Knowledge catalogue
arXiv:2609.20734v1 Announce Type: new Abstract: Reasoning and agentic workloads increasingly demand efficient long-context inference. Yet full-attention decoding reads the growing history at every ste
arXiv:2509.19276v2 Announce Type: replace-cross Abstract: Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this ta
arXiv:2603.05757v2 Announce Type: replace Abstract: Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynam
arXiv:2501.09166v2 Announce Type: replace-cross Abstract: Pretrained Transformers keep what they learned in their weights and lose what they observe once a session ends. The first version of this pape
arXiv:2609.17068v1 Announce Type: cross Abstract: Congenital heart disease (CHD) diagnosis and surgical planning often require patient-specific 3D anatomical models, but manual segmentation is labor-i
arXiv:2609.16648v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training drives the frontier capabilities of large language models, with its wall-clock dominated by autoregressive r
arXiv:2609.17218v1 Announce Type: new Abstract: Label-free clustering of frozen pretrained visual embeddings offers a scalable route to biodiversity monitoring, but image-only fine-grained taxonomy ex
arXiv:2609.17112v1 Announce Type: new Abstract: Large video models have exhibited impressive performance on a wide range of visual question answering tasks, owing to the rise of powerful, pretrained t
arXiv:2609.17435v1 Announce Type: new Abstract: We submit MeTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native
arXiv:2609.16532v1 Announce Type: new Abstract: Continued pretraining (CPT) with data augmentation such as paraphrasing can store inside a large language model (LLM) the knowledge of a small source co
arXiv:2609.14339v1 Announce Type: new Abstract: Decentralized training enables large-model training over low-end GPUs and internet-grade connections, but communication along both data-parallel and pip
arXiv:2609.14715v1 Announce Type: new Abstract: We scale our conventional sub-150M pretraining recipe from 53.5M to 109.7M parameters, holding the method fixed (Qwen3-style decoder with grouped-query
arXiv:2609.13202v1 Announce Type: new Abstract: Feature engineering has long been a cornerstone of tabular machine learning. Tabular foundation models (TFMs) are pretrained on a wide range of tabular
arXiv:2511.12101v3 Announce Type: replace-cross Abstract: Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action gener
arXiv:2609.13812v1 Announce Type: new Abstract: We present GeomVLA, a Vision-Language-Action (VLA) model that unifies perception, latent scene motion prediction, and action generation within a shared
arXiv:2609.14073v1 Announce Type: cross Abstract: Counterfactual world models (CWM) extract motion from pretrained video predictors by comparing factual and intervened predictions. However, responses
arXiv:2609.13654v1 Announce Type: new Abstract: Pretrained foundation models (FMs) have achieved remarkable success in computer vision, yet their high fine-tuning cost limits practical deployment. Par
arXiv:2609.15322v1 Announce Type: cross Abstract: Pretrained driving vision-language models (VLMs) integrate visual, route, language, and driving context into rich driving priors, yet their representa
arXiv:2609.15364v1 Announce Type: new Abstract: Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce
arXiv:2609.15014v1 Announce Type: cross Abstract: Pretrained generative robot policies can produce effective behaviors across diverse environments, but deployment can lead to requirements and preferen
arXiv:2609.13838v1 Announce Type: new Abstract: Purpose: To develop and evaluate TotalSynth, a reusable pretrained framework for whole-body synthetic CT (sCT) generation from MRI and cone-beam CT (CBC
arXiv:2609.14156v1 Announce Type: new Abstract: Integrating contact information into visuomotor policies remains an open problem. Touch is essential to robust manipulation, yet most modern policies, i
arXiv:2609.13984v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models combine a pretrained vision encoder, a language backbone, and an action head, but their relative contribution has
arXiv:2609.12731v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models inevitably internalize sensitive or non-compliant concepts from large-scale pretraining data, necessitating post-ho
arXiv:2609.12993v1 Announce Type: cross Abstract: We investigate the effect of pretrained T5 model scale and explicit motion features on pose-to-text Indian Sign Language Translation (SLT) for the WSL
arXiv:2609.12123v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is an effective approach for adapting large pretrained models by learning low-rank weight updates. In practice, the LoRA rank
arXiv:2609.13141v1 Announce Type: new Abstract: Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context un
arXiv:2501.04234v2 Announce Type: replace-cross Abstract: Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus
arXiv:2609.12853v1 Announce Type: cross Abstract: The widespread adoption of data-driven, energy-efficient model predictive control (MPC) in buildings remains hindered by substantial effort to collect
arXiv:2609.11270v1 Announce Type: new Abstract: Pretrained generative robot policies learn expressive action priors from demonstrations. However, existing reinforcement learning methods only steer the
arXiv:2609.10915v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design coup
arXiv:2609.11716v1 Announce Type: cross Abstract: Post-training quantization compresses large language models (LLMs) by storing their weights at reduced precision, and each quantized weight introduces
arXiv:2609.06849v1 Announce Type: new Abstract: Sleep provides a nightly window into health by capturing coordinated activity across the brain, heart, muscles and respiratory system. We introduce Slee
arXiv:2609.08115v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) pretraining relies on an auxiliary load-balancing loss (LBL) to drive per-expert utilization toward uniformity. Post-training i
arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and tr
arXiv:2609.10355v1 Announce Type: cross Abstract: Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained larg
arXiv:2609.05730v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation fo
arXiv:2601.08026v5 Announce Type: replace Abstract: Scientific compound figures combine multiple labeled panels into a single image, and downstream pretraining and retrieval require panel-aligned visu
arXiv:2609.06079v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide action generation for robot control. VLMs provide hie
arXiv:2609.09123v1 Announce Type: new Abstract: Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods distill pretrained bidirectional vid
arXiv:2601.20845v2 Announce Type: replace Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require dom
arXiv:2609.06581v1 Announce Type: new Abstract: Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detector
arXiv:2609.04239v1 Announce Type: new Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series (TS) foundation model (TSFM) tailored to financial
arXiv:2609.04355v1 Announce Type: cross Abstract: Pretrained vision-language-action (VLA) models enable broad manipulation but remain unreliable in tasks demanding precision and repeatability. Applyin
arXiv:2609.04672v1 Announce Type: new Abstract: We introduce WEECFP, a parameter-free 1024-dimensional continuous molecular fingerprint that scatters each Morgan substructure across roughly thirty-two
arXiv:2609.03069v1 Announce Type: new Abstract: Neural operators are fast, differentiable surrogates for physical simulation, but their accuracy often degrades when domain geometry, size, or operating
arXiv:2609.03085v1 Announce Type: new Abstract: There is growing interest in adopting CLIP-style vision--language model (VLM) pretraining for mammography. However, models that directly employ the stan
arXiv:2609.03880v1 Announce Type: new Abstract: We introduce Xiaomi-TabLDM, a tabular large data foundation model for classification and regression via in-context learning, which delivers superior pre
arXiv:2609.01757v1 Announce Type: new Abstract: Vision-Language Pretrained Models (VLPMs) offer a scalable path to open-vocabulary chest radiology understanding, yet two aspects remain underexplored:
arXiv:2609.02663v1 Announce Type: new Abstract: Pretrained vision-language models (VLMs) have shown promising performance in medical image segmentation by incorporating clinical text. However, it rema
arXiv:2609.01802v1 Announce Type: new Abstract: Prompt tuning provides a parameter-efficient way to adapt foundation models (FMs) by freezing the pretrained backbone and updating only a small set of l
Next year frontier models are going to one shot everything 100x faster & cheaper than they are No reasoning traces to monitor Instinctive intelligence Which is why what you embed in pretraining is eve
arXiv:2609.02341v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) have shown strong potential in autonomous driving by leveraging multimodal pretraining for instruction following, v
arXiv:2609.01308v1 Announce Type: new Abstract: Cardiac magnetic resonance (CMR) imaging provides complementary information on cardiac anatomy, function, and tissue characterization across multiple se
arXiv:2609.00968v1 Announce Type: new Abstract: SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observations. Existing latent diffusion ap
arXiv:2609.01108v1 Announce Type: new Abstract: TRACE (Math & Lienhart, arXiv:2602.01135) reads causal graphs over event types out of a pretrained autoregressive sequence model by thresholding a per-p
arXiv:2609.01353v1 Announce Type: new Abstract: Protein inverse folding aims to recover amino acid sequences for a given 3D protein structure, underpinning broad applications such as enzyme engineerin
arXiv:2609.00184v1 Announce Type: new Abstract: Large language models (LLMs) rely on static pretraining corpora, causing their knowledge to become outdated over time. Existing approaches for evaluatin
arXiv:2609.01277v1 Announce Type: cross Abstract: Although pretrained joint audio-visual diffusion models offer rich control over what to generate, they provide no explicit control over when an uttera
arXiv:2601.06022v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding b