Knowledge catalogue
arXiv:2607.25169v1 Announce Type: cross Abstract: Message-passing graph neural networks are bounded by the 1-WL test and can miss topological structure that distinguishes non-isomorphic graphs. Positi
arXiv:2607.26015v1 Announce Type: new Abstract: Syntactic convergence (the tendency of speakers to adapt in language towards the grammatical profiles of their interlocutors) is a well-documented featu
arXiv:2607.24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task. Previous work has improved p
arXiv:2607.24771v1 Announce Type: new Abstract: Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in no
arXiv:2607.23860v1 Announce Type: cross Abstract: Deep ensembles provide the most reliable uncertainty estimates in deep learning, but their cost grows linearly with the number of members. Implicit en
arXiv:2607.24560v1 Announce Type: cross Abstract: We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer
arXiv:2607.24424v1 Announce Type: new Abstract: Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features ca
Mage-VL is a codec-native, proactive-streaming multimodal foundation model for image and video understanding, whose visual encoder is trained entirely from scratch at a compact 4B scale. It targets a
Great to see this out, proud of the team!!! @AMD Instella 16B MoE foundation model, fully open with checkpoint after each stage from pretraining, long-context, SFT, DPO and RL. Dataset detail, trainin
arXiv:2607.20561v1 Announce Type: cross Abstract: LoRA adapters provide an efficient way to specialize a pretrained model for many downstream tasks, but deploying one adapter per task requires adapter
arXiv:2607.21529v1 Announce Type: cross Abstract: Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational misma
arXiv:2607.18218v2 Announce Type: replace-cross Abstract: Foundation models have emerged as a driving force in computational pathology, with the potential to transform cancer diagnosis, prognosis, and
Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to act. This approach is 30× cheaper than Gemini 3.1 Flash on pretraining and achieve
arXiv:2607.21582v1 Announce Type: cross Abstract: Compositional generalization is essential for robot to follow diverse instructions. However, pretrained policies are known to take shortcuts, deferrin
arXiv:2503.13969v2 Announce Type: replace Abstract: Field detection in team sports is an essential task in sports video analysis. However, collecting large-scale and diverse real-world datasets for tr
arXiv:2607.19111v1 Announce Type: new Abstract: Large pretrained vision models have substantially improved appearance-based 3D shape retrieval, but they still confuse shapes that look similar while di
arXiv:2607.20301v1 Announce Type: cross Abstract: Fine-tuning has been widely used to adapt large language models (LLMs) for domain-specific tasks. Parameter efficient fine-tuning (PEFT) methods such
arXiv:2607.19383v1 Announce Type: cross Abstract: Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series z
arXiv:2607.13805v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining learns a shared representation space through large-scale contrastive learning. However, existing methods that enf
arXiv:2607.13660v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyp
arXiv:2607.12463v1 Announce Type: new Abstract: Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in
arXiv:2607.12245v1 Announce Type: new Abstract: Few-shot industrial defect detection remains difficult for standard supervised detectors, which achieve poor performance on boundary-dominated industria
arXiv:2607.12360v1 Announce Type: new Abstract: The cooldown phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining, lowers the final training loss in so
arXiv:2511.08226v2 Announce Type: replace-cross Abstract: In order to achieve Continual Learning (CL), the problem of catastrophic forgetting, one that has plagued neural networks since their inceptio
arXiv:2607.07817v1 Announce Type: cross Abstract: We present DreamCharacter-1, a lightweight post-adaptation framework that calibrates pretrained 3D foundation models toward high-fidelity, production-
arXiv:2607.08152v1 Announce Type: cross Abstract: On the recent EyeBench benchmark, predicting reading comprehension from eye movements exposes a stark gap: text-aware models using pretrained language
arXiv:2202.13142v3 Announce Type: replace Abstract: A key challenge of real-world image super-resolution (SR) is to recover the missing details in low-resolution (LR) images with complex unknown degra
arXiv:2602.11399v2 Announce Type: replace-cross Abstract: As unsupervised pretraining becomes increasingly ubiquitous in reinforcement learning, a more thorough theoretical understanding of these meth
arXiv:2607.07173v1 Announce Type: new Abstract: Subject-driven personalized text-to-image generation requires a pretrained diffusion model to acquire a specific subject from a few reference images whi
arXiv:2607.06629v1 Announce Type: new Abstract: Brain age -- the age inferred from a physiological recording -- is an emerging biomarker whose deviation from chronological age tracks neurological and
arXiv:2607.05859v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are promising for construction-site monitoring, and recent construction-tailored VLMs have primarily adapted pretrained VL
arXiv:2409.06067v3 Announce Type: replace Abstract: Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneity among different clients. In light of t
arXiv:2607.06018v1 Announce Type: new Abstract: Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not r
arXiv:2510.13808v2 Announce Type: replace Abstract: Large Vision Language Models (VLMs) excel at general visual reasoning but experience significant performance degradation when deployed in novel doma
arXiv:2607.06163v1 Announce Type: cross Abstract: Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal p
arXiv:2607.05155v1 Announce Type: new Abstract: Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deploy
arXiv:2607.03585v1 Announce Type: new Abstract: Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from h
arXiv:2607.03644v1 Announce Type: cross Abstract: Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, rada
arXiv:2607.04780v1 Announce Type: cross Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutati
arXiv:2607.04880v1 Announce Type: new Abstract: Recent advances in large-scale pretrained vision-language-action models have improved robot policy learning, but directly deploying such policies in use
arXiv:2507.02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable
arXiv:2607.02494v1 Announce Type: cross Abstract: Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Model
arXiv:2607.00684v1 Announce Type: new Abstract: The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts. Handcrafted templates and Large Langu
arXiv:2602.22428v2 Announce Type: replace-cross Abstract: Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existin
arXiv:2603.10263v2 Announce Type: replace-cross Abstract: We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a 'distribution c
arXiv:2607.00250v1 Announce Type: new Abstract: Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only a single kn
arXiv:2607.00647v1 Announce Type: new Abstract: Training-free guidance (TFG) steers a pretrained diffusion model toward a desired attribute at inference. To be effective, this guidance must be applied
arXiv:2511.17979v2 Announce Type: replace Abstract: Diffusion models have achieved remarkable success in generative modeling, yet how to effectively adapt large pretrained models to new tasks remains
arXiv:2606.30686v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) systems, built on pretrained vision-language models (VLMs), have shown rapidly improving performance on robot manipulatio
arXiv:2606.31513v1 Announce Type: new Abstract: Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections -- a severely ill-posed problem.
arXiv:2606.31043v1 Announce Type: new Abstract: Residual reinforcement learning adapts a pretrained robot policy by learning an additive correction to its actions. While effective when adaptation amou
arXiv:2606.29664v1 Announce Type: new Abstract: Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic
arXiv:2606.28516v1 Announce Type: new Abstract: We present CLEAR-MoE, a four-phase post-training pipeline that converts a frozen pretrained Vision Transformer (ViT) into a sparse Mixture-of-Experts (M
arXiv:2606.30140v1 Announce Type: cross Abstract: Recent breakthroughs in foundation models and Large Language Models (LLMs) have introduced new opportunities for studying and decoding genomic sequenc
arXiv:2606.29059v1 Announce Type: cross Abstract: World modeling requires forecasting uncertain futures while preserving information useful for downstream perception. Existing visual world models ofte
arXiv:2606.30059v1 Announce Type: new Abstract: Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external
arXiv:2606.29093v1 Announce Type: new Abstract: A deep defogging pipeline pretrained on controlled laboratory fog and fine-tuned with domain-randomized synthetic fog applied to clear outdoor scenes ge
arXiv:2606.28728v1 Announce Type: cross Abstract: Leveraging large-scale weakly supervised datasets is crucial to train robust end-to-end automatic speech recognition (ASR) models. However, such datas
arXiv:2606.30258v1 Announce Type: cross Abstract: Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Ye
arXiv:2602.20360v2 Announce Type: replace-cross Abstract: Flow-based generative methods offer a simple and effective framework for high-fidelity generation, yet pretrained flow models are rarely used