Knowledge catalogue
arXiv:2602.18020v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demons
arXiv:2510.16023v2 Announce Type: replace Abstract: Linear polymers, macromolecules formed from monomers covalently bonded into continuous chains, underpin countless technologies and are indispensable
arXiv:2506.01850v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual enco
arXiv:2602.00541v2 Announce Type: replace Abstract: Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical me
arXiv:2606.06835v1 Announce Type: new Abstract: The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most l
arXiv:2606.06155v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models leverage the rich world knowledge of pretrained vision-language models (VLMs) to enable instruction-following robo
arXiv:2606.06461v1 Announce Type: new Abstract: Leveraging prior knowledge from pretrained policies, foundation models, or human operators offers an efficient alternative to learning robot skills from
arXiv:2606.05506v1 Announce Type: new Abstract: We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileg
arXiv:2601.21700v3 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining dat
arXiv:2602.23214v2 Announce Type: replace Abstract: Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained gen
arXiv:2505.11166v3 Announce Type: replace-cross Abstract: Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-
arXiv:2606.03217v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become a widely used mechanism for eliciting multi-step reasoning in large language models by generating intermed
arXiv:2606.03657v1 Announce Type: new Abstract: Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a functi
arXiv:2601.22841v2 Announce Type: replace Abstract: Large-scale foundation models (FMs) in remote sensing (RS) (denoted as RS FMs) are developed following paradigms established in computer vision (CV)
arXiv:2606.03713v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder
arXiv:2303.15619v2 Announce Type: replace-cross Abstract: The choice of which tokens to mask is a central, under-examined design decision in masked language modeling (MLM). Standard pretraining masks
arXiv:2411.15240v5 Announce Type: replace-cross Abstract: Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, r
arXiv:2606.02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robot
arXiv:2606.01909v1 Announce Type: cross Abstract: We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and
arXiv:2504.03635v4 Announce Type: replace Abstract: Reasoning is a core capability of language models (LMs), yet it remains unclear how much model capacity is necessary to support reasoning during pre
arXiv:2606.00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most exi
arXiv:2606.00703v1 Announce Type: cross Abstract: Low-precision pretraining (FP8, MXFP4, NVFP4) is now standard for frontier language models, yet the literature is almost entirely achievability -- alg
arXiv:2606.01702v1 Announce Type: cross Abstract: Deep learning in computer-aided design (CAD) remains fundamentally constrained by the data scarcity challenge: authentic CAD data is difficult to coll
arXiv:2602.08689v2 Announce Type: replace Abstract: Diffusion models generate samples through an iterative denoising process guided by a pretrained neural network. Once the denoiser is fixed, the samp
arXiv:2512.10339v2 Announce Type: replace Abstract: Inference-time steering adapts pretrained diffusion and flow models to new tasks without retraining, often utilizing ratio-of-densities construction
arXiv:2606.00284v1 Announce Type: new Abstract: While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naive finetuning on targeted data erodes existing
arXiv:2606.02277v1 Announce Type: new Abstract: Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should gu
arXiv:2606.00512v1 Announce Type: new Abstract: In many modern machine learning pipelines, abundant pretrained representations serve as noisy proxy covariates, while task-specific labels remain scarce
arXiv:2605.24470v2 Announce Type: replace Abstract: Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an im
arXiv:2606.02237v1 Announce Type: new Abstract: Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distribution
arXiv:2605.30748v1 Announce Type: cross Abstract: We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion d
arXiv:2605.30393v1 Announce Type: cross Abstract: Public numeric benchmarks appear in pretraining, so an evaluation that conditions on a date may be measuring memorized recall rather than out-of-sampl
arXiv:2605.30991v1 Announce Type: cross Abstract: Inference-time reward alignment steers pretrained diffusion and flow-based generative models to satisfy user-specified rewards without retraining. Rec
which is NOT new; see this quote from 5 years ago. the fact that all this is still true says a lot. This was right five years ago, and still is: “Large scale pretrained models are certainly likely to
arXiv:2506.00175v5 Announce Type: replace-cross Abstract: Modern AI systems are typically developed through multiple stages-pretraining, fine-tuning rounds, and subsequent adaptation or alignment, whe
arXiv:2603.01006v2 Announce Type: replace-cross Abstract: REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher
arXiv:2605.29628v1 Announce Type: cross Abstract: Contrastive Language-Audio Pretraining (CLAP) models are widely used for audio understanding and support modality-agnostic condition swapping in many
arXiv:2605.29283v1 Announce Type: cross Abstract: Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single aver
arXiv:2601.14758v4 Announce Type: replace-cross Abstract: Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) has emerged as a cost-effective way to overcome the
arXiv:2605.30257v1 Announce Type: new Abstract: We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposi
arXiv:2605.28864v1 Announce Type: new Abstract: The Cognitive Categorical Transformer (CCT) is a 306M-parameter architecture that augments a pretrained GPT-2 Small backbone with cognitively grounded c
arXiv:2605.29691v1 Announce Type: new Abstract: Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs) whose pretrained representations support a wide range of d
arXiv:2603.10961v2 Announce Type: replace Abstract: Wearable accelerometers enable large-scale health monitoring, yet learning robust human-activity representations has been constrained by scarce labe
arXiv:2605.28526v1 Announce Type: new Abstract: Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the
arXiv:2601.19302v3 Announce Type: replace Abstract: This paper introduces Formula Prompting (FP) and Formula-One Prompting (F-1), two single-call methods that elicit governing equations before solving
arXiv:2605.27678v1 Announce Type: new Abstract: Foundation model training is becoming multimodal, from post-training pipelines to large-scale pretraining. As modality coverage broadens, context window
arXiv:2601.06329v2 Announce Type: replace-cross Abstract: Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving a
arXiv:2509.25582v3 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks w
arXiv:2605.28669v1 Announce Type: cross Abstract: Sense representations (explicit, per-token meaning decompositions) are useful for disambiguation, steering, and cross-lingual alignment, but existing
arXiv:2603.07860v2 Announce Type: replace Abstract: Pretrained diffusion models are effective priors for Bayesian inverse problems, but posterior sampling with these priors is often costly because dat
arXiv:2605.26332v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been
arXiv:2605.27286v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining. However, most existing T
arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-trai
arXiv:2602.17234v2 Announce Type: replace Abstract: Backtesting LLMs on resolved events assumes models reason only from pre-cutoff knowledge, yet pretrained models inevitably leak post-cutoff knowledg
arXiv:2605.24684v1 Announce Type: cross Abstract: Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretraine
arXiv:2605.25765v1 Announce Type: cross Abstract: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attracti
arXiv:2605.25354v1 Announce Type: new Abstract: While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamical
arXiv:2605.25477v1 Announce Type: cross Abstract: The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demons
arXiv:2605.24911v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-au
arXiv:2605.23033v1 Announce Type: cross Abstract: Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct