmarks that reflect the diversity and complexity of real-world documents are essential for accurately evaluating Automatic Text Recognition (ATR) sy
arXiv:2605.26444v1 Announce Type: new Abstract: Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection l
arXiv:2605.27097v1 Announce Type: new Abstract: The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods
arXiv:2605.26691v1 Announce Type: new Abstract: Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume t
arXiv:2605.26234v1 Announce Type: cross Abstract: A recent conjecture by Joel Fine posits a relationship between the coefficients of the HOMFLY polynomial of a knot K in the 3-sphere S^3, and the sign
arXiv:2605.27091v1 Announce Type: cross Abstract: Reliable set-valued prediction provides a principled way to mitigate hallucinations in open-ended question answering (QA), yet existing conformal appr
arXiv:2605.26546v1 Announce Type: new Abstract: Mobile graphical user interface (GUI) agents enable AI models to autonomously operate smartphones on behalf of users. However, most existing systems foc
arXiv:2605.27358v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales
arXiv:2605.27158v1 Announce Type: new Abstract: Discovering the governing equations of a dynamical system from observed trajectories provides deeper insight into its structure than mere prediction of
arXiv:2605.26693v1 Announce Type: cross Abstract: Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the
arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-trai
arXiv:2605.27320v1 Announce Type: new Abstract: Agentic AI systems combine probabilistic reasoning with delegated action through tools, context, memory, orchestration, and external workflow integratio
arXiv:2605.26191v1 Announce Type: cross Abstract: This research addresses the problem of adaptive modeling in time-series data streams with clear input-output relationships. This problem is challengin
arXiv:2603.25415v2 Announce Type: replace Abstract: Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Org
arXiv:2507.13762v4 Announce Type: replace Abstract: Motivation: Structure-based drug design (SBDD) has advanced with deep generative models, but bridging the gap between continuous atomic coordinates
arXiv:2605.26842v1 Announce Type: cross Abstract: The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to pro
arXiv:2510.06381v2 Announce Type: replace-cross Abstract: We propose Monte Carlo Permutation Search (MCPS), a general-purpose Monte Carlo Tree Search (MCTS) algorithm that improves upon the GRAVE algo
arXiv:2605.26647v1 Announce Type: cross Abstract: Feedforward network (FFN) layers account for a large fraction of parameters and nonlinear expressivity in Transformer-based large language models (LLM
arXiv:2512.01678v5 Announce Type: replace Abstract: Graph Neural Networks (GNNs) present a fundamental hardware challenge by fusing irregular, memory-bound graph traversals with regular, compute-inten
arXiv:2504.05046v2 Announce Type: replace Abstract: Existing human Motion Capture (MoCap) methods mostly focus on the visual similarity while neglecting the physical plausibility. As a result, downstr
arXiv:2605.27235v1 Announce Type: new Abstract: Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, an
arXiv:2605.26624v1 Announce Type: new Abstract: Electroencephalogram (EEG)-based emotion recognition is an important affective computing task, and recent EEG foundation models provide useful generic r
arXiv:2605.26718v1 Announce Type: new Abstract: Efficient onboard multi-field sparse reconstruction is essential for the autonomous operation of aerospace vehicles. While existing deep learning models
arXiv:2605.26459v1 Announce Type: new Abstract: Muon-style optimizers take a matrix-valued momentum or preconditioned update B = U operatorname{diag}(sigma_1,ldots,sigma_r) V^op and replace it with it
arXiv:2407.15073v4 Announce Type: replace Abstract: Causal discovery aims to identify causal relationships between variables and is a fundamental problem across the sciences. Traditional statistical c
arXiv:2605.26381v1 Announce Type: new Abstract: We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial
arXiv:2605.26430v1 Announce Type: new Abstract: Collaborative transport of objects via pushing by multiple robots has many applications, ranging from construction and warehouse environments to post di
arXiv:2605.26878v1 Announce Type: new Abstract: Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation and utility ag
arXiv:2605.26320v1 Announce Type: cross Abstract: The application of generalist multimodal models (GMMs) to specialized scientific domains remains limited due to the scarcity of comprehensive domain-s
arXiv:2605.27366v1 Announce Type: new Abstract: Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated a
arXiv:2602.09878v2 Announce Type: replace Abstract: World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely im
arXiv:2605.26879v1 Announce Type: new Abstract: Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate
arXiv:2605.27361v1 Announce Type: new Abstract: Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping
arXiv:2605.26585v1 Announce Type: new Abstract: We study the adversarial kernel bandit problem, in which the loss at each round is induced by an arbitrary bounded element of a reproducing kernel Hilbe
arXiv:2605.26895v1 Announce Type: cross Abstract: Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the
arXiv:2605.27024v1 Announce Type: new Abstract: Implicit neural representations have emerged as a promising paradigm for video compression, with recent methods achieving competitive performance on nat
arXiv:2605.26678v1 Announce Type: new Abstract: Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank
arXiv:2605.26814v1 Announce Type: cross Abstract: We train a pair of autoregressive models to construct zero-mean control variates to mitigate the sign problem in quantum Monte Carlo simulations. The