conftrace_

Techniques

9,432 papers (36 classified directly here)

Subtopics · a paper can sit in several, so these overlap

Model Architecture (5,047) Pretraining (2,736) Attention (1,162) Normalization (434) Attention Mechanism (265)

Papers per year

1

1

3

4

2

9

12

33

95

225

447

788

914

1,131

1,059

1,342

1,450

1,375

541

'10

'15

'20

'25

Papers (including subtopics)

UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting CVPR 2025 UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation ICLR 2025 Uni-Sign: Toward Unified Sign Language Understanding at Scale ICLR 2025 UniSpeaker: A Unified Approach for Multimodality-driven Speaker Generation EMNLP 2025 UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines CVPR 2025 Universal Image Restoration Pre-training via Degradation Classification ICLR 2025 UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation ICLR 2025 Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues ICLR 2025 Unlocking the Potential of Model Calibration in Federated Learning ICLR 2025 Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model ICLR 2025 Unsupervised Anomaly Detection for Tabular Data Using Deep Noise Evaluation AAAI 2025 Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras ICCV 2025 Unveiling the Potential of BERT-family: A New Recipe for Building Scalable, General and Competitive Large Language Models ACL 2025 Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach CVPR 2025 UnZipLoRA: Separating Content and Style from a Single Image ICCV 2025 UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis ICCV 2025 Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting ICML 2025 UTBNLP at Semeval-2025 Task 11: Predicting Emotion Intensity with BERT and VAD-Informed Attention. SemEval 2025 UTF: Under-trained Tokens as Fingerprints —— a Novel Approach to LLM Identification ACL 2025 VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention AAAI 2025 VADE: Visual Attention Guided Hallucination Detection and Elimination ACL 2025 VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting AAAI 2025 Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs ACL 2025 VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models AAAI 2025 Video Language Model Pretraining with Spatio-temporal Masking CVPR 2025