{"total":82,"rows":[{"id":"2501.18427","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","created":"2025-01-30","cited_by_count":165,"area":"lr"},{"id":"2601.08584","title":"Ministral 3","created":"2026-01-13","cited_by_count":114,"area":null},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"id":"2507.01016","title":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers","created":"2025-07-01","cited_by_count":70,"area":"vla"},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62,"area":"lr"},{"id":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"area":"inference"},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"area":null},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"id":"2504.19449","title":"R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference","created":"2025-04-28","cited_by_count":21,"area":"inference"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2505.13940","title":"DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"id":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2506.04213","title":"FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers","created":"2025-06-04","cited_by_count":18,"area":"diffusion"},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2505.13778","title":"CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs","created":"2025-05-19","cited_by_count":14,"area":"lr"},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"id":"2412.13702","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","created":"2024-12-18","cited_by_count":12,"area":"mllm"},{"id":"2511.06055","title":"Neodragon: Mobile Video Generation using Diffusion Transformer","created":"2025-11-08","cited_by_count":12,"area":"diffusion"},{"id":"2410.15281","title":"LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends","created":"2024-10-20","cited_by_count":10,"area":"driving"},{"id":"2412.01822","title":"VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models","created":"2024-12-02","cited_by_count":10,"area":"mllm"},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2502.11306","title":"Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation","created":"2025-02-16","cited_by_count":10,"area":"distill"},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2510.10467","title":"AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2410.09982","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"id":"2505.08854","title":"Generative AI for Autonomous Driving: Frontiers and Opportunities","created":"2025-05-13","cited_by_count":7,"area":"driving"},{"id":"2502.12947","title":"Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models","created":"2025-02-18","cited_by_count":6,"area":"moe"},{"id":"2506.02006","title":"MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing","created":"2025-05-24","cited_by_count":6,"area":"inference"},{"id":"2501.17755","title":"AI Governance through Markets","created":"2025-01-29","cited_by_count":5,"area":null},{"id":"2507.18212","title":"Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation","created":"2025-07-24","cited_by_count":5,"area":null},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2411.06839","title":"LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models","created":"2024-11-11","cited_by_count":4,"area":"distill"},{"id":"2412.16719","title":"Lillama: Large Language Models Compression via Low-Rank Feature Distillation","created":"2024-12-21","cited_by_count":4,"area":"distill"},{"id":"2510.22763","title":"Iterative Layer Pruning for Efficient Translation Inference","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2511.05184","title":"Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models","created":"2025-11-07","cited_by_count":4,"area":"lr"},{"id":"2410.21262","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2510.22101","title":"Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2512.17970","title":"CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2602.01997","title":"On the Limits of Layer Pruning for Generative Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"id":"2502.14305","title":"Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2506.23670","title":"Efficient Interleaved Speech Modeling through Knowledge Distillation","created":"2025-06-30","cited_by_count":2,"area":"distill"},{"id":"2508.08446","title":"OverFill: Two-Stage Models for Efficient Language Model Decoding","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.00588","title":"Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning","created":"2026-02-28","cited_by_count":2,"area":null},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2501.04211","title":"CURing Large Models: Compression via CUR Decomposition","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2504.17531","title":"Towards Machine-Generated Code for the Resolution of User Intentions","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2506.12876","title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2508.00305","title":"Systematic Evaluation of Optimization Techniques for Long-Context Language Models","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2510.08008","title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","created":"2025-10-09","cited_by_count":1,"area":"moe"},{"id":"2602.02891","title":"TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.13052","title":"Quantization-Aware Collaborative Inference for Large Embodied AI Models","created":"2026-02-13","cited_by_count":1,"area":null},{"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":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.08170","title":"Understanding Layer Patching in Model Size Interpolation","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2609.15759","title":"Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2505.10822","title":"Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation","created":"2025-05-16","cited_by_count":0,"area":"distill"},{"id":"2505.18166","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2507.08151","title":"Distilling Empathy from Large Language Models","created":"2025-07-10","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":"2512.17108","title":"Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2512.19069","title":"Can abstract concepts from LLM improve SLM performance?","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2602.00577","title":"SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution","created":"2026-01-31","cited_by_count":0,"area":"safety"},{"id":"2602.06127","title":"Compressing LLMs with MoP: Mixture of Pruners","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.09130","title":"UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.10627","title":"Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.21171","title":"FTerViT: Fully Ternary Vision Transformer","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.04063","title":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.07819","title":"Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.26530","title":"DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2607.22583","title":"Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2610.11332","title":"ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}