Knowledge catalogue
arXiv:2609.36661v1 Announce Type: new Abstract: Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a
arXiv:2609.34272v1 Announce Type: new Abstract: BF16 is now standard in large-scale pretraining, including in fused attention kernels such as FlashAttention, and these kernels are widely trusted. When
arXiv:2609.33178v1 Announce Type: new Abstract: Molecularly guided pathology foundation models (PFMs) exploit transcriptomic or proteomic information to enrich whole-slide image (WSI) representations,
arXiv:2609.34196v1 Announce Type: new Abstract: Modern vision-language models (VLMs) achieve strong performance across a broad range of multimodal tasks, yet still struggle with visual questions that
arXiv:2609.33707v1 Announce Type: cross Abstract: Vision-language-action (VLA) models adapt pretrained vision-language models (VLMs) for closed-loop robot control, transferring their perceptual and se
arXiv:2609.34253v1 Announce Type: new Abstract: Pretrained autoregressive Transformers represent a large sunk investment in compute. Existing conversion methods reuse that investment by changing eithe
arXiv:2609.33530v1 Announce Type: cross Abstract: Natural Language Understanding (NLU) plays a crucial role in various applications, yet its performance suffers from weaknesses in handling the complex
arXiv:2609.34866v1 Announce Type: new Abstract: Most post-training quantization pipelines fit each weight matrix to its pretrained counterpart, one matrix at a time. Whether that proxy tracks what an
arXiv:2609.32928v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar and RGB-D cameras can record cardiac and respiratory waveforms continuously and without contact, but labeled recordings r
arXiv:2609.33701v1 Announce Type: new Abstract: Pretrained biomedical vision-language models achieve strong zero-shot performance in biomedical image classification. However, downstream biomedical cla
arXiv:2609.32129v1 Announce Type: new Abstract: Pretrained robot policies offer strong manipulation skills but are typically limited to single-agent settings, where a robot acts in isolation. In this
arXiv:2609.31698v1 Announce Type: new Abstract: Most existing MEG and EEG (M/EEG) visual decoding methods align brain signals with a single global embedding extracted from a pretrained visual encoder,
arXiv:2603.09160v2 Announce Type: replace Abstract: Dense image captioning is critical for vision-language pretraining and for text-to-image generation, but scaling expert-quality annotations is prohi
arXiv:2609.34250v1 Announce Type: new Abstract: Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance t
arXiv:2509.23219v2 Announce Type: replace Abstract: Technical-domain benchmarks constructed from arXiv papers can overlap the same public text used in LLM pretraining. Auditing this risk at training-c
arXiv:2609.31180v1 Announce Type: cross Abstract: Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces.
arXiv:2609.30708v1 Announce Type: cross Abstract: A key challenge in medical image analysis is the scarcity of large annotated datasets for specific populations and diseases. As deep learning models r
arXiv:2609.31620v1 Announce Type: new Abstract: Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual re
arXiv:2604.05904v2 Announce Type: replace-cross Abstract: Gray-box RC models are widely used to enable energy-efficient model predictive control (MPC) in buildings. However, estimating RC parameters r
arXiv:2609.31206v1 Announce Type: new Abstract: Auroral spectrographs such as the Auroral Spectrograph In Skibotn (ASIS) record hundreds of thousands of emission spectra, but only a few hundred can be
arXiv:2609.29382v1 Announce Type: cross Abstract: Flow-matching Vision-Language-Action (VLA) models have emerged as a potential solution for generalist robot control, designed by combining a pretraine
I’ve been experimenting with whether Qwen3.8-Flash-Next’s pretrained PLE n-gram memory can improve a much smaller Qwen3.5-0.8B model. I trained the 0.8B setup with limited resources, mostly using free
arXiv:2609.29822v1 Announce Type: new Abstract: Robotic imitation learning often relies on external cameras, yet local interaction cues such as object proximity, contact onset, and grasp state are dif
arXiv:2609.28339v1 Announce Type: new Abstract: Pretrained generative Diffusion Transformers (DiTs) capture rich pixel-level visual and language-conditioned structure through large-scale image and vid
arXiv:2609.27455v1 Announce Type: new Abstract: World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pretrained Video Diffusion Models (VDMs). In
arXiv:2609.28314v1 Announce Type: new Abstract: Human teleoperators spend substantial time demonstrating behaviors that robots can already perform autonomously, limiting the scalability of data collec
arXiv:2609.28312v1 Announce Type: cross Abstract: We present VGM-VS, a visual servoing method built on a pretrained feed-forward visual geometry model. Given the current view and a reference image cap
arXiv:2609.25775v1 Announce Type: new Abstract: Recent advances in generative video models have enabled the synthesis of visually realistic content, posing significant challenges to synthetic video de
arXiv:2609.25008v1 Announce Type: new Abstract: I pretrained a language model end-to-end in Rust - alone, with no team, no PyTorch, and no Python in the training path - for $164 in rented GPU time. I
arXiv:2609.25081v1 Announce Type: new Abstract: We describe ufakzeka-1, a 151M-parameter (182M with embeddings) decoder-only Turkish language model pretrained from scratch on 13.5B tokens of openly li
arXiv:2609.23924v1 Announce Type: new Abstract: Pretrained EEG foundation models are increasingly proposed as general-purpose encoders for brain-computer interfaces, yet recent benchmarks disagree abo
arXiv:2609.24111v1 Announce Type: cross Abstract: Test-time adaptation (TTA) addresses distribution shift using only unlabeled test data. Existing methods typically adapt pretrained models by updating
arXiv:2609.23460v1 Announce Type: new Abstract: Deep learning has advanced automated electrocardiogram (ECG) diagnosis, but the field's most accurate models, foundation models pretrained on millions o
arXiv:2609.24064v1 Announce Type: new Abstract: New Guinea is the world's richest island flora (~2,856 orchid species), yet most species are represented by only a handful of photographs, far fewer tha
arXiv:2609.24839v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models enable efficient geometry estimation from sparse images, but their pretrained nature can make them vulnerable to d
arXiv:2603.26556v3 Announce Type: replace-cross Abstract: Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference
arXiv:2609.18207v1 Announce Type: cross Abstract: Reinforcement learning fine-tuning on top of large, pretrained Vision-Language-Action (VLA) models offers promise for highly reliable robot deployment
arXiv:2609.18197v1 Announce Type: new Abstract: Humanoid whole-body manipulation requires coordinated whole-body dynamics, yet large-scale trajectories from a target robot are expensive to collect and
arXiv:2404.00727v3 Announce Type: replace Abstract: All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR m
arXiv:2609.15702v1 Announce Type: new Abstract: Pretrained score-based diffusion models provide strong unconditional priors, yet enforcing measurement or physics consistency in inverse problems is oft
arXiv:2506.24092v3 Announce Type: replace Abstract: Adapting large pretrained vision models to medical image classification is often limited by memory, computation, and task-specific specializations.
arXiv:2609.15781v1 Announce Type: cross Abstract: Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to
arXiv:2609.06960v1 Announce Type: new Abstract: Invasive neural recordings provide high-fidelity measurements of brain activity, with signals such as intracranial EEG (iEEG) and intracortical spiking
arXiv:2609.05834v1 Announce Type: new Abstract: World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the r
arXiv:2609.10021v1 Announce Type: new Abstract: Vision--language--action (VLA) models acquire broad generalization through large-scale pretraining, yet adapting them to a new task and robot embodiment
arXiv:2609.08224v1 Announce Type: new Abstract: Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained vision-language
An Anthropic PBC researcher has resigned over concerns that artificial intelligence labs are “gambling with our lives.” Jacob Coxon was part of the company’s AI pretraining team until today. He announ
arXiv:2407.03463v2 Announce Type: replace Abstract: In the realm of self-supervised learning (SSL), conventional wisdom has gravitated towards the utility of massive, general domain datasets for pretr
arXiv:2609.06385v1 Announce Type: new Abstract: Pretrained 3D generative models produce detailed geometry and appearance but are primarily designed for object-centric generation within a limited spati
arXiv:2609.04461v1 Announce Type: cross Abstract: Foundation models are beginning to reshape brain-signal analysis by moving the field beyond task-specific decoding pipelines toward reusable models pr
arXiv:2609.04707v1 Announce Type: cross Abstract: Wireless foundation models (WFMs) have emerged as a promising approach for learning reusable representations from large-scale wireless data and adapti
arXiv:2609.03177v1 Announce Type: new Abstract: Frontier large language models (LLMs) have become attractive priors for optimization due to their large-scale pretraining that enables them to navigate
arXiv:2609.03702v1 Announce Type: new Abstract: General-purpose code embeddings power tools for code search, classification, and retrieval. Compact transformer encoders for code typically rely on eith
arXiv:2609.02187v1 Announce Type: new Abstract: General-purpose vision-language models (VLMs) now support strong visual recognition, instruction following, and generation. However, most pretrained vis
arXiv:2609.00454v1 Announce Type: new Abstract: Pretrained transformer-based language models achieve strong performance across a wide range of NLP tasks but remain limited in encoding geo-locational s
arXiv:2603.16792v2 Announce Type: replace-cross Abstract: Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained
arXiv:2512.03400v2 Announce Type: replace-cross Abstract: We study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers, using Rubik's C
arXiv:2608.28878v1 Announce Type: cross Abstract: This paper develops a hybrid offline-online multi-agent reinforcement learning framework based on decision transformers. The policy is first pretraine
arXiv:2608.29426v1 Announce Type: cross Abstract: Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomo
arXiv:2608.28308v1 Announce Type: new Abstract: We study the scaling behavior of learning rate and batch size in pretraining dense large language models on English-prevalent corpora. Beyond scaling ex