Knowledge catalogue
arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicate
arXiv:2609.38325v1 Announce Type: new Abstract: We introduce modal kinetic typography, which animates a vector glyph to express a semantic concept while keeping it legible. Our key idea is to build mo
arXiv:2609.38630v1 Announce Type: new Abstract: Privacy redaction must remove personal information while preserving relationships expressed in text. We develop a multilingual named-entity tagger with
arXiv:2609.39591v1 Announce Type: new Abstract: Uncertainty estimation in machine learning typically decomposes uncertainty into aleatoric uncertainty (AU) and epistemic uncertainty (EU) using the sta
arXiv:2609.39048v1 Announce Type: cross Abstract: Protein optimization remains a longstanding goal in life sciences. Existing machine learning-assisted directed evolution (MLDE) methods primarily rely
arXiv:2603.18822v2 Announce Type: replace Abstract: What is known about the values of national populations rests almost entirely on questionnaires, which prompt respondents to rate researcher-supplied
arXiv:2609.39049v1 Announce Type: cross Abstract: A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let cod
arXiv:2609.39926v1 Announce Type: new Abstract: Achieving cross-sensor generalization and arbitrary-scale reconstruction with a single model remains challenging in hyperspectral super-resolution (HSR)
arXiv:2512.00729v2 Announce Type: replace Abstract: Motivated by the observed human-like behaviours in Large Reasoning Models (LRMs), this paper introduces a comprehensive taxonomy to characterise ato
arXiv:2601.12310v2 Announce Type: replace Abstract: Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic dri
arXiv:2609.39034v1 Announce Type: cross Abstract: Designing expressive sequence layers with efficient inference remains a central challenge in modern machine learning. Standard softmax attention achie
arXiv:2609.39019v1 Announce Type: new Abstract: Multi-view learning seeks to learn more comprehensive representations by exploiting the complementarity and consistency across diverse modalities or vie
arXiv:2609.38225v1 Announce Type: cross Abstract: Imitation learning enables robots to acquire complex skills directly from massive demonstration datasets, but its performance degrades severely when d
arXiv:2609.38414v1 Announce Type: new Abstract: Synthetic data generation is dominated by the fit-then-sample paradigm: a generative model is trained on a private dataset and then sampled from. Despit
arXiv:2609.39447v1 Announce Type: new Abstract: Interpreting properties of LLM-generated data is important for understanding its utility and limitations across learning tasks. In this work, we charact
arXiv:2609.39827v1 Announce Type: cross Abstract: Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes
arXiv:2609.38537v1 Announce Type: new Abstract: GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabili
arXiv:2609.39466v1 Announce Type: new Abstract: In this work, we introduce a new clustering method, namely T-ARC (Topology-Aware Randomized Clustering), that corrects the geometric bias of K-means by
arXiv:2609.39109v1 Announce Type: cross Abstract: Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalam
arXiv:2609.38434v1 Announce Type: cross Abstract: Real-world optimization problems are difficult to model accurately because many objectives and constraints reside in domain experts' tacit knowledge,
arXiv:2609.38658v1 Announce Type: cross Abstract: TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but thei
arXiv:2609.39969v1 Announce Type: cross Abstract: Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding tra
arXiv:2609.40134v1 Announce Type: cross Abstract: Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random a
arXiv:2609.38353v1 Announce Type: cross Abstract: Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they o
arXiv:2602.06700v2 Announce Type: replace-cross Abstract: Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply cou
arXiv:2609.38371v1 Announce Type: cross Abstract: Existing LLM-driven robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focus
arXiv:2609.38867v1 Announce Type: new Abstract: Large language model (LLM) computer-use agents are typically evaluated with clean written instructions, despite speech being an increasingly popular int
arXiv:2609.39334v1 Announce Type: cross Abstract: Test-time scaling has recently emerged as a powerful approach for improving LLM reasoning by allocating additional computation during inference, subst
arXiv:2609.38958v1 Announce Type: new Abstract: Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning. However, the internal mecha
arXiv:2609.38391v1 Announce Type: new Abstract: Document text forgery has evolved beyond simple pixel-level manipulation: modern attacks alter not only the appearance of a document but also its meanin
arXiv:2609.39033v1 Announce Type: cross Abstract: CLIP is a powerful vision-language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt i
arXiv:2609.38637v1 Announce Type: cross Abstract: Visual object tracking typically assumes that the initial template and subsequent search frames share the same sensing modality. In practice, sensor a
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human mot
arXiv:2609.39599v1 Announce Type: cross Abstract: 3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-
arXiv:2609.39335v1 Announce Type: new Abstract: Video virtual try-on has attracted increasing attention due to its broad potential in digital fashion and intelligent e-commerce. However, existing meth
arXiv:2609.38565v1 Announce Type: new Abstract: Over the past 25 years, sketching and sampling have become widely used tools for accelerating large-scale regression. In iterative randomized solvers, a
arXiv:2609.38469v1 Announce Type: cross Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send
arXiv:2609.39913v1 Announce Type: new Abstract: We test whether large language models solve formally matched kinship problems equally well when relations are expressed in familiar vocabulary or by exp
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value ca
arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear h
arXiv:2609.39497v1 Announce Type: new Abstract: Randomized smoothing certifies the probability of a fixed output event as the center of Gaussian noise moves. Feasibility or confidence filtering report
arXiv:2609.39343v1 Announce Type: new Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introduc
arXiv:2609.39001v1 Announce Type: cross Abstract: LLM services are billed per token and context windows are measured in tokens, yet the number of tokens needed for the same content varies across langu
arXiv:2609.39055v1 Announce Type: new Abstract: How can we personalize a shared expert library from a user's pairwise choices? Prior work can realize different reward trade-offs by merging reward-spec
arXiv:2609.39741v1 Announce Type: new Abstract: Large forecasting applications often combine statistical, machine-learning, and neural models. These families solve the same problem but differ in fitte
arXiv:2609.39235v1 Announce Type: cross Abstract: World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet exist
arXiv:2609.39114v1 Announce Type: new Abstract: This paper examines how row-wise renormalization affects Muon, focusing on the gap between NorMuon's worst-case guarantees and its practical performance
arXiv:2609.38205v1 Announce Type: new Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the trans
arXiv:2510.01581v2 Announce Type: replace-cross Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in li
arXiv:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly const
arXiv:2609.38541v1 Announce Type: new Abstract: Instruction-guided video editing has made significant progress, yet existing methods use multimodal large language models (MLLMs) primarily as semantic
arXiv:2603.21144v2 Announce Type: replace-cross Abstract: This paper proposes a new formulation of functional Gaussian Process regression on manifolds, based on an Empirical Bayes approach, in the spa
arXiv:2609.40083v1 Announce Type: cross Abstract: One-class artifact detectors for whole-slide images learn normal tissue from a clean training pool and flag departures from it. The pool is built by a
arXiv:2609.39618v1 Announce Type: new Abstract: Soft pneumatic actuators (SPAs) are highly promising and have been extensively explored within the field of soft robotics. Under pneumatic pressure load
arXiv:2404.11624v2 Announce Type: replace-cross Abstract: We introduce the Token Space, a categorical framework for AI computations. A Token is a finite tuple whose entries are elements of a carrier s
arXiv:2609.38201v1 Announce Type: new Abstract: Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. Thi
arXiv:2609.39797v1 Announce Type: new Abstract: Autonomous powder weighing is one of many bottlenecks in laboratory automation due to the complex, non-linear dynamics of heterogeneous materials. Robot
arXiv:2609.39792v1 Announce Type: new Abstract: Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned archi
arXiv:2609.39822v1 Announce Type: new Abstract: Vision-language-action (VLA) models face a timing gap between low-rate inference and high-rate robot execution. We characterize this gap through end-to-
arXiv:2609.39611v1 Announce Type: new Abstract: Agile multi-UAV flight requires accurate and low-latency onboard estimation of the kinematic states of neighboring UAVs for collision avoidance, motion