conftrace_
← Architectures
Deep Learning › Architectures ›

Transformers

9,294 papers

Papers per year

Papers

FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model NIPS 2024
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction NIPS 2024
A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning NIPS 2024
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers NIPS 2024
In-Context Learning with Representations: Contextual Generalization of Trained Transformers NIPS 2024
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking NIPS 2024
On Feature Learning in Structured State Space Models NIPS 2024
Local to Global: Learning Dynamics and Effect of Initialization for Transformers NIPS 2024
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention NIPS 2024
Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning NIPS 2024
Base of RoPE Bounds Context Length NIPS 2024
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers NIPS 2024
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers NIPS 2024
Instruction Embedding: Latent Representations of Instructions Towards Task Identification NIPS 2024
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs NIPS 2024
DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching NIPS 2024
Decomposable Transformer Point Processes NIPS 2024
Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge NIPS 2024
Molecule Design by Latent Prompt Transformer NIPS 2024
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding NIPS 2024
Revisiting motion information for RGB-Event tracking with MOT philosophy NIPS 2024
Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers NIPS 2024
A Theoretical Understanding of Self-Correction through In-context Alignment NIPS 2024
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos NIPS 2024
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis NIPS 2024