Knowledge catalogue
arXiv:2605.30601v1 Announce Type: new Abstract: Modern deep networks remain fragile under distribution shift and adversarial perturbations, often due to excessive or poorly structured input sensitivit
arXiv:2605.31075v1 Announce Type: new Abstract: Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, c
arXiv:2601.09633v2 Announce Type: replace Abstract: Taxonomies form the backbone of structured knowledge representation across diverse domains, enabling applications such as e-commerce and semantic se
arXiv:2605.30673v1 Announce Type: new Abstract: Classroom videos contain observable teaching practices, but their pedagogical and visual signals are rarely organized in forms suitable for model evalua
arXiv:2510.03839v2 Announce Type: replace Abstract: We present a theoretical framework for M-FISHER, a method for sequential distribution shift detection and stable adaptation in streaming data. For d
arXiv:2605.30784v1 Announce Type: new Abstract: Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive
arXiv:2605.30628v1 Announce Type: cross Abstract: Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, n
arXiv:2605.31044v1 Announce Type: new Abstract: Reinforcement learning has shown promising results for optimizing the control of industrial energy systems, yet most existing studies remain limited to
arXiv:2605.31547v1 Announce Type: new Abstract: Dynamical systems reconstruction (DSR) aims to learn surrogate models that capture the dynamics underlying time-series data. Reliably deploying these su
arXiv:2605.30600v1 Announce Type: new Abstract: Randomized sketching is a central tool for compressing large-scale optimization problems while preserving accuracy. In particular, sketches that are bas
arXiv:2605.30888v1 Announce Type: new Abstract: Building strong reward models (RMs) for language model alignment is bottlenecked by the cost and difficulty of acquiring diverse and reliable preference
arXiv:2602.01186v2 Announce Type: replace-cross Abstract: Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high
arXiv:2605.30831v1 Announce Type: cross Abstract: Activity cliffs, structurally similar compounds with large potency differences, are widely treated as intrinsic features of chemical datasets. We argu
arXiv:2603.00068v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) systems impose substantial and growing environmental costs, yet transparency about these impacts has declined eve
arXiv:2602.04031v2 Announce Type: replace Abstract: Tabular Language Models (TLMs) have been claimed to achieve strong generalization for tabular prediction. We conduct a systematic re-evaluation of T
arXiv:2605.30389v1 Announce Type: cross Abstract: Pattern languages are a classical model in formal language theory and algorithmic learning theory. This note formulates the problem of computing the i
arXiv:2602.15293v2 Announce Type: replace-cross Abstract: This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The
arXiv:2605.31363v1 Announce Type: new Abstract: Many languages are written in multiple scripts, requiring large language models (LLMs) to generate equivalent linguistic content in distinct orthographi
arXiv:2605.30537v1 Announce Type: new Abstract: Data selection is increasingly used to reduce the cost of large language model (LLM) fine-tuning, with recent methods prioritizing samples by current ut
arXiv:2601.02380v4 Announce Type: replace-cross Abstract: Recent reports claim that Large Language Models (LLMs) have achieved the ability to derive new science and exhibit human-level general intelli
arXiv:2605.31192v1 Announce Type: new Abstract: Recently, thanks to the advent of Multimodal-LLMs, deepfake detectors are striving not only to be generalizable but also interpretable. We propose that
arXiv:2509.23195v2 Announce Type: replace Abstract: The hierarchical syntactic structure and non-hierarchical, statistical, or sequential factors have long been framed as rival theories in accounting
arXiv:2512.05038v2 Announce Type: replace Abstract: Concept vectors aim to enhance model interpretability by linking internal representations with human-understandable semantics, but their practical u
arXiv:2605.30454v1 Announce Type: cross Abstract: Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the a
arXiv:2605.31404v1 Announce Type: cross Abstract: Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster map
arXiv:2605.31289v1 Announce Type: cross Abstract: Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL). Two well established approaches are thr
arXiv:2602.07864v2 Announce Type: replace Abstract: Spatial intelligence is crucial for vision--language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a si
arXiv:2602.02459v2 Announce Type: replace Abstract: Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action
arXiv:2601.19791v3 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results
arXiv:2605.31294v1 Announce Type: new Abstract: Recent advances in Audio-LLMs like GPT-4o have ushered in an era of conversational interaction with language models. Conversational avatars however, sti
arXiv:2605.31283v1 Announce Type: new Abstract: We present SHELLS (Semantic Head Estimation via Layered Local Sampling), an efficient feed-forward framework for 3D head reconstruction in dense semanti
arXiv:2605.31245v1 Announce Type: new Abstract: Recently, sparse autoencoders (SAEs) have emerged as an attractive tool for interpreting and interacting with representations in practical neural networ
arXiv:2509.20784v3 Announce Type: replace-cross Abstract: The fundamental representational units (FRUs) of large language models (LLMs) remain undefined, limiting further understanding of their underl
arXiv:2605.31069v1 Announce Type: cross Abstract: Accurately predicting future events is fundamental to content understanding and decision-making across various domains. While prior research has prima
arXiv:2605.31175v1 Announce Type: new Abstract: The annealing phase is a pivotal convergence stage in LLM pre-training that ultimately determines final model quality. However, effectively selecting tr
arXiv:2605.30913v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in conversational settings where user tone ranges from polite to adversarial or toxic, yet less
arXiv:2605.31025v1 Announce Type: new Abstract: In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve p
arXiv:2605.30995v1 Announce Type: cross Abstract: Public consultations generate large volumes of data in the form of stakeholder submissions that are practically unfeasible to analyse manually. We pre
arXiv:2605.31308v1 Announce Type: new Abstract: Agent benchmarks increasingly record rich interaction trajectories, yet evaluation often reduces each rollout to a pass rate or reward score. We introdu
arXiv:2605.31367v1 Announce Type: cross Abstract: Token mixing layers play a key role in how language models can learn and generate long-range dependencies. Their efficiency relies on the necessary tr
arXiv:2605.30906v1 Announce Type: new Abstract: To enable an efficient interaction of non-communicating mobile robots in collision avoidance scenarios, we present a novel combined trajectory planning
arXiv:2605.30563v1 Announce Type: new Abstract: Factored tasks are a classical planning representation that extends SAS+ with limited forms of disjunctive preconditions, conditional effects, and angel
arXiv:2605.31452v1 Announce Type: new Abstract: Building on our previous work, this paper develops practical, low-barrier methods for freelance translators and smaller language service providers to ev
arXiv:2507.17335v2 Announce Type: replace-cross Abstract: License plate recognition in open environments is widely applicable across various domains; however, the diversity of license plate types and
arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains
arXiv:2605.31419v1 Announce Type: new Abstract: We present a dense RGB-D SLAM system using differentiable triangles as the 3D map representation. While 3D Gaussian Splatting has emerged as the leading
arXiv:2603.22867v1 Announce Type: cross Abstract: Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real
arXiv:2605.30532v1 Announce Type: cross Abstract: We study true self-avoiding walk (TSAW) as a mechanism for improving empirical integral estimation via Markov chain Monte Carlo (MCMC). We consider fi
arXiv:2605.31159v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on prefixes sampled from its own policy while matching a stronger teacher. This addresses the prefix mis
arXiv:2605.31113v1 Announce Type: new Abstract: Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrity of user-generated content (UGC) platforms such a
arXiv:2603.26885v2 Announce Type: replace Abstract: Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-sta
arXiv:2605.31590v1 Announce Type: cross Abstract: Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intri
arXiv:2605.30930v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly act as collaborative partners, human--AI alignment is often evaluated through explicit task success, accu
arXiv:2605.30780v1 Announce Type: new Abstract: In this paper, we use asymmetric vibrations to demonstrate two degree-of-freedom (DoF) in-hand manipulation of grasped parts. The asymmetric vibrations
arXiv:2505.18069v3 Announce Type: replace Abstract: Hebbian and anti-Hebbian plasticity are widely observed in the brain and are classically modeled as mechanistic, local homosynaptic rules stabilized
arXiv:2605.30576v1 Announce Type: new Abstract: Exploration in reinforcement learning for autonomous driving is inherently unsafe: agents must experience novel behaviors to learn, yet exploration can
arXiv:2411.19463v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as a critical technique for enhancing large language model (LLM) capabilities. However, pract
arXiv:2506.22304v3 Announce Type: replace-cross Abstract: Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by their iterative nature requiring costly samp
arXiv:2605.31521v1 Announce Type: new Abstract: Semantic speech tokenizers have become a widely used interface for Audio-LLMs, owing to their compact single-codebook design and strong linguistic align
arXiv:2605.30376v1 Announce Type: cross Abstract: Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical i