{"total":19,"rows":[{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90,"area":null},{"id":"2503.17069","title":"PVChat: Personalized Video Chat with One-Shot Learning","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2504.19414","title":"GMAR: Gradient-Driven Multi-Head Attention Rollout for Vision Transformer Interpretability","created":"2025-04-28","cited_by_count":11,"area":null},{"id":"2605.07363","title":"MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":7,"area":null},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"area":null},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2512.17601","title":"HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2603.23998","title":"Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2510.04331","title":"DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2603.10685","title":"A$^2$-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2607.10992","title":"LoSA-Net: A Localized and Scale-Adaptive Network for Boundary-Sensitive Prediction of Perineural Invasion in 3D MRI","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2510.23052","title":"Knocking-Heads Attention","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2505.02351","title":"Opt-GPTQ: An Optimized GPTQ Combining Sparse Attention and Quantization Techniques","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2603.08343","title":"Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2607.10988","title":"MMA-Former: Multi-Window Mixture-of-Head Attention Transformer for Adaptive PNI Prediction in 3D MRI","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.23733","title":"VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.38832","title":"Scaling Parameter and Context in Attention: Native Sparse Attention from Mixture-of-Head","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39188","title":"Attention Function as an Intrinsic Inductive Bias: How Models' Behavior Diverges in Novel Contexts","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}