Knowledge catalogue
arXiv:2608.14054v1 Announce Type: new Abstract: Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time
arXiv:2608.13973v1 Announce Type: new Abstract: Recent foundation model-based methods have endowed RGB images with strong zero-shot anomaly detection (ZSAD) through vision-language pretraining. Howeve
arXiv:2608.14229v1 Announce Type: new Abstract: Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform g
arXiv:2608.12997v1 Announce Type: new Abstract: Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffusion prior, but latent SDS often pr
arXiv:2606.16454v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with l
arXiv:2604.03181v2 Announce Type: replace-cross Abstract: Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing pol
arXiv:2603.17450v2 Announce Type: replace-cross Abstract: Sequential Recommendation (SR) in multimodal settings typically relies on small frozen pretrained encoders, which limits semantic capacity and
arXiv:2603.02462v2 Announce Type: replace-cross Abstract: A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a give
arXiv:2608.10690v1 Announce Type: new Abstract: Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus
arXiv:2608.10605v1 Announce Type: cross Abstract: In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage sel
arXiv:2608.10295v1 Announce Type: cross Abstract: Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy.
arXiv:2608.10989v1 Announce Type: cross Abstract: Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with differe
arXiv:2608.11204v1 Announce Type: cross Abstract: Learning reliable surgical manipulation policies is bottlenecked by the scarcity of action-labeled demonstrations: teleoperated surgical robot (e.g.,
arXiv:2603.12231v3 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual fe
arXiv:2608.07982v1 Announce Type: new Abstract: Vision foundation models (VFMs) such as DINO are pretrained for single-image representation, whereas remote sensing change detection requires reasoning
arXiv:2608.07596v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models transform representations from pretrained vision-language models (VLMs) into robot actions, yet the interface that
arXiv:2608.09331v1 Announce Type: cross Abstract: Brain-to-audio reconstruction is limited by prior domination: when a pretrained generator is conditioned on a weak neural signal, it produces realisti
arXiv:2608.09006v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks. However, fine-tuning LLMs for Gloss-Free Sign Language Tra
arXiv:2603.22213v2 Announce Type: replace-cross Abstract: While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data
arXiv:2608.08290v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) repurposes a pretrained CLIP encoder for dense prediction without additional labeled supervision. Existing
arXiv:2608.09052v1 Announce Type: cross Abstract: Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA. H
arXiv:2608.09287v1 Announce Type: cross Abstract: Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically in
arXiv:2608.09537v1 Announce Type: new Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model t
arXiv:2608.06582v1 Announce Type: new Abstract: Flow-based generative models can efficiently produce candidate structures for crystal structure prediction (CSP), but their pretrained objectives do not
arXiv:2608.06613v1 Announce Type: cross Abstract: Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remai
A few months ago, I had the idea of making a LLM from scratch as a personal project (for learning and partly for improving my resume). Since I learned a lot from other posts on here over the past year
Impressive new paper from Meta. (bookmark it) Scaling laws assume model size and training data act on loss independently. This work introduces Skaling law, which couples capacity and data through a si
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as interchangeable interfaces. Using pretrained language mode
arXiv:2608.07267v1 Announce Type: new Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies t
arXiv:2608.07341v1 Announce Type: cross Abstract: Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorized. extbf{Contamination mitigation
arXiv:2608.05999v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. H
arXiv:2608.05151v1 Announce Type: cross Abstract: Wastewater operators need answers grounded in how their plant's variables interact and how fast effects propagate, not in generic pretraining text, wh
arXiv:2608.06252v1 Announce Type: cross Abstract: Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL). Automatic BdSL recognition on personal devices c
arXiv:2608.05207v1 Announce Type: new Abstract: Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discov
arXiv:2608.04833v1 Announce Type: new Abstract: RGB-infrared (RGB-IR) object detection benefits from complementary visible and thermal cues, but effective fusion remains challenging under illumination
arXiv:2603.18774v2 Announce Type: replace Abstract: Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong sc
arXiv:2603.14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of pretrained Di
arXiv:2608.03015v1 Announce Type: cross Abstract: Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as
arXiv:2608.03494v1 Announce Type: new Abstract: Vocabulary extension is an efficient way to adapt pretrained large language models (LLMs) to new languages, but the initialization of newly added token
arXiv:2608.03791v1 Announce Type: new Abstract: Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpo
arXiv:2608.03517v1 Announce Type: new Abstract: Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to
arXiv:2608.02829v1 Announce Type: new Abstract: Model families train every size from scratch. Can a pretrained large model be converted into a smaller sibling? We characterize the 1.4B->410M conversio
arXiv:2608.01725v1 Announce Type: cross Abstract: Modern computing and networking infrastructure emits telemetry continuously, yet operators convert it into decisions with a separate predictor per tas
arXiv:2608.01663v1 Announce Type: new Abstract: Promptable segmentation foundation models (FMs) such as SAM3 and Medical SAM3 promise few-shot, interactively-specified segmentation for medical imaging
arXiv:2608.02124v1 Announce Type: cross Abstract: Vision-language models (VLMs) remain unreliable when predictions require fine-grained visual evidence. We identify a previously overlooked cause: spec
arXiv:2608.01013v1 Announce Type: new Abstract: Adapting a pretrained vision-language-action (VLA) policy to a new robot usually assumes embodiment-specific demonstrations. This assumption is especial
arXiv:2608.00582v1 Announce Type: new Abstract: Pretrained byte-level BPE tokenizers can segment underrepresented languages inefficiently. Replacing a tokenizer changes the meaning of nearly every tok
arXiv:2607.29337v1 Announce Type: cross Abstract: Background and Objective: Generating realistic medical images with anatomically accurate segmentation masks helps address the shortage of annotated da
arXiv:2607.28611v1 Announce Type: new Abstract: Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibi
openPangu-2.0-Pro is an MoE model trained on Ascend. The model has 505B total parameters and 18B activated parameters. Its context length is 512k. The total pretraining data contains 34T tokens. Durin
arXiv:2607.23377v1 Announce Type: cross Abstract: The largest machine learning models in particle physics are also the most expensive to train, yet the return on scaling a given architecture cannot be
arXiv:2607.27680v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become the standard mechanism for fine-tuning large pretrained models, yet its statistical properties remain only parti
arXiv:2607.27982v1 Announce Type: new Abstract: Rigging is inherently task-dependent because the same mesh may require different skeletons and deformation behaviors across animation tasks. In practice
arXiv:2607.26247v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) fine-tunes large pretrained models at a fraction of the cost of full fine-tuning, but its performance depends strongly on how
arXiv:2607.26237v1 Announce Type: new Abstract: Pretrained diffusion models generate realistic images but are constrained by the statistical biases of their training data, limiting their ability to pr
arXiv:2603.27519v2 Announce Type: replace Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organ
arXiv:2603.09971v2 Announce Type: replace Abstract: We present TiPToP, a modular manipulation system that integrates pretrained foundation models with a GPU-accelerated Task and Motion Planner to solv
arXiv:2607.25479v1 Announce Type: cross Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text
arXiv:2607.24848v1 Announce Type: cross Abstract: Pretrained molecular encoders are commonly evaluated through downstream prediction, but predictive accuracy alone does not establish that a learned re
arXiv:2607.11509v2 Announce Type: replace Abstract: Medical image anomaly detection remains challenging because networks pretrained on natural images often exhibit limited adaptability to medical imag