{"total":67,"rows":[{"id":"2506.12479","title":"AI Flow: Perspectives, Scenarios, and Approaches","created":"2025-06-14","cited_by_count":44,"area":null},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2602.03051","title":"SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression","created":"2026-02-03","cited_by_count":12,"area":"mechinterp"},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2508.01506","title":"FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models","created":"2025-08-02","cited_by_count":9,"area":null},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2505.12942","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","created":"2025-05-19","cited_by_count":8,"area":"inference"},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2602.20208","title":"Model Merging in the Essential Subspace","created":"2026-02-23","cited_by_count":7,"area":null},{"id":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","cited_by_count":7,"area":null},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2507.05557","title":"Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2507.07580","title":"COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2603.04800","title":"MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models","created":"2026-03-05","cited_by_count":5,"area":"mllm"},{"id":"2603.17946","title":"CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention","created":"2026-03-18","cited_by_count":5,"area":"inference"},{"id":"2505.11076","title":"Addition is almost all you need: Compressing large language models with double binary factorization","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2510.05544","title":"Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM","created":"2025-10-07","cited_by_count":3,"area":"mllm"},{"id":"2510.14163","title":"Towards Reversible Model Merging For Low-rank Weights","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2604.02570","title":"WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models","created":"2026-04-02","cited_by_count":3,"area":"mllm"},{"id":"2605.08314","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2509.25136","title":"BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.22543","title":"Ruyi2 Technical Report","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2604.01609","title":"Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2606.10520","title":"UniSVQ: 2-bit Unified Scalar-Vector Quantization","created":"2026-06-09","cited_by_count":2,"area":"inference"},{"id":"2508.15068","title":"S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner","created":"2025-08-20","cited_by_count":1,"area":"agents"},{"id":"2510.11234","title":"Neural Weight Compression for Language Models","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.16851","title":"Neuronal Group Communication for Efficient Neural representation","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2512.00272","title":"WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols","created":"2025-11-29","cited_by_count":1,"area":"safety"},{"id":"2512.13494","title":"SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.15200","title":"COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2605.08568","title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.30992","title":"Eigenvectors of Experts are Training-free Non-collapsing Routers","created":"2026-05-29","cited_by_count":1,"area":"moe"},{"id":"2606.19164","title":"Data-Aware Model Merging in the Essential Subspace for Multi-Task Knowledge Aggregation","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.08754","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2510.19385","title":"Beyond Uniform SVD:Dual-Level Optimization across Columns and Modules for LLM Compression","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2510.25977","title":"NeuronMLP: Efficient LLM Inference via Singular Value Decomposition Compression and Tiling on AWS Trainium","created":"2025-10-29","cited_by_count":0,"area":"inference"},{"id":"2511.02681","title":"Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes","created":"2025-11-04","cited_by_count":0,"area":"inference"},{"id":"2601.09865","title":"Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.11464","title":"MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models","created":"2026-01-16","cited_by_count":0,"area":"mllm"},{"id":"2602.18420","title":"SPQ: An Ensemble Technique for Large Language Model Compression","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.14110","title":"SVD Contextual Sparsity Predictors for Fast LLM Inference","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.13508","title":"Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling","created":"2026-04-15","cited_by_count":0,"area":"moe"},{"id":"2604.17709","title":"DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.18085","title":"Predicting LLM Compression Degradation from Spectral Statistics","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.15626","title":"IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.17985","title":"SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.30836","title":"Cross-Layer Subspace Coupling for LLM Compression: A Unifying Framework and Its Empirical Limits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.00573","title":"LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.07596","title":"Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.19993","title":"Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.09204","title":"Complexity-Guided Component-wise Initialization for Language Model Pretraining","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.18284","title":"Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.29071","title":"Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.26389","title":"LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.30226","title":"LaMoC: Loss-Aware Modular Compression for LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.04646","title":"Importance-Aware Low-Rank Distillation of Diffusion Transformers","created":"2026-09-04","cited_by_count":0,"area":"diffusion"},{"id":"2609.07155","title":"Mind the Approximation: Fisher-Weighted SVD Compression for ViTs","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.21172","title":"TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching","created":"2026-09-18","cited_by_count":0,"area":"inference"},{"id":"2609.40127","title":"Learning Functional Subspaces for Neural Network Compression","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00717","title":"Sequential Functional Structured Tucker Compression for Large Language Model Attentions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05504","title":"The Functional Structure of Post-Compression Recovery in Low-Rank LLMs","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.15398","title":"GA-SVD: Generation-aware Singular Value Decomposition for LLM Compression","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16813","title":"Carve VFM: Carving Specialists out of Generalists, Automatic Task-Specific Compression of Vision Foundation Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18098","title":"From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}