{"total":57,"rows":[{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"area":"moe"},{"id":"2506.23266","title":"Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging","created":"2025-06-29","cited_by_count":28,"area":"moe"},{"id":"2509.16105","title":"DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning","created":"2025-09-19","cited_by_count":26,"area":"moe"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2509.10377","title":"Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs","created":"2025-09-12","cited_by_count":25,"area":"moe"},{"id":"2505.19645","title":"MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE","created":"2025-05-26","cited_by_count":19,"area":"moe"},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2411.08982","title":"Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection","created":"2024-11-13","cited_by_count":16,"area":"moe"},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10,"area":null},{"id":"2604.04356","title":"REAM: Merging Improves Pruning of Experts in LLMs","created":"2026-04-06","cited_by_count":10,"area":"moe"},{"id":"2505.03531","title":"Faster MoE LLM Inference for Extremely Large Models","created":"2025-05-06","cited_by_count":9,"area":"moe"},{"id":"2508.05257","title":"MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs","created":"2025-08-07","cited_by_count":9,"area":"moe"},{"id":"2509.08342","title":"Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism","created":"2025-09-10","cited_by_count":9,"area":"moe"},{"id":"2511.04805","title":"PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference","created":"2025-11-06","cited_by_count":9,"area":"moe"},{"id":"2603.06003","title":"EvoESAP: Non-Uniform Expert Pruning for Sparse MoE","created":"2026-03-06","cited_by_count":9,"area":"moe"},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2602.09316","title":"Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density","created":"2026-02-10","cited_by_count":7,"area":"moe"},{"id":"2508.17467","title":"MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models","created":"2025-08-24","cited_by_count":6,"area":"mllm"},{"id":"2509.02753","title":"LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference","created":"2025-09-02","cited_by_count":6,"area":"moe"},{"id":"2606.15716","title":"How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle","created":"2026-06-14","cited_by_count":6,"area":"moe"},{"id":"2603.09983","title":"MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios","created":"2026-02-12","cited_by_count":5,"area":"moe"},{"id":"2505.13345","title":"Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference","created":"2025-05-19","cited_by_count":4,"area":"moe"},{"id":"2603.02217","title":"Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2603.18297","title":"Path-Constrained Mixture-of-Experts","created":"2026-03-18","cited_by_count":4,"area":"moe"},{"id":"2509.22299","title":"HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space","created":"2025-09-26","cited_by_count":3,"area":"moe"},{"id":"2602.07616","title":"SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models","created":"2026-02-07","cited_by_count":3,"area":"moe"},{"id":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"area":"moe"},{"id":"2606.05538","title":"Less is MoE: Trimming Experts in Domain-Specialist Language Models","created":"2026-06-04","cited_by_count":2,"area":"moe"},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2601.11616","title":"Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective","created":"2026-01-09","cited_by_count":1,"area":"moe"},{"id":"2604.10603","title":"MoEITS: A Green AI approach for simplifying MoE-LLMs","created":"2026-04-12","cited_by_count":1,"area":"moe"},{"id":"2605.09281","title":"TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling","created":"2026-05-10","cited_by_count":1,"area":"moe"},{"id":"2605.13997","title":"HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts","created":"2026-05-13","cited_by_count":1,"area":"moe"},{"id":"2605.14438","title":"BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE","created":"2026-05-14","cited_by_count":1,"area":"moe"},{"id":"2605.28207","title":"Pruning and Distilling Mixture-of-Experts into Dense Language Models","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2605.29350","title":"ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression","created":"2026-05-28","cited_by_count":1,"area":"moe"},{"id":"2606.29982","title":"Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference","created":"2026-06-29","cited_by_count":1,"area":"moe"},{"id":"2607.01444","title":"On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain","created":"2026-07-01","cited_by_count":1,"area":"moe"},{"id":"2608.15299","title":"MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation","created":"2026-08-15","cited_by_count":1,"area":"moe"},{"id":"2505.06481","title":"QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration","created":"2025-05-10","cited_by_count":0,"area":"moe"},{"id":"2512.21788","title":"InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation","created":"2025-12-25","cited_by_count":0,"area":"diffusion"},{"id":"2601.13563","title":"ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits","created":"2026-01-20","cited_by_count":0,"area":"moe"},{"id":"2605.16349","title":"Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2606.00079","title":"BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization","created":"2026-05-22","cited_by_count":0,"area":"moe"},{"id":"2606.18304","title":"Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression","created":"2026-06-16","cited_by_count":0,"area":"moe"},{"id":"2606.27866","title":"FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models","created":"2026-06-26","cited_by_count":0,"area":"moe"},{"id":"2607.05116","title":"Communication-Aware Placement and Pruning for Efficient Mixture-of-Experts Inference","created":"2026-07-06","cited_by_count":0,"area":"moe"},{"id":"2608.05303","title":"EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.26650","title":"Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs","created":"2026-08-27","cited_by_count":0,"area":"moe"},{"id":"2609.01024","title":"PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2609.06076","title":"Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment","created":"2026-09-05","cited_by_count":0,"area":"moe"},{"id":"2609.30465","title":"RAZOR: Pruning Replaceable Experts in LLMs","created":"2026-09-24","cited_by_count":0,"area":"moe"},{"id":"2609.33614","title":"EAT: Expert Account Tracker for Efficient MoE Inference","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2609.36222","title":"BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.38823","title":"DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference","created":"2026-09-30","cited_by_count":0,"area":"moe"}],"next_cursor":null}