Knowledge catalogue
arXiv:2603.05999v2 Announce Type: replace Abstract: Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360^irc images due to the substan
arXiv:2604.02327v2 Announce Type: replace-cross Abstract: Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tas
arXiv:2606.29451v1 Announce Type: new Abstract: Self-supervised learning (SSL) pretrained models have become a dominant paradigm for visual representation learning, but they are vulnerable to backdoor
arXiv:2606.29241v1 Announce Type: new Abstract: Data-generating priors are a central component of tabular foundation models because they define the task distribution used during pretraining. However,
arXiv:2606.29097v1 Announce Type: new Abstract: Recent research has investigated the use of large language models (LLMs) to generate traffic scenarios for autonomous driving. However, pretrained LLMs
arXiv:2606.29964v1 Announce Type: new Abstract: Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view:
arXiv:2606.20014v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments rem
arXiv:2606.27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models
arXiv:2505.06668v2 Announce Type: replace Abstract: We present StableMotion, a novel framework that leverages geometric and content priors from pretrained large-scale image diffusion models for motion
arXiv:2606.28117v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models. When applied sequentially across
arXiv:2606.26618v1 Announce Type: new Abstract: Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their traini
arXiv:2606.27095v1 Announce Type: cross Abstract: Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initia
arXiv:2606.26899v1 Announce Type: new Abstract: Embedding-based retrieval ranks items by their similarity to a query in a shared vector space and usually aims to return the highest-scoring items. In m
arXiv:2606.26534v1 Announce Type: cross Abstract: Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styl
arXiv:2606.25010v1 Announce Type: cross Abstract: Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabil
arXiv:2606.25844v1 Announce Type: new Abstract: A common practice converts a one-dimensional signal into an image so that a vision backbone pretrained on natural photographs can be reused for recognit
arXiv:2606.25478v1 Announce Type: new Abstract: Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generaliza
arXiv:2606.24912v1 Announce Type: cross Abstract: Automatic Music Transcription (AMT) models have achieved a high level of success in polyphonic transcription of various instruments. Velocity, typical
arXiv:2606.24051v1 Announce Type: new Abstract: Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow
arXiv:2503.13505v3 Announce Type: replace-cross Abstract: Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often pr
arXiv:2504.17070v3 Announce Type: replace-cross Abstract: Robots need task planning methods to achieve goals that require more than one action. Recently, large pretrained models have demonstrated impr
arXiv:2606.23938v1 Announce Type: new Abstract: Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose interme
arXiv:2606.24102v1 Announce Type: new Abstract: Most electronic health record (EHR) foundation models encode clinical events as discrete event tokens from a fixed vocabulary and therefore cannot direc
arXiv:2606.24253v1 Announce Type: new Abstract: Modern VLMs and VLA systems commonly adopt off-the-shelf ViTs such as SigLIP2 as visual encoders, but diverse downstream requirements in latency, tempor
arXiv:2606.24516v1 Announce Type: new Abstract: A growing family of training-free solvers -- FlowDPS, FLOWER, PnP-Flow and their diffusion ancestors (DPS, DAPS) -- repurpose a pretrained flow-matching
arXiv:2606.24178v1 Announce Type: cross Abstract: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object clas
arXiv:2606.20697v1 Announce Type: new Abstract: AlphaEarth Foundations (AEF) unify global remote sensing foundation embeddings through multimodal self-supervised learning, but their pretraining focuse
arXiv:2606.22955v1 Announce Type: new Abstract: Large-scale pretrained foundation models have revolutionized general medical screening, but often falter on rare diseases because such conditions are un
arXiv:2606.23641v1 Announce Type: new Abstract: Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained vision-language representations, yet downs
arXiv:2606.20867v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models enable general-purpose robotic control via large-scale multimodal pretraining, yet their effectiveness under few-sho
arXiv:2509.21489v3 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into que
arXiv:2603.27048v3 Announce Type: replace Abstract: Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain l
arXiv:2606.22958v1 Announce Type: cross Abstract: Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis, such as classifier-free guidance, atte
arXiv:2606.21876v1 Announce Type: new Abstract: The Categorical Jacobian (CJ) of Zhang et al. (2024) reads protein contacts from a language model by perturbing every residue with every alternative ami
arXiv:2606.22938v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains
arXiv:2606.22383v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks whil
arXiv:2606.14970v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse dow
TSAuditor is a contamination auditing framework for time series foundation models that uses probe adaptation dynamics to detect when evaluation datasets may have been exposed during pretraining, valid
arXiv:2602.00945v2 Announce Type: replace-cross Abstract: LLMs are multilingual by training, yet their lingua franca is often English, reflecting English language dominance in pretraining. Other langu
arXiv:2606.12069v1 Announce Type: new Abstract: Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or
arXiv:2606.10657v1 Announce Type: new Abstract: Multiple-choice (MCQA) benchmarks are the standard for evaluating pretrained large language models, but their reliance on log-likelihood scoring makes t
As believers of open research, we are disappointed to see Anthropic silently degrading Fable 5 for AI development 'Any topic related to building pretraining pipelines, distributed training infrastruct
arXiv:2606.10196v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose
arXiv:2606.11096v1 Announce Type: new Abstract: Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing s
arXiv:2603.23183v2 Announce Type: replace-cross Abstract: Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generat
arXiv:2606.10929v1 Announce Type: cross Abstract: Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear di
arXiv:2606.10654v1 Announce Type: new Abstract: We investigate what self-supervised speech recognition models (S3Ms) learn about speaker groups (SGs). We examine several states of S3Ms: pretrained, fi
arXiv:2606.10653v1 Announce Type: new Abstract: Although pretrained text-to-image (T2I) generation models can produce high-quality images, they often fail to faithfully reflect the semantic intent of
arXiv:2606.07692v1 Announce Type: cross Abstract: Foundation models for wearable biosignals have matched or exceeded supervised specialists across a range of clinical tasks, yet all rely on modalities
arXiv:2606.09672v1 Announce Type: new Abstract: Ask a pretrained biomedical language model whether 'cortisol 28 ug/dL' and 'stock-market volatility' are related, and it returns a cosine similarity of
arXiv:2603.29824v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning methods such as LoRA enable efficient adaptation of large pretrained models, but often lag behind full fine-tuning i
arXiv:2606.07725v1 Announce Type: cross Abstract: Displacement time series from Global Navigation Satellite Systems (GNSS) are essential for a wide range of applications, including monitoring tectonic
arXiv:2509.24762v3 Announce Type: replace Abstract: Modeling event sequences of multiple event types with marked temporal point processes (MTPPs) provides a principled way to uncover governing dynamic
arXiv:2606.09052v1 Announce Type: cross Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision. Yet e
arXiv:2606.08788v1 Announce Type: new Abstract: Representation alignment with pretrained vision models has recently shown strong potential for accelerating diffusion transformer training. By aligning
arXiv:2606.09355v1 Announce Type: new Abstract: Robust inertial odometry is essential for various carriers when external sensing is unreliable. Learning-based methods reduce integration drift by captu
arXiv:2606.08679v1 Announce Type: cross Abstract: Pretrained models are often evaluated on multi-task leaderboards to measure their applicability in diverse contexts. However, current methods for aggr
arXiv:2606.09303v1 Announce Type: new Abstract: The rapid development of pretrained foundation models has enabled more general image segmentation. Multimodal large language models (MLLMs) have been wi
arXiv:2506.06891v3 Announce Type: replace Abstract: We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al., 20
arXiv:2606.09019v1 Announce Type: cross Abstract: Codec-based autoregressive (AR) speech language models have achieved strong text-to-speech (TTS) quality by modeling speech as sequences of discrete a