{"total":90,"rows":[{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2403.02781","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","created":"2024-03-05","cited_by_count":72,"area":"mllm"},{"id":"2505.18657","title":"MLLMs are Deeply Affected by Modality Bias","created":"2025-05-24","cited_by_count":40,"area":"mllm"},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2403.07839","title":"MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2403.15132","title":"Transfer CLIP for Generalizable Image Denoising","created":"2024-03-22","cited_by_count":29,"area":null},{"id":"2407.19409","title":"LLAVADI: What Matters For Multimodal Large Language Models Distillation","created":"2024-07-28","cited_by_count":26,"area":"mllm"},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2408.09441","title":"CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination","created":"2024-08-18","cited_by_count":21,"area":"mllm"},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2409.17805","title":"Cascade Prompt Learning for Vision-Language Model Adaptation","created":"2024-09-26","cited_by_count":19,"area":"mllm"},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2311.18237","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2409.05929","title":"M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture","created":"2024-09-09","cited_by_count":13,"area":"moe"},{"id":"2407.10366","title":"Accessing Vision Foundation Models via ImageNet-1K","created":"2024-07-15","cited_by_count":10,"area":null},{"id":"2602.07026","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","created":"2026-02-02","cited_by_count":10,"area":"mllm"},{"id":"2407.01445","title":"FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2407.18134","title":"$\\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2408.04145","title":"ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model","created":"2024-08-08","cited_by_count":9,"area":"distill"},{"id":"2504.16801","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","created":"2025-04-23","cited_by_count":9,"area":"distill"},{"id":"2410.09454","title":"Skipping Computations in Multimodal LLMs","created":"2024-10-12","cited_by_count":7,"area":"mllm"},{"id":"2505.01386","title":"CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2509.25638","title":"Generalized Contrastive Learning for Universal Multimodal Retrieval","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2406.17960","title":"MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation","created":"2024-06-25","cited_by_count":6,"area":"distill"},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2505.21549","title":"Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation","created":"2025-05-25","cited_by_count":6,"area":null},{"id":"2311.08479","title":"Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2409.13939","title":"Simple Unsupervised Knowledge Distillation With Space Similarity","created":"2024-09-20","cited_by_count":5,"area":"distill"},{"id":"2412.04434","title":"Towards Real-Time Open-Vocabulary Video Instance Segmentation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2506.02671","title":"Test-Time Distillation for Continual Model Adaptation","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2409.06166","title":"Revisiting Prompt Pretraining of Vision-Language Models","created":"2024-09-10","cited_by_count":4,"area":"mllm"},{"id":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2510.21879","title":"TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge","created":"2025-10-23","cited_by_count":4,"area":"mllm"},{"id":"2512.14480","title":"SuperCLIP: CLIP with Simple Classification Supervision","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2405.17660","title":"LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking","created":"2024-05-27","cited_by_count":3,"area":"distill"},{"id":"2412.16777","title":"HyperCLIP: Adapting Vision-Language models with Hypernetworks","created":"2024-12-21","cited_by_count":3,"area":"mllm"},{"id":"2502.16815","title":"CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2506.18072","title":"Multimodal Medical Image Binding via Shared Text Embeddings","created":"2025-06-22","cited_by_count":3,"area":null},{"id":"2509.21153","title":"WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2601.08303","title":"SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices","created":"2026-01-13","cited_by_count":3,"area":"diffusion"},{"id":"2311.14517","title":"tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2401.04903","title":"SnapCap: Efficient Snapshot Compressive Video Captioning","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2403.00376","title":"Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model","created":"2024-03-01","cited_by_count":2,"area":"mllm"},{"id":"2404.11249","title":"A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene","created":"2024-04-17","cited_by_count":2,"area":"distill"},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2504.21044","title":"AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection","created":"2025-04-28","cited_by_count":2,"area":"safety"},{"id":"2505.21317","title":"A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features","created":"2025-05-27","cited_by_count":2,"area":"distill"},{"id":"2508.04469","title":"FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding","created":"2025-08-06","cited_by_count":2,"area":"mllm"},{"id":"2603.12824","title":"NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval","created":"2026-03-13","cited_by_count":2,"area":"mllm"},{"id":"2310.19654","title":"MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2312.01987","title":"Bootstrapping SparseFormers from Vision Foundation Models","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2504.07029","title":"Distilling Textual Priors from LLM to Efficient Image Fusion","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2505.07675","title":"Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization","created":"2025-05-12","cited_by_count":1,"area":"mllm"},{"id":"2505.18053","title":"FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation","created":"2025-05-23","cited_by_count":1,"area":"mllm"},{"id":"2506.16994","title":"Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2510.18795","title":"ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2511.11912","title":"A Systematic Study of Model Extraction Attacks on Graph Foundation Models","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2511.15572","title":"From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers","created":"2025-11-19","cited_by_count":1,"area":"mechinterp"},{"id":"2511.20721","title":"Foundry: Distilling 3D Foundation Models for the Edge","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2606.08063","title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","created":"2026-06-06","cited_by_count":1,"area":"mllm"},{"id":"2608.01730","title":"Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2411.14789","title":"Simplifying CLIP: Unleashing the Power of Large-Scale Models on Consumer-level Computers","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2412.03871","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","created":"2024-12-05","cited_by_count":0,"area":"mllm"},{"id":"2506.00910","title":"PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models","created":"2025-06-01","cited_by_count":0,"area":"mllm"},{"id":"2507.09487","title":"HMID-Net: An Exploration of Masked Image Modeling and Knowledge Distillation in Hyperbolic Space","created":"2025-07-13","cited_by_count":0,"area":"distill"},{"id":"2509.08372","title":"Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2511.17886","title":"When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA","created":"2025-11-22","cited_by_count":0,"area":"mllm"},{"id":"2602.04699","title":"Annotation Free Spacecraft Detection and Segmentation using Vision Language Models","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"id":"2602.05909","title":"CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.07768","title":"PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification","created":"2026-02-08","cited_by_count":0,"area":"mllm"},{"id":"2603.00136","title":"TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings","created":"2026-02-24","cited_by_count":0,"area":"mllm"},{"id":"2603.05421","title":"DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression","created":"2026-03-05","cited_by_count":0,"area":"mllm"},{"id":"2603.22867","title":"TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI","created":"2026-03-24","cited_by_count":0,"area":"inference"},{"id":"2603.25383","title":"CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation","created":"2026-03-26","cited_by_count":0,"area":"distill"},{"id":"2603.29631","title":"Storing Less, Finding More: How Novelty Filtering Improves Cross-Modal Retrieval on Edge Cameras","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.00314","title":"Prompt-Guided Prefiltering for VLM Image Compression","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2605.26415","title":"The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2605.26615","title":"FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2605.29380","title":"TRACER: Persistent Regularization for Robust Multimodal Finetuning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.00428","title":"HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.04604","title":"COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.08815","title":"Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles","created":"2026-08-09","cited_by_count":0,"area":"mllm"},{"id":"2608.10524","title":"Rethinking Text-Based Image Retrieval in Specific Domain","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.24935","title":"A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.10321","title":"On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16946","title":"High-Fidelity Video Quality Assessment with VQA-Specific Saliency","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.30739","title":"SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}