← Architectures
Deep Learning › Architectures ›

Transformers

9294 directly classified papers

Papers per year

Papers

End-to-End Entity-Predicate Association Reasoning for Dynamic Scene Graph Generation ICCV 2025
An Empirical Study of Autoregressive Pre-training from Videos ICCV 2025
HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting AAAI 2025
Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation ACL 2025
Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics ICCV 2025
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection NAACL 2025
Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax NAACL 2025
MojoBench: Language Modeling and Benchmarks for Mojo NAACL 2025
A Closer Look into Mixture-of-Experts in Large Language Models NAACL 2025
Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning NAACL 2025
MoLA: MoE LoRA with Layer-wise Expert Allocation NAACL 2025
Evaluation of Multilingual Image Captioning: How far can we get with CLIP models? NAACL 2025
Transformer-based Causal Language Models Perform Clustering NAACL 2025
MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding NAACL 2025
Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence NAACL 2025
NOTA: Multimodal Music Notation Understanding for Visual Large Language Model NAACL 2025
GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models NAACL 2025
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers NAACL 2025
Demystifying the Power of Large Language Models in Graph Generation NAACL 2025
Construction of NER Model in Ancient Chinese: Solution of EvaHan 2025 Challenge NAACL 2025
Simple Named Entity Recognition (NER) System with RoBERTa for Ancient Chinese NAACL 2025
Multi-Domain Ancient Chinese Named Entity Recognition Based on Attention-Enhanced Pre-trained Language Model NAACL 2025
Text-to-speech system for low-resource languages: A case study in Shipibo-Konibo (a Panoan language from Peru) NAACL 2025
Comparing representations of long clinical texts for the task of patient-note identification NAACL 2025
Lidar Waveforms are Worth 40x128x33 Words ICCV 2025