Home Knowledge Base Pretrained Transformers

Pretrained Transformers

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers

arXiv:2605.24059v2 Announce Type: replace Abstract: We present a three-step recipe for identifying attention-head circuits in pretrained transformers. A per-head spectral signal -- the time-integrated participation ratio of each head's attention output -- ranks heads doing sustained content-dependent computation without labels or attribution gradients. A task-pattern screen filters this general indicator into a task-specific candidate circuit, and group ablation against a matched-random...

arXiv CS 5d ago

EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction

arXiv:2606.02971v1 Announce Type: new Abstract: Extracting reporting obligations from EU legislation is critical for assessing and reducing regulatory reporting burden. However, distinguishing reporting requirements from structurally similar provisions requires specialised legal understanding. Current legal NLP methods lack specialised datasets with clear guidelines and comparative evaluation of extraction paradigms and domain adaptation strategies.

arXiv CS 7d ago

Clustering Guided Domain-Specific Pretrained Foundation Model Very High-Resolution Arctic Remote Sensing

new Abstract: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM) by combining diversity-aware regional-scale image curation with masked autoencoder (MAE) self-supervised pretraining of a Vision Transformer (ViT) encoder for very-high-spatial-resolution (VHSR) satellite image analysis. Spectral and acquisition-metadata descriptors were used in a scalable affinity-propagation clustering workflow to select approximately 3 million chips from 267 TB of Vantor VHSR...

arXiv CS 9d ago

Clustering Guided Domain-Specific Pretrained Foundation Model for Very High-Resolution Arctic Remote Sensing

arXiv:2605.30467v2 Announce Type: replace Abstract: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM) by combining diversity-aware regional-scale image curation with masked autoencoder (MAE) self-supervised pretraining of a Vision Transformer (ViT) encoder for very-high-spatial-resolution (VHSR) satellite image analysis. Spectral and acquisition-metadata descriptors were used in a scalable affinity-propagation clustering workflow to select approximately 3...

arXiv CS 5d ago

Elastic ViTs from Pretrained Models without Retraining

arXiv:2510.17700v2 Announce Type: replace Abstract: Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deployment choices under real-world constraints. We introduce SnapViT: Single-shot network approximation for pruned Vision Transformers, a new post-pretraining structured pruning method that enables elastic inference across a continuum of compute budgets. Our approach efficiently combines gradient...

arXiv CS 9d ago

The Variance Brain Foundation Models Forgot: Third-Order Statistics Predict Cognition Where Billion-Parameter Models Fail

arXiv:2606.04010v1 Announce Type: cross Abstract: Brain foundation models (BFMs) are self-supervised Transformers pretrained on fMRI data. We posit that these models should capture each subject's cognitive performance from their fMRI signal.

arXiv CS 6d ago

Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks

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., 2023). To address the challenge of reward poisoning attacks targeting the DPT, we propose a novel adversarial training framework, called Adversarially Trained DPT (AT-DPT). Our method simultaneously trains a population of attackers to minimize the true reward of the DPT by poisoning environment...

arXiv CS 1d ago

From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

arXiv:2606.02559v1 Announce Type: new Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules. Existing replacement-based methods share two design constraints: full-layer granularity and contiguous selection. We argue that this is overly restrictive: in fact, redundancy in pretrained transformers is not confined to contiguous regions, nor does it evenly distribute between Attention...

arXiv CS 8d ago

TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics

Announce Type: replace Abstract: We present TokaMind, to our knowledge the first open-source foundation model for tokamak plasma dynamics, based on a Multi-Modal Transformer (MMT) and pretrained on heterogeneous diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model...

arXiv Physics 2d ago

TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics

Announce Type: replace-cross Abstract: We present TokaMind, to our knowledge the first open-source foundation model for tokamak plasma dynamics, based on a Multi-Modal Transformer (MMT) and pretrained on heterogeneous diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model...

arXiv CS 2d ago