Knowledge catalogue
arXiv:2610.05402v1 Announce Type: new Abstract: A central challenge in continual learning is to acquire new knowledge without forgetting what the model has already learned. This challenge appears in l
arXiv:2610.06694v1 Announce Type: new Abstract: Graph foundation models aim to transfer across graphs, feature spaces, relational schemas, and prediction tasks, yet existing approaches typically gener
arXiv:2610.03797v1 Announce Type: new Abstract: World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction
arXiv:2610.04601v1 Announce Type: new Abstract: Magnetic Resonance Imaging (MRI) is widely regarded as the optimal sensor for fetal brain analysis due to its superior soft-tissue contrast and anatomic
arXiv:2610.03483v1 Announce Type: cross Abstract: We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tra
arXiv:2610.02853v1 Announce Type: new Abstract: Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection
arXiv:2610.02538v1 Announce Type: cross Abstract: Inference-time control steers a pretrained generative model towards a target distribution without retraining. We study tilted targets pi_0propto G_0,p
arXiv:2610.02427v1 Announce Type: cross Abstract: Flow-map distillation enables one- and few-step generation by learning finite-time transitions of a pretrained generative ODE. We investigate whether
arXiv:2610.02597v1 Announce Type: new Abstract: Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowled
arXiv:2610.03249v1 Announce Type: cross Abstract: Deploying a pretrained controller exposes it to conditions that are absent from its training data. Sensor drift, outright sensor failure and accumulat
arXiv:2610.03516v1 Announce Type: cross Abstract: World action models (WAMs) have advanced robot control by predicting how observations and actions evolve over time. Despite this progress, RGB and act
arXiv:2610.01846v1 Announce Type: cross Abstract: Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representa
arXiv:2610.01625v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning enables distributed clients to adapt pretrained vision-language models without sharing raw data or updating th
arXiv:2610.00673v1 Announce Type: cross Abstract: Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage
arXiv:2610.01989v1 Announce Type: new Abstract: Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to supp
arXiv:2610.00277v1 Announce Type: new Abstract: Federated multimodal graph foundation models (GFMs) aim to adapt pretrained multimodal models to decentralized graph data, where each client owns a priv
arXiv:2610.02144v1 Announce Type: new Abstract: We introduce Faynt, a family of 10M- and 75M-parameter Transformer policies for Super Smash Bros. Melee, each controlling all 26 characters with a singl
arXiv:2610.00426v1 Announce Type: new Abstract: We introduce IrekoGPT, a post-hoc method for converting pretrained LLMs into slimmable models whose width can be adjusted at inference time. Building on
arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics d
arXiv:2610.00676v1 Announce Type: cross Abstract: Unsupervised skill discovery has emerged as a promising approach for leveraging reward-free datasets to pretrain general-purpose policies. However, cu
arXiv:2610.01199v1 Announce Type: new Abstract: We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high ac
arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-ima
arXiv:2610.00395v1 Announce Type: new Abstract: Inference-time steering enables pretrained diffusion models to satisfy new constraints without full retraining. However, specificity-aware generation is
arXiv:2610.00907v1 Announce Type: cross Abstract: Relational foundation models (RFMs) are pretrained once on a collection of relational databases and prediction tasks, and then applied zero-shot to pr
arXiv:2610.02054v1 Announce Type: new Abstract: Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervisio
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics
arXiv:2609.40353v1 Announce Type: new Abstract: The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general
arXiv:2609.39763v1 Announce Type: cross Abstract: Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion
arXiv:2609.40306v1 Announce Type: cross Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physi
arXiv:2609.40347v1 Announce Type: new Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of re
arXiv:2609.38362v1 Announce Type: new Abstract: Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining dist
arXiv:2609.39630v1 Announce Type: new Abstract: Pretrained tabular generators can reproduce training records even when aggregate utility remains high. When retraining is unavailable or too costly, sam
arXiv:2609.40165v1 Announce Type: cross Abstract: We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrained generative robot policies using only relative p
arXiv:2609.38984v1 Announce Type: cross Abstract: World-action models (WAMs) leverage pretrained video models to improve generalization in robot control by jointly predicting future visual states and
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:2609.39109v1 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:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effecti
arXiv:2609.36337v1 Announce Type: new Abstract: Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large da
arXiv:2609.37150v1 Announce Type: new Abstract: VLAs combine pretrained vision-language representations with action generation to enable language-guided control across diverse tasks, becoming a mainst
arXiv:2609.37496v1 Announce Type: new Abstract: Paired synthetic aperture radar (SAR) and electro-optical (EO) imagery is increasingly available across sensors, resolutions, and geographic regions. Ye
arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. Me
arXiv:2609.37227v1 Announce Type: new Abstract: Inference-time steering adapts pretrained diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or sam
arXiv:2609.37384v1 Announce Type: new Abstract: Molecular representation learning is central to computer-aided drug discovery. Molecular graphs, SMILES strings, and 3D conformations provide complement
arXiv:2609.37793v1 Announce Type: new Abstract: World-Action Models (WAMs) couple visual dynamics with action prediction, bringing the rich priors of pretrained video models to robotic manipulation. H
arXiv:2609.37529v1 Announce Type: new Abstract: Pretrained denoisers provide a powerful way to incorporate image priors into restoration algorithms. Plug-and-Play and RED approaches exploit fixed-nois
arXiv:2609.36680v1 Announce Type: new Abstract: Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In vi
arXiv:2609.37391v1 Announce Type: new Abstract: Diffusion language models (DLMs) enable parallel generation by predicting and committing multiple tokens at each denoising step, yet they can generate i
arXiv:2609.36950v1 Announce Type: new Abstract: Simulation-based inference is challenging when many heterogeneous observations must be composed, hierarchical latent structure must be preserved, and th
arXiv:2609.36107v1 Announce Type: new Abstract: While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these
arXiv:2609.37989v1 Announce Type: new Abstract: Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, tas
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since addi
arXiv:2609.37198v1 Announce Type: new Abstract: Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few re
arXiv:2609.32376v1 Announce Type: new Abstract: Iterative generation poses a joint optimization problem across steps, as intermediate predictions shape subsequent computations and ultimately determine
arXiv:2609.32570v1 Announce Type: new Abstract: Clustering algorithms that operate on nearest-neighbor graphs, such as FINCH (First Integer Neighbor Clustering Hierarchy), depend heavily on the qualit
arXiv:2609.33106v1 Announce Type: new Abstract: Pretrained macro-placement policies can reduce repeated optimization across circuits, but deployment often exposes them to unfamiliar designs when the o
arXiv:2609.33735v1 Announce Type: new Abstract: Text-guided image editing aims to perform a desired edit while preserving source content unrelated to it. Pretrained rectified-flow models enable traini
arXiv:2609.32771v1 Announce Type: new Abstract: Adapting pretrained models to new data can cause catastrophic forgetting of previously learned behavior. When only a few past samples remain, they give
arXiv:2609.32579v1 Announce Type: new Abstract: A linear projection can reduce the dimension of query and key vectors without updating the pretrained model, but it remains unclear which training objec
arXiv:2609.32510v1 Announce Type: new Abstract: Cloud removal methods are typically specialized to individual datasets and input configurations, limiting reuse across sensors, spectral bands, and obse
arXiv:2609.33607v1 Announce Type: new Abstract: Pretrained graph-text models align graph representations with textual semantics, enabling recognition of unseen classes and transfer across graph domain