Knowledge catalogue
arXiv:2608.28625v1 Announce Type: cross Abstract: We study predictive pretraining for scientific document representation using the discourse structure of papers. We propose SciJEPA, a citation-free fr
arXiv:2608.29920v1 Announce Type: new Abstract: Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA wit
arXiv:2507.00754v3 Announce Type: replace Abstract: The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the
arXiv:2311.13892v4 Announce Type: replace-cross Abstract: The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to nu
arXiv:2608.30975v1 Announce Type: cross Abstract: Cardiac magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine videos and spatial LGE/mapping stacks, yet most deep lear
arXiv:2603.12165v3 Announce Type: replace Abstract: Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult t
arXiv:2606.23687v2 Announce Type: replace Abstract: Large language models (LLMs) are typically pretrained on short sequences and then extended to work on longer sequences with additional training. How
arXiv:2606.21803v2 Announce Type: replace Abstract: Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test ti
arXiv:2608.30567v1 Announce Type: new Abstract: We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-con
arXiv:2602.01605v2 Announce Type: replace Abstract: Time Series Foundation Models (TSFMs) leverage extensive pretraining to accurately predict unseen time series during inference, without the need for
arXiv:2608.30964v1 Announce Type: new Abstract: Pretrained vision embeddings are increasingly used as general-purpose representations for modelling how people appraise urban scenes, and are validated
arXiv:2608.30395v1 Announce Type: new Abstract: As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inf
arXiv:2608.30880v1 Announce Type: new Abstract: Generalizable embodied manipulation remains difficult to achieve through pretraining alone, due to unseen physical conditions in the real world. We argu
arXiv:2608.27079v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies provide strong priors for robot manipulation, yet adapting them online to fine-grained biomedical tasks
arXiv:2604.02324v2 Announce Type: replace-cross Abstract: Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in
arXiv:2608.26821v1 Announce Type: new Abstract: Vision-language-action (VLA) models leverage pretrained vision-language representations for robot control, yet simply adding historical frames does not
arXiv:2608.25568v1 Announce Type: new Abstract: To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has att
arXiv:2608.25738v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) are increasingly distributed as pretrained checkpoints and reused as backbones for new tasks. However, current SNN wate
arXiv:2608.25575v1 Announce Type: new Abstract: Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and rela
arXiv:2608.25990v1 Announce Type: new Abstract: Orthogonal optimisers such as Muon can substantially accelerate large language model pretraining relative to Adam, yet the mechanism remains incompletel
arXiv:2608.25100v1 Announce Type: cross Abstract: Large Language Models (LLMs) are powerful but limited by static parametric knowledge that becomes outdated once pretraining ends. Knowledge editing ad
arXiv:2608.26033v1 Announce Type: new Abstract: In medical imaging, it is common to use learned perceptual image patch similarity (LPIPS) to compare images semantically in feature space. Although back
arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco
arXiv:2507.18405v3 Announce Type: replace Abstract: Vision Transformers (ViTs) face two limitations: the rigid resolution dependency of positional embeddings, which complicates cross-resolution fine-t
arXiv:2604.04407v2 Announce Type: replace-cross Abstract: Guided depth super-resolution (GDSR) is a multi-modal approach for depth map super-resolution that relies on a low-resolution depth map and a
arXiv:2606.13856v2 Announce Type: replace Abstract: Fine-tuning a vision-language-action model (VLA-JEPA) on a single GPU should be simple: load a pretrained checkpoint, run training, deploy. There is
arXiv:2602.02824v2 Announce Type: replace Abstract: LLM unlearning aims to remove the influence of undesirable knowledge from pretrained language models, which offers a practical mechanism for address
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while reta
arXiv:2608.23094v1 Announce Type: cross Abstract: One implicit DDIM inversion step is the cheapest probe of whether a pretrained diffusion model encodes local manifold geometry. It is the stationarity
arXiv:2608.22193v1 Announce Type: new Abstract: We present SAM3Dual, our third-place solution to the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. SAM3D
arXiv:2608.22358v1 Announce Type: new Abstract: Deep atmospheric convection governs South Asian monsoon variability, yet attempting to learn its latent world model directly from zero-inflated, heavy-t
arXiv:2608.22869v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning to achieve strong performance on long-
arXiv:2608.21160v1 Announce Type: new Abstract: Machines that understand humans should perceive the present and anticipate the future. Existing human-centric vision model are pretrained on human image
arXiv:2608.20910v1 Announce Type: new Abstract: With large pretrained models, existing methods have effectively improved instruction-based video editing. However, most of them rely on an in-place edit
arXiv:2606.15765v2 Announce Type: replace Abstract: Vision foundation models (VFMs) exhibit complementary strengths shaped by their pretraining objectives. Yet prevailing methods for multi-task dense
arXiv:2608.20011v1 Announce Type: new Abstract: Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow
arXiv:2608.19906v1 Announce Type: new Abstract: Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP
arXiv:2608.19735v1 Announce Type: new Abstract: We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic cli
arXiv:2608.20024v1 Announce Type: new Abstract: District heating energy hubs require reliable heat load forecasts for efficient operational scheduling. Conventional forecasting workflows train system-
arXiv:2608.19182v1 Announce Type: cross Abstract: We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for learning sim-to-real transferabl
arXiv:2608.18907v1 Announce Type: cross Abstract: Small-scale image classification is often limited by the scarcity of training data. Generative data augmentation (GDA) based on pretrained generative
arXiv:2608.18399v1 Announce Type: new Abstract: Vision transformers (ViTs) trained to copy a pretrained teacher's attention maps recover most of fine-tuning's in-distribution accuracy yet fall measura
https://huggingface.co/inclusionAI/Ling-3.0-tiny-base https://huggingface.co/inclusionAI/Ling-3.0-flash-base-midtrain https://huggingface.co/inclusionAI/Ling-3.0-flash-base-30T https://huggingface.co/
arXiv:2608.17519v1 Announce Type: new Abstract: Vision-based surgical skill assessment has shown strong in-domain results, yet a fundamental question remains unasked: do these models learn transferabl
arXiv:2608.17616v1 Announce Type: new Abstract: We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retrain
SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers SCoPE adds camera sightlines as positional coordinates to a pretrained video diffusion transformer. Given a first frame
arXiv:2608.16978v1 Announce Type: new Abstract: Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining,
arXiv:2608.14591v1 Announce Type: cross Abstract: The integration of artificial intelligence (AI) and wireless communications is widely regarded as a core objective of sixth-generation (6G) systems. H
arXiv:2608.14824v1 Announce Type: cross Abstract: We present a parameter-free episodic evaluation of nearest-centroid classification for elephant vocalisations on fixed pretrained acoustic embeddings,
arXiv:2509.14104v2 Announce Type: replace Abstract: Self-supervised learning (SSL) through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) foundation model (F
arXiv:2608.15061v1 Announce Type: new Abstract: Do feed-forward networks (FFNs) in visual grounding decoders add essential computation once a pretrained vision-language model has already encoded image
arXiv:2608.15285v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temp
arXiv:2410.17397v2 Announce Type: replace-cross Abstract: We introduce a framework for seamlessly integrating quantum computing into pretrained large language models (LLMs). The key idea is to constru
arXiv:2608.14790v1 Announce Type: new Abstract: Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable co
arXiv:2608.15144v1 Announce Type: cross Abstract: Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose intermediate likelihood component is generally intractab
arXiv:2608.16224v1 Announce Type: cross Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question formulations without task-specific training. Howev
arXiv:2608.15055v1 Announce Type: new Abstract: Hypergraphs effectively model higher-order groupwise relationships beyond pairwise interactions, while pretrained language models (PLMs) and large langu
arXiv:2608.14675v1 Announce Type: cross Abstract: While Self-Supervised Learning (SSL) effectively extracts general representations from noisy, unconstrained physiological signals such as photoplethys
arXiv:2608.15861v1 Announce Type: new Abstract: Fine-grained wrist activity recognition can support applications such as procedural step guidance and context-aware assistance, yet acquiring labeled da
arXiv:2608.14414v1 Announce Type: new Abstract: Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunolog