{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2410.04417","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","created":"2024-10-06","cited_by_count":391},{"id":"2408.15664","title":"Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts","created":"2024-08-28","cited_by_count":205},{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69},{"id":"2411.10803","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","created":"2024-11-16","cited_by_count":68},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60},{"id":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46},{"id":"2408.10284","title":"AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference","created":"2024-08-19","cited_by_count":42},{"id":"2310.02410","title":"Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness","created":"2023-10-03","cited_by_count":34},{"id":"2410.01264","title":"Backdooring Vision-Language Models with Out-Of-Distribution Data","created":"2024-10-02","cited_by_count":33},{"id":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32},{"id":"2409.18938","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","created":"2024-09-27","cited_by_count":30},{"id":"2509.01552","title":"Variation-aware Vision Token Dropping for Faster Large Vision-Language Models","created":"2025-09-01","cited_by_count":27},{"id":"2411.03312","title":"Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters","created":"2024-11-05","cited_by_count":25},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25},{"id":"2504.15299","title":"D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving","created":"2025-04-17","cited_by_count":20},{"id":"2410.17954","title":"ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling","created":"2024-10-23","cited_by_count":19},{"id":"2601.22674","title":"VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration","created":"2026-01-30","cited_by_count":18},{"id":"2408.05430","title":"HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou","created":"2024-08-10","cited_by_count":16},{"id":"2412.10925","title":"Video Representation Learning with Joint-Embedding Predictive Architectures","created":"2024-12-14","cited_by_count":15},{"id":"2503.15798","title":"Mixture of Lookup Experts","created":"2025-03-20","cited_by_count":12},{"id":"2503.16980","title":"VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models","created":"2025-03-21","cited_by_count":12},{"id":"2506.15724","title":"MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference","created":"2025-06-06","cited_by_count":12},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11},{"id":"2503.06823","title":"eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference","created":"2025-03-10","cited_by_count":11},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10},{"id":"2411.16550","title":"Representation Collapsing Problems in Vector Quantization","created":"2024-11-25","cited_by_count":10},{"id":"2505.22918","title":"Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape","created":"2025-05-28","cited_by_count":10},{"id":"2506.13329","title":"EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization","created":"2025-06-16","cited_by_count":10},{"id":"2512.12560","title":"StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding","created":"2025-12-14","cited_by_count":10},{"id":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10},{"id":"2405.15052","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","created":"2024-05-23","cited_by_count":8},{"id":"2410.05315","title":"PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms","created":"2024-10-05","cited_by_count":8},{"id":"2508.03351","title":"SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models","created":"2025-08-05","cited_by_count":8},{"id":"2512.13525","title":"Janus: Disaggregating Attention and Experts for Scalable MoE Inference","created":"2025-12-15","cited_by_count":8},{"id":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7},{"id":"2506.03990","title":"DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding","created":"2025-06-04","cited_by_count":7},{"id":"2412.09731","title":"Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy","created":"2024-12-12","cited_by_count":6},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6},{"id":"2509.00388","title":"GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction","created":"2025-08-30","cited_by_count":6},{"id":"2606.05688","title":"Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models","created":"2026-06-04","cited_by_count":6},{"id":"2310.19991","title":"PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices","created":"2023-10-30","cited_by_count":5},{"id":"2509.18763","title":"Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models","created":"2025-09-23","cited_by_count":5},{"id":"2510.26730","title":"ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference","created":"2025-10-30","cited_by_count":5},{"id":"2604.17087","title":"EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling","created":"2026-04-18","cited_by_count":5},{"id":"2604.19884","title":"From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization","created":"2026-04-21","cited_by_count":5},{"id":"2412.08602","title":"Empirical Measurements of AI Training Power Demand on a GPU-Accelerated Node","created":"2024-12-11","cited_by_count":4},{"id":"2510.22936","title":"PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models","created":"2025-10-27","cited_by_count":4},{"id":"2601.03889","title":"Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures","created":"2026-01-07","cited_by_count":4},{"id":"2601.21198","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","created":"2026-01-29","cited_by_count":4},{"id":"2503.00245","title":"CoSMoEs: Compact Sparse Mixture of Experts","created":"2025-02-28","cited_by_count":3},{"id":"2504.09345","title":"MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints","created":"2025-04-12","cited_by_count":3},{"id":"2505.15160","title":"Lossless Token Merging Even Without Fine-Tuning in Vision Transformers","created":"2025-05-21","cited_by_count":3},{"id":"2505.22179","title":"Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design","created":"2025-05-28","cited_by_count":3},{"id":"2511.08914","title":"SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM Quantization","created":"2025-11-12","cited_by_count":3},{"id":"2511.17793","title":"Attention Guided Alignment in Efficient Vision-Language Models","created":"2025-11-21","cited_by_count":3},{"id":"2512.17073","title":"Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation","created":"2025-12-18","cited_by_count":3},{"id":"2605.04075","title":"RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction","created":"2026-04-14","cited_by_count":3},{"id":"2305.18786","title":"Scalable Performance Analysis for Vision-Language Models","created":"2023-05-30","cited_by_count":2},{"id":"2409.04018","title":"Towards Energy-Efficiency by Navigating the Trilemma of Energy, Latency, and Accuracy","created":"2024-09-06","cited_by_count":2},{"id":"2409.12994","title":"Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML","created":"2024-09-19","cited_by_count":2},{"id":"2506.13166","title":"GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models","created":"2025-06-16","cited_by_count":2},{"id":"2601.05495","title":"MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding","created":"2026-01-09","cited_by_count":2},{"id":"2604.06798","title":"MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization","created":"2026-04-08","cited_by_count":2},{"id":"2604.12537","title":"MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models","created":"2026-04-14","cited_by_count":2},{"id":"2605.19378","title":"Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock","created":"2026-05-12","cited_by_count":2},{"id":"2504.08359","title":"Kernel-Level Energy-Efficient Neural Architecture Search for Tabular Dataset","created":"2025-04-11","cited_by_count":1},{"id":"2507.02957","title":"CS-VLM: Compressed Sensing Attention for Efficient Vision-Language Representation Learning","created":"2025-06-30","cited_by_count":1},{"id":"2605.15484","title":"When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing","created":"2026-05-15","cited_by_count":1},{"id":"2605.19929","title":"Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models","created":"2026-05-19","cited_by_count":1},{"id":"2605.27465","title":"AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers","created":"2026-05-26","cited_by_count":1},{"id":"2605.30992","title":"Eigenvectors of Experts are Training-free Non-collapsing Routers","created":"2026-05-29","cited_by_count":1}],"next_cursor":null}