{"total":32,"rows":[{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2408.08696","title":"Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling","created":"2024-08-16","cited_by_count":47,"area":null},{"id":"2507.11851","title":"Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential","created":"2025-07-16","cited_by_count":47,"area":null},{"id":"2511.14617","title":"Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning","created":"2025-11-18","cited_by_count":25,"area":null},{"id":"2509.18824","title":"Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2502.01662","title":"Fast Large Language Model Collaborative Decoding via Speculation","created":"2025-02-01","cited_by_count":12,"area":null},{"id":"2506.15556","title":"PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction","created":"2025-06-18","cited_by_count":8,"area":null},{"id":"2512.21323","title":"Parallel Token Prediction for Language Models","created":"2025-12-24","cited_by_count":7,"area":null},{"id":"2601.21708","title":"FBS: Modeling Native Parallel Reading inside a Transformer","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2502.18890","title":"TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2410.01103","title":"Approximately Aligned Decoding","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2602.11877","title":"Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2606.11552","title":"Teaching Diffusion to Speculate Left-to-Right","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2512.08537","title":"Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2607.19510","title":"Total Variation Distance Estimation in Autoregressive Models","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2407.19401","title":"Towards Secure and Private AI: A Framework for Decentralized Inference","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2510.13668","title":"STAR: Decode-Phase Rescheduling for LLM Inference","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2603.18599","title":"SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2608.27339","title":"Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2510.11958","title":"Direct Multi-Token Decoding","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2603.13438","title":"Draft-and-Target Sampling for Video Generation Policy","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.17942","title":"Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.25463","title":"CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.28049","title":"Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2606.10935","title":"CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.29223","title":"Depth Exploration for LLM Decoding","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.05148","title":"Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.12913","title":"Decoupled Contrastive Decoding via Expert-Aligned Drafting","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.28099","title":"Speculative Probing: LLM Monitoring at Speculative-Decoding Cost","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.16648","title":"GrowMTP: Can RL Grow Its Own Draft Head?","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}