Knowledge catalogue
arXiv:2610.20035v1 Announce Type: cross Abstract: We introduce Weighted Adjoint Matching, a method to finetune a pretrained diffusion or flow matching model given a differentiable reward. We derive it
arXiv:2510.02298v2 Announce Type: replace Abstract: Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without s
arXiv:2610.14957v1 Announce Type: new Abstract: Recent video generative models have shown strong capability in synthesizing high-quality and temporally coherent videos. Yet, adapting them for controll
arXiv:2605.06538v2 Announce Type: replace Abstract: Diffusion-based posterior samplers draw from measurement- or reward-conditioned posteriors using pretrained diffusion priors. Though widely used for
arXiv:2610.17015v1 Announce Type: new Abstract: Scaling up data and model capacity has driven substantial progress in visual representation learning. However, conventional pretext tasks exhibit dimini
arXiv:2610.18373v1 Announce Type: new Abstract: Quadruped robots performing outdoor deliveries must interpret complex scenes, anticipate changes, and navigate in socially compliant ways. Robot demonst
arXiv:2610.16489v1 Announce Type: new Abstract: Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires consid
arXiv:2610.15781v1 Announce Type: new Abstract: Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically cons
arXiv:2610.17451v1 Announce Type: new Abstract: Self-supervised polysomnography foundation models (PSG FMs) aim to capture clinically useful information beyond sleep staging, yet are rarely compared w
arXiv:2610.14704v1 Announce Type: new Abstract: Coupling a pretrained vision-language model (VLM) with a diffusion or flow-matching action expert has become the mainstream vision-language-action (VLA)
arXiv:2610.14091v1 Announce Type: new Abstract: Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting t
arXiv:2610.14039v1 Announce Type: cross Abstract: Existing vision-language-action (VLA) models benefit from large-scale vision-language pretraining, but tend to memorize training trajectories, limitin
arXiv:2610.15761v1 Announce Type: cross Abstract: For languages with limited resources, Sentiment Analysis remains a challenging problem due to limited annotated data and strong domain variability acr
arXiv:2610.15585v1 Announce Type: new Abstract: World Action Models (WAMs), often built upon pretrained video-generation world models, have emerged as a promising framework for general-purpose and ope
arXiv:2610.16517v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are often pretrained via imitation learning, making reinforcement learning (RL) post-training important when deplo
arXiv:2610.12728v1 Announce Type: new Abstract: Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained
arXiv:2610.13117v1 Announce Type: new Abstract: Vision-language-action (VLA) models and world action models (WAMs) have advanced robotic policy learning by building on pretrained vision-language model
arXiv:2610.12793v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because
arXiv:2610.13035v1 Announce Type: cross Abstract: Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences mak
arXiv:2610.12781v1 Announce Type: new Abstract: Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only N s
arXiv:2610.12602v1 Announce Type: cross Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part
For the past few weeks I've been trying out converting existing dense models to sparse Mixture-of-Experts models, with no pretraining from scratch. The Idea If you can turn a dense model into an MoE t
Standard Bots develops AI‑native industrial robot arms (used for machine tending, welding, assembly) that rely on a shared pretrained base model with 1–2 billion parameters. The model is adapted to ea
arXiv:2610.11115v1 Announce Type: new Abstract: The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constr
arXiv:2610.12250v1 Announce Type: cross Abstract: Pretrained audio encoders are reused for downstream tasks that are often unknown when the encoder is trained, so their usefulness depends partly on wh
arXiv:2602.14032v2 Announce Type: replace Abstract: Enhancing the generalization of robotic learning in diverse unseen environments remains a fundamental challenge. Existing approaches often rely on l
arXiv:2610.11076v1 Announce Type: cross Abstract: Domain-specific continual adaptation of LLMs risks catastrophic forgetting, creating a fundamental tension between acquiring new capabilities and pres
arXiv:2610.10560v1 Announce Type: cross Abstract: AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their
arXiv:2610.12172v1 Announce Type: cross Abstract: Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial Language Modelin
arXiv:2610.11401v1 Announce Type: cross Abstract: World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion
arXiv:2610.09109v1 Announce Type: new Abstract: Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming lim
arXiv:2610.08255v1 Announce Type: cross Abstract: Many organizations adapt large pretrained models to their own tasks by fine-tuning on private data. Several of these parties often hold data for the s
arXiv:2610.09450v1 Announce Type: new Abstract: Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We
arXiv:2610.10528v1 Announce Type: cross Abstract: Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long
arXiv:2610.09407v1 Announce Type: new Abstract: Pretrained diffusion models are powerful priors for inverse problems, but posterior sampling under nonlinear, non-differentiable forward models remain h
arXiv:2610.09496v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision
arXiv:2610.10415v1 Announce Type: cross Abstract: Pretrained text-to-speech (TTS) models can generate expressive speech, but reliable inference-time emotion control remains challenging: prompts and re
arXiv:2610.10317v1 Announce Type: new Abstract: Tabular foundation models (TFMs) are pretrained across diverse tabular tasks and make predictions on a new table at inference time using its labeled exa
arXiv:2610.08810v1 Announce Type: new Abstract: Fine-tuned geospatial foundation models (GeoFMs) pretrained on large satellite archives have been shown to improve crop classification accuracy and geog
arXiv:2610.07754v1 Announce Type: cross Abstract: Adversarial training is one of the most reliable defenses against adversarial attacks, but its high computational cost must generally be paid anew for
arXiv:2610.07601v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides a natural framework for adapting pretrained models to video temporal grounding, where gen
arXiv:2610.07958v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across
arXiv:2610.08639v1 Announce Type: new Abstract: As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existin
arXiv:2610.08418v1 Announce Type: new Abstract: Biological connectomes encode structured solutions to visual computation that may provide reusable inductive biases for artificial vision. We develop Co
arXiv:2610.08694v1 Announce Type: new Abstract: Gene expression is widely measured in biomedicine, yet clinical outcome prediction remains challenging due to high dimensionality, strong feature correl
arXiv:2610.07032v1 Announce Type: cross Abstract: Large-scale pretrained transformer models have achieved state-of-the-art performance across diverse machine translation tasks, including multilingual
arXiv:2610.07036v1 Announce Type: new Abstract: Parameter-efficient fine-tuning adapts pretrained models at a fraction of the cost of full fine-tuning, yet most low-rank adapters are single-task and r
arXiv:2610.07484v1 Announce Type: new Abstract: Self-supervised EEG models often reconstruct masked waveforms or predict discrete codes. We study a task-aligned alternative: masked band-power predicti
arXiv:2610.08630v1 Announce Type: new Abstract: Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, us
arXiv:2610.07384v1 Announce Type: cross Abstract: Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query ima
arXiv:2610.05353v1 Announce Type: cross Abstract: Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images
arXiv:2610.06221v1 Announce Type: new Abstract: Pretrained diffusion models provide powerful image priors for training-free posterior sampling in image restoration. To guide this sampling process, fre
arXiv:2610.05608v1 Announce Type: new Abstract: We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video
arXiv:2610.04703v1 Announce Type: cross Abstract: Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation. However,
arXiv:2610.05879v1 Announce Type: cross Abstract: We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic
arXiv:2610.03960v1 Announce Type: cross Abstract: Instruction fine-tuning adapts a pretrained language model to follow instructions by training it on instruction--response pairs from a collection of t
arXiv:2610.05718v1 Announce Type: new Abstract: We introduce Reduced-rank Mahalanobis Distance (ReMaD), a novel prototypical distance-based refinement to classification and out-of-distribution (OOD) d
arXiv:2610.05417v1 Announce Type: new Abstract: Recent works augment Vision-Language Models with geometry features from pretrained 3D models, expecting that the geometric signal will boost spatial rea
arXiv:2610.05371v1 Announce Type: new Abstract: Ensemble guidance combines pretrained diffusion priors with black-box forward models to solve inverse problems without differentiating through the physi
arXiv:2610.06605v1 Announce Type: new Abstract: Transformers asked to multiply multi-digit numbers in a single forward pass often fail, and interpretability studies of pretrained language models find