{"total":84,"rows":[{"id":"2503.12340","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","created":"2025-03-16","cited_by_count":67,"area":null},{"id":"2503.23798","title":"Adaptive Layer-skipping in Pre-trained LLMs","created":"2025-03-31","cited_by_count":27,"area":null},{"id":"2501.04765","title":"TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training","created":"2025-01-08","cited_by_count":21,"area":"diffusion"},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16,"area":null},{"id":"2504.00502","title":"ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers","created":"2025-04-01","cited_by_count":14,"area":"mllm"},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2410.20210","title":"Looking Beyond The Top-1: Transformers Determine Top Tokens In Order","created":"2024-10-26","cited_by_count":12,"area":null},{"id":"2503.16843","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models","created":"2025-03-21","cited_by_count":11,"area":"mllm"},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2602.17951","title":"ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models","created":"2026-02-20","cited_by_count":11,"area":"vla"},{"id":"2410.13184","title":"Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2512.16391","title":"Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference","created":"2025-12-18","cited_by_count":10,"area":"lr"},{"id":"2601.18091","title":"From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models","created":"2026-01-26","cited_by_count":10,"area":"lr"},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2505.22135","title":"RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding","created":"2025-05-28","cited_by_count":8,"area":"inference"},{"id":"2601.06787","title":"Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning","created":"2026-01-11","cited_by_count":8,"area":null},{"id":"2508.02751","title":"SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference","created":"2025-08-03","cited_by_count":6,"area":"inference"},{"id":"2511.22686","title":"Emergent Extreme-View Geometry in 3D Foundation Models","created":"2025-11-27","cited_by_count":6,"area":null},{"id":"2503.11816","title":"Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques","created":"2025-03-14","cited_by_count":5,"area":"inference"},{"id":"2502.17355","title":"On Relation-Specific Neurons in Large Language Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2504.10804","title":"Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2603.19664","title":"The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference","created":"2026-03-20","cited_by_count":4,"area":"inference"},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2606.09080","title":"Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2409.09071","title":"Elastic On-Device LLM Service","created":"2024-09-08","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":"2502.00439","title":"UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs","created":"2025-02-01","cited_by_count":3,"area":null},{"id":"2502.02007","title":"Reasoning Bias of Next Token Prediction Training","created":"2025-02-04","cited_by_count":3,"area":"lr"},{"id":"2502.04348","title":"Prompt-based Depth Pruning of Large Language Models","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2503.11272","title":"When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2504.03794","title":"Entropy-Based Block Pruning for Efficient Large Language Models","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2505.17138","title":"RAP: Runtime Adaptive Pruning for LLM Inference","created":"2025-05-22","cited_by_count":3,"area":"inference"},{"id":"2509.08897","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval","created":"2025-09-10","cited_by_count":3,"area":"mllm"},{"id":"2511.21974","title":"Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2512.20612","title":"Making Large Language Models Efficient Dense Retrievers","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2601.19503","title":"GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2606.27755","title":"Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?","created":"2026-06-26","cited_by_count":3,"area":"vla"},{"id":"2409.14595","title":"EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2503.14932","title":"Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2505.07289","title":"Semantic Retention and Extreme Compression in LLMs: Can We Have Both?","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2505.13547","title":"Exploring Federated Pruning for Large Language Models","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2505.24009","title":"Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.16787","title":"Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2510.25979","title":"AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2512.20636","title":"Data-Free Pruning of Self-Attention Layers in LLMs","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2604.18610","title":"SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression","created":"2026-04-13","cited_by_count":2,"area":"mllm"},{"id":"2411.15281","title":"ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation","created":"2024-11-22","cited_by_count":1,"area":"lr"},{"id":"2501.02436","title":"Network Dynamics-Based Framework for Understanding Deep Neural Networks","created":"2025-01-05","cited_by_count":1,"area":null},{"id":"2503.18908","title":"FFN Fusion: Rethinking Sequential Computation in Large Language Models","created":"2025-03-24","cited_by_count":1,"area":"lr"},{"id":"2505.21077","title":"Efficient Large Language Model Inference with Neural Block Linearization","created":"2025-05-27","cited_by_count":1,"area":"inference"},{"id":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2509.06326","title":"AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2602.20207","title":"Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2604.18103","title":"Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"id":"2605.06105","title":"Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.11744","title":"Training-Inference Consistent Segmented Execution for Long-Context LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.22476","title":"Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.02559","title":"From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.03784","title":"Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2607.26849","title":"ToxScreen: Detecting Whether an LLM Has Been Poisoned","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2607.28418","title":"WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2502.20726","title":"Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.21535","title":"FAR: Function-preserving Attention Replacement for IMC-friendly Inference","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2506.03303","title":"Hopscotch: Discovering and Skipping Redundancies in Language Models","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2506.14704","title":"Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2509.06836","title":"COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2510.09380","title":"Utilizing dynamic sparsity on pretrained DETR","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2511.14781","title":"Quantifying the Role of OpenFold Components in Protein Structure Prediction","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2512.12744","title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2601.17987","title":"Systematic Characterization of Minimal Deep Learning Architectures: A Unified Analysis of Convergence, Pruning, and Quantization","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2601.19089","title":"EPAS: Efficient Training with Progressive Activation Sharing","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.02163","title":"Reg4Pru: Regularisation Through Random Token Routing for Token Pruning","created":"2026-02-02","cited_by_count":0,"area":"inference"},{"id":"2605.18865","title":"From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.26538","title":"CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.29579","title":"ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models","created":"2026-06-28","cited_by_count":0,"area":"lr"},{"id":"2606.31397","title":"Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.03580","title":"SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.11138","title":"Attention-Path Fragility as an Uncertainty Signal in Large Language Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.33977","title":"GroupMask: Layer-Adaptive Group-wise Sparsity for Semi-Structured LLM Pruning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36842","title":"Does the VGGT Family Need All Its Layers?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.10303","title":"On the Necessity of Attention-FFN Split in Vision Transformers","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.15005","title":"Retraining-Free Depth Pruning of Vision Transformers: A Cross Domain Study of Layer Redundancy","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}