{"total":75,"rows":[{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2312.05677","title":"Batched Low-Rank Adaptation of Foundation Models","created":"2023-12-09","cited_by_count":32,"area":null},{"id":"2410.09836","title":"Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift","created":"2024-10-13","cited_by_count":24,"area":null},{"id":"2402.03412","title":"See More Details: Efficient Image Super-Resolution by Experts Mining","created":"2024-02-05","cited_by_count":23,"area":null},{"id":"2405.02797","title":"Adapting to Distribution Shift by Visual Domain Prompt Generation","created":"2024-05-05","cited_by_count":23,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2412.12004","title":"The Open Source Advantage in Large Language Models (LLMs)","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2504.08710","title":"Hypergraph Vision Transformers: Images are More than Nodes, More than Edges","created":"2025-04-11","cited_by_count":16,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2409.12272","title":"Mastering Chess with a Transformer Model","created":"2024-09-18","cited_by_count":15,"area":null},{"id":"2410.02200","title":"Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2405.10246","title":"A Foundation Model for Brain Lesion Segmentation with Mixture of Modality Experts","created":"2024-05-16","cited_by_count":14,"area":null},{"id":"2509.16638","title":"KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control","created":"2025-09-20","cited_by_count":13,"area":null},{"id":"2310.02842","title":"Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2501.01808","title":"MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation","created":"2025-01-03","cited_by_count":12,"area":null},{"id":"2503.19598","title":"The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2410.07901","title":"Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization","created":"2024-10-10","cited_by_count":11,"area":null},{"id":"2502.18863","title":"Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2311.05185","title":"Mixture of Weak & Strong Experts on Graphs","created":"2023-11-09","cited_by_count":7,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2403.10568","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2408.12606","title":"A Large Model for Non-invasive and Personalized Management of Breast Cancer from Multiparametric MRI","created":"2024-08-08","cited_by_count":4,"area":null},{"id":"2603.22198","title":"Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2405.20094","title":"Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2512.18804","title":"Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation","created":"2025-12-21","cited_by_count":3,"area":null},{"id":"2401.07441","title":"Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2411.14429","title":"Revisiting the Integration of Convolution and Attention for Vision Backbone","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2511.20621","title":"DiFR: Inference Verification Despite Nondeterminism","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2601.22887","title":"MoVE: Mixture of Value Embeddings -- A New Axis for Scaling Parametric Memory in Autoregressive Models","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.01412","title":"UETrack: A Unified and Efficient Framework for Single Object Tracking","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.14157","title":"Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks","created":"2026-03-14","cited_by_count":2,"area":null},{"id":"2605.07287","title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2503.00049","title":"Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2507.04397","title":"Multi-Expert Learning Framework with the State Space Model for Optical and SAR Image Registration","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2510.04295","title":"Hypernetwork-Driven Low-Rank Adaptation Across Attention Heads","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2601.09902","title":"A Novel Contrastive Loss for Zero-Day Network Intrusion Detection","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2601.22095","title":"GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.00046","title":"REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2604.03260","title":"Why Attend to Everything? Focus is the Key","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.21724","title":"Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2609.10278","title":"FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulation","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2609.12531","title":"Temporal Recurrence Favors Fewer Layers","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2408.09752","title":"A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Method","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2501.07016","title":"A Multi-Modal Deep Learning Framework for Pan-Cancer Prognosis","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2502.06635","title":"Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2504.17834","title":"Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2512.21433","title":"DeepCQ: General-Purpose Deep-Surrogate Framework for Lossy Compression Quality Prediction","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2512.22423","title":"Bright 4B: Scaling Hyperspherical Learning for Segmentation in 3D Brightfield Microscopy","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.12483","title":"A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.17176","title":"NextCrystal: a Symmetry-Driven Generative Framework for Crystal Structure Prediction","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.12354","title":"Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.28658","title":"Divide and Restore: A Modular Task-Decoupled Framework for Universal Image Restoration","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.13244","title":"4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.14540","title":"WILD-SAM: Phase-Aware Expert Adaptation of SAM for Landslide Detection in Wrapped InSAR Interferograms","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.18866","title":"HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.06127","title":"Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06310","title":"Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06501","title":"Cubit: Token Mixer with Kernel Ridge Regression","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23470","title":"Learning Individual Dynamics from Sparse Cross-Sectional Snapshots","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.26164","title":"Data Fusion and Contrastive Alignment for Unconstrained IR Molecular Structure Elucidation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.02129","title":"PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.08965","title":"CoRe-UIE: Rethinking Coexisting and Region-wise Degradation for Underwater Image Enhancement","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.20283","title":"Queries Knew More Than We Thought: Uncovering Latent Knowledge in Segmentation Models","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.30728","title":"Learning Polarization Image Restoration with General Restoration Priors","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36770","title":"Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00541","title":"Random Recursive Models","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}