Knowledge catalogue
arXiv:2610.14705v1 Announce Type: cross Abstract: Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging bec
arXiv:2609.32717v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional s
arXiv:2610.16790v1 Announce Type: cross Abstract: Language model APIs can expose token-specific biases while withholding logits and token probabilities. Existing bias-based extraction recovers relativ
arXiv:2610.19623v1 Announce Type: new Abstract: Single-image 3D reconstruction has advanced rapidly, yet standalone garments remain challenging due to thin-shell geometry, open boundaries, and layered
arXiv:2610.19844v1 Announce Type: new Abstract: Memory-efficient subspace optimization has emerged as a practical approach to reducing the memory cost of LLM training while preserving optimization per
arXiv:2610.19789v1 Announce Type: new Abstract: Self-distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published baseli
arXiv:2610.19443v1 Announce Type: new Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual inputs
arXiv:2610.15339v1 Announce Type: new Abstract: Current fMRI encoding models frame prediction as deterministic regression, yet identical stimuli evoke a distribution of neural responses (arising from
arXiv:2610.19190v1 Announce Type: new Abstract: Many sentiment datasets use one annotator for each item, so the test labels show the conventions of that person. We build a Nepali benchmark from two an
arXiv:2610.18612v1 Announce Type: cross Abstract: System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly driv
arXiv:2610.20223v1 Announce Type: new Abstract: Vision-language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling robots to generate actions from visual observ
arXiv:2610.19746v1 Announce Type: new Abstract: Vision-language-action (VLA) models have recently achieved remarkable progress by leveraging large-scale robot datasets and foundation models for genera
arXiv:2610.20160v1 Announce Type: new Abstract: Learning world models across diverse domains calls for a unified control space, yet ac- tion interfaces vary across domains and action annotations are o
arXiv:2610.20418v1 Announce Type: new Abstract: Tabular foundation models enable in-context learning by predicting unseen observations from a labeled support table without task-specific parameter upda
arXiv:2602.11965v2 Announce Type: replace Abstract: Temporal domain generalization (TDG) learns from a sequence of observed domains to predict models for unseen future domains. Existing parameter-dyna
arXiv:2606.16569v2 Announce Type: replace Abstract: Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the re
arXiv:2610.20004v1 Announce Type: new Abstract: Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context
arXiv:2610.17584v1 Announce Type: new Abstract: Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while con
arXiv:2610.20369v1 Announce Type: new Abstract: Neural partial differential equation (PDE) surrogates trained with mean squared error (MSE) can capture dominant dynamics but often lose high-frequency
arXiv:2610.19700v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning by learning low-rank weight updates. Increasing rank expands adaptation capacity, but
arXiv:2610.19674v1 Announce Type: new Abstract: Geometry foundation models estimate camera poses and 3D scene structure from video sequences, but maintaining consistent reconstructions over long horiz
arXiv:2610.19810v1 Announce Type: cross Abstract: Large language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At
arXiv:2610.19630v1 Announce Type: cross Abstract: Automated materials discovery requires evaluating large pools of candidate configurations, with density functional theory (DFT) as a major throughput
arXiv:2610.20247v1 Announce Type: new Abstract: Multilingual models share capacity across languages, so adding languages can hurt performance on existing ones. Mixture-of-experts models expand this ca
arXiv:2610.15056v1 Announce Type: cross Abstract: Large language models can post-edit ASR by using linguistic context to compare N-best hypotheses and rewrite the transcript when needed, often improvi
arXiv:2610.19327v1 Announce Type: new Abstract: Robotic ultrasound can standardize image acquisition and reduce operator workload and variability, but policy learning remains limited by the lack of re
arXiv:2610.19232v1 Announce Type: new Abstract: Large language models impose substantial memory demands and arithmetic costs during inference. Dense-to-mixture-of-experts (MoE) conversion is a model o
arXiv:2610.16636v1 Announce Type: cross Abstract: State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grow
arXiv:2610.19557v1 Announce Type: new Abstract: Contrastive learning for time series depends on deciding which pairs of inputs should be treated as similar and dissimilar. Because few augmentations re
arXiv:2610.20456v1 Announce Type: new Abstract: The scaling relationship of compute and performance for language models (LMs) has been extensively studied; more recently, models are being designed to
arXiv:2610.18520v1 Announce Type: cross Abstract: Autoregressive language models produce, at every prediction step, a vocabulary-sized logit vector whose structure determines the conditional next-toke
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitat
arXiv:2511.00198v2 Announce Type: replace-cross Abstract: Autoregressive language models are usually trained with next-token prediction under a fixed left-to-right target order. This paper studies tar
arXiv:2610.17959v1 Announce Type: cross Abstract: The design of attention mechanisms in long-context large language models faces an ``impossible triangle'' among KV cache size, training and prefill FL
arXiv:2610.19517v1 Announce Type: cross Abstract: Vision-language-action (VLA) models connect visual perception and language understanding with robot control, providing a foundation for instruction-co
arXiv:2503.04940v3 Announce Type: replace-cross Abstract: Emergent Language (EL) focuses on the emergence of communication among artificial agents. Although symbolic communication channels more closel
arXiv:2610.19825v1 Announce Type: cross Abstract: Integrating world models into Vision-Language-Action models (VLAs) has emerged as a promising direction, enabling policies to anticipate future dynami
arXiv:2610.19814v1 Announce Type: new Abstract: Transformer-based tabular foundation models (TFMs) achieve state-of-the-art performance on small to medium-sized tabular prediction tasks while processi
arXiv:2610.19324v1 Announce Type: new Abstract: In large language models (LLMs), attention concentrates heavily on the first token. This 'attention sink' is believed to protect deep models against ove
arXiv:2610.17638v1 Announce Type: new Abstract: World Action Models (WAMs) use generative visual representations to condition robot actions, yet how these representations organize action-relevant info
arXiv:2610.17786v1 Announce Type: cross Abstract: We study industrial fault diagnosis as a classification task that assigns sensor time-series windows to predefined health states or fault types. Scarc
arXiv:2610.17944v1 Announce Type: new Abstract: Current image-guided neuronavigation techniques, such as intraoperative MRI and ultrasound, are limited by high costs, limited sensitivity and operation
arXiv:2607.19198v2 Announce Type: replace-cross Abstract: Amorphous materials exhibit exceptional mechanical and functional properties, yet their rugged energy landscapes are notoriously difficult to
arXiv:2610.14589v1 Announce Type: new Abstract: Walking sequences reveal human-interpretable attributes related to body structure, posture, and motion. Gait attribute recognition provides a concrete r
arXiv:2610.14155v1 Announce Type: cross Abstract: Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions. Vision-language-action (VLA) models combine pr
arXiv:2610.16892v1 Announce Type: new Abstract: Emotions are expressed on a continuum and are naturally described in the valence-arousal (VA) space. Existing VA-based image editors are typically train
arXiv:2610.14746v1 Announce Type: cross Abstract: World Action Models (WAMs) commonly couple video and action experts through dense, layer-wise Mixture-of-Transformers (MoT) attention, exposing action
arXiv:2610.16320v1 Announce Type: new Abstract: Building age is fundamental for urban infrastructure safety, operation, and planning, as it directly affects structural safety, and sustainable developm
arXiv:2610.15290v1 Announce Type: cross Abstract: We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allow
arXiv:2610.14413v1 Announce Type: new Abstract: Computational coarse-graining aims to replace a sequence of updates with a cheaper module while preserving task performance. We present a continuation-r
arXiv:2610.17332v1 Announce Type: new Abstract: Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership in
arXiv:2610.16908v1 Announce Type: new Abstract: End-to-end driving requires rich spatiotemporal representations to support scene understanding and trajectory planning under strict latency constraints.
arXiv:2610.17387v1 Announce Type: new Abstract: Day-ahead (DA) electricity price forecasting is usually posed per market, with a separate model fitted to each grid's own history. This caps accuracy: s
arXiv:2610.18696v1 Announce Type: new Abstract: Particle picking in cryo-electron microscopy is commonly formulated as an object-detection problem in which individual particles are represented by boun
arXiv:2610.14710v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong potential for text-attributed graph learning by leveraging rich pre-trained knowledge and language unders
arXiv:2610.15794v1 Announce Type: new Abstract: Flow matching is a common generative recipe for robot foundation models. Vision-language-action models (VLAs) generate action chunks, while world-action
arXiv:2610.17789v1 Announce Type: cross Abstract: A long-horizon manipulation task consists of primitive skills and the transitions connecting them. Learning skills that can be executed in sequence re
arXiv:2610.16433v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) provide general-purpose forecasting capabilities, yet their forecasts can remain misaligned with the temporal char
arXiv:2610.14277v1 Announce Type: cross Abstract: Tensor parallelism ends every layer with an all-reduce that sits between two dependent matrix multiplications, so its cost cannot be hidden and grows
arXiv:2610.17466v1 Announce Type: new Abstract: Frechet Distributional (FD) objectives provide an effective distribution-level signal for post-training generative models. For latent generative models,