conftrace_

causal attention

21 papers

Explore in graph

Co-occurring keywords

large language model (13587) positional encoding (182) attention mechanism (4001) sentence embedding (502) autoregressive language model (58) autoregressive model (456) speech enhancement (581) image synthesis (603) representation learning (6206) transformer architecture (1560)

Papers

Hybrid Autoregressive-Diffusion Model for Real-Time Sign Language Production ACL 2026
Causality Matters: How Temporal Information Emerges in Video Language Models AAAI 2026
Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER ACL 2026
KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs ACL 2026
Prompt Tuning Can Simply Adapt Large Language Models to Text Encoders NAACL 2025
Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings COLING 2025
Holistic Tokenizer for Autoregressive Image Generation ICCV 2025
Identifying and Mitigating Position Bias of Multi-image Vision-Language Models CVPR 2025
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer ICCV 2025
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs ACL 2025
Mitigating Object Hallucination via Concentric Causal Attention NIPS 2024
EDC: Effective and Efficient Dialog Comprehension For Dialog State Tracking NAACL 2024
CausalNET: Unveiling Causal Structures on Event Sequences by Topology-Informed Causal Attention IJCAI 2024
Chain and Causal Attention for Efficient Entity Tracking EMNLP 2024
Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection CVPR 2024
Improving Input-label Mapping with Demonstration Replay for In-context Learning EMNLP 2023
Causality-Guided Multi-Memory Interaction Network for Multivariate Stock Price Movement Prediction ACL 2023
Monoaural Speech Enhancement Using a Nested U-Net with Two-Level Skip Connections INTERSPEECH 2022
Transformer Language Models without Positional Encodings Still Learn Positional Information EMNLP 2022
Causal Attention for Unbiased Visual Recognition ICCV 2021
Lightweight Causal Transformer with Local Self-Attention for Real-Time Speech Enhancement INTERSPEECH 2021