conftrace_

positional encoding

182 papers

Explore in graph

Also known as

PE

Co-occurring keywords

attention mechanism (4001) transformer architecture (1560) graph neural network (3962) large language model (13587) context window (73) neural network (6616) language model (4599) self-attention mechanism (352) vision transformer (1106) length extrapolation (31)

Papers

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding ICCV 2025
Disentangle to Decay: Linear Attention with Trainable Decay Factor COLING 2025
Hansel: Output Length Controlling Framework for Large Language Models AAAI 2025
A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation EMNLP 2025
Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method ACL 2025
DAPE-BR: Distance-Aware Positional Encoding for Mitigating Object Hallucination in LVLMs EMNLP 2025
Enhancing Transformers for Generalizable First-Order Logical Entailment ACL 2025
Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding ACL 2025
Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? A Petroglyph Revisited ACL 2025
Mind the Time: Temporally-Controlled Multi-Event Video Generation CVPR 2025
Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding ACL 2025
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices CVPR 2025
GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding CVPR 2025
HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation ACL 2025
PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodings EMNLP 2025
FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers ICCV 2025
Beyond Perspective: Neural 360-Degree Video Compression ICCV 2025
LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation ACL 2025
GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis using Convolutional Neural Networks WACV 2025
Spatially-Adaptive Hash Encodings for Neural Surface Reconstruction WACV 2025
On the Interplay between Positional Encodings, Morphological Complexity, and Word Order Flexibility IJCNLP 2025
Algebraic Positional Encodings NIPS 2024
Long-Context Language Modeling with Parallel Context Encoding ACL 2024
Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers CVPR 2024
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding NIPS 2024