conftrace_
← Models
Deep Learning › Models ›

Transformers

1,816 papers

Papers per year

Papers

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning NIPS 2024
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains NIPS 2024
Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz NIPS 2024
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers NIPS 2024
$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes NIPS 2024
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion NIPS 2024
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting NIPS 2024
Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts NIPS 2024
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series NIPS 2024
Transformers Represent Belief State Geometry in their Residual Stream NIPS 2024
Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context NIPS 2024
Understanding Transformer Reasoning Capabilities via Graph Algorithms NIPS 2024
Humanoid Locomotion as Next Token Prediction NIPS 2024
Compact Proofs of Model Performance via Mechanistic Interpretability NIPS 2024
SongCreator: Lyrics-based Universal Song Generation NIPS 2024
Non-asymptotic Convergence of Training Transformers for Next-token Prediction NIPS 2024
Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs NIPS 2024
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction NIPS 2024
In-Context Learning with Representations: Contextual Generalization of Trained Transformers NIPS 2024
Transcendence: Generative Models Can Outperform The Experts That Train Them 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
Molecule Design by Latent Prompt Transformer NIPS 2024
DeTrack: In-model Latent Denoising Learning for Visual Object Tracking NIPS 2024