{"total":52,"rows":[{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249,"area":null},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184,"area":null},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170,"area":null},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91,"area":null},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85,"area":null},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"area":null},{"id":"2302.07253","title":"Energy Transformer","created":"2023-02-14","cited_by_count":71,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2110.08743","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","created":"2021-10-17","cited_by_count":27,"area":null},{"id":"2409.03621","title":"Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers","created":"2024-09-05","cited_by_count":25,"area":null},{"id":"2402.02526","title":"CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition","created":"2024-02-04","cited_by_count":23,"area":"moe"},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2101.04547","title":"Of Non-Linearity and Commutativity in BERT","created":"2021-01-12","cited_by_count":16,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2509.09498","title":"SEDM: Selective Self-Evolving Distributed Memory for Agents","created":"2025-09-11","cited_by_count":16,"area":null},{"id":"2105.13471","title":"Inspecting the concept knowledge graph encoded by modern language models","created":"2021-05-27","cited_by_count":15,"area":null},{"id":"2106.04279","title":"Staircase Attention for Recurrent Processing of Sequences","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2207.03509","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2212.06011","title":"A Neural ODE Interpretation of Transformer Layers","created":"2022-12-12","cited_by_count":14,"area":null},{"id":"2109.07383","title":"RankNAS: Efficient Neural Architecture Search by Pairwise Ranking","created":"2021-09-15","cited_by_count":12,"area":null},{"id":"2104.03474","title":"Revisiting Simple Neural Probabilistic Language Models","created":"2021-04-08","cited_by_count":10,"area":null},{"id":"2410.14574","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","created":"2024-10-18","cited_by_count":9,"area":"moe"},{"id":"2309.06054","title":"Breaking through the learning plateaus of in-context learning in Transformer","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2306.01610","title":"Centered Self-Attention Layers","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2103.03457","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2505.00792","title":"Improving Routing in Sparse Mixture of Experts with Graph of Tokens","created":"2025-05-01","cited_by_count":4,"area":"moe"},{"id":"2604.12151","title":"Distinct mechanisms underlying in-context learning in transformers","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2202.12411","title":"TrimBERT: Tailoring BERT for Trade-offs","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2301.04761","title":"NarrowBERT: Accelerating Masked Language Model Pretraining and Inference","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2302.09304","title":"Interpretability in Activation Space Analysis of Transformers: A Focused Survey","created":"2023-01-22","cited_by_count":3,"area":"mechinterp"},{"id":"2310.01180","title":"Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2411.00052","title":"Larger models yield better results? Streamlined severity classification of ADHD-related concerns using BERT-based knowledge distillation","created":"2024-10-30","cited_by_count":3,"area":"distill"},{"id":"2510.16411","title":"Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures","created":"2025-10-18","cited_by_count":3,"area":"moe"},{"id":"2206.15312","title":"FL-Tuning: Layer Tuning for Feed-Forward Network in Transformer","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2409.13728","title":"Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2208.14580","title":"Efficient Sparsely Activated Transformers","created":"2022-08-31","cited_by_count":1,"area":"moe"},{"id":"2602.04491","title":"Greedy-Gnorm: A Gradient Matrix Norm-Based Alternative to Attention Entropy for Head Pruning","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2606.17522","title":"An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2106.11740","title":"LV-BERT: Exploiting Layer Variety for BERT","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2302.02123","title":"Greedy Ordering of Layer Weight Matrices in Transformers Improves Translation","created":"2023-02-04","cited_by_count":0,"area":null}],"next_cursor":null}