Ran Xu

Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation AAAI 2026 DistVS: Large-scale Vector Search with Compute-Memory Disaggregation NSDI 2026 OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment ACL 2026 Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs CVPR 2026 Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D EMNLP 2025 Retrieval-augmented GUI Agents with Generative Guidelines EMNLP 2025 RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization ACL 2025 SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains NAACL 2025 Structured Policy Optimization: Enhance Large Vision-Language Model via Self-referenced Dialogue ICCV 2025 Text2Data: Low-Resource Data Generation with Textual Control AAAI 2025 Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting ICCV 2025 Trust but Verify: Programmatic VLM Evaluation in the Wild ICCV 2025 BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers EMNLP 2024 Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation CVPR 2024 EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records EMNLP 2024 FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability ACL 2024 HIVE: Harnessing Human Feedback for Instructional Visual Editing CVPR 2024 Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models ACL 2024 LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer ECCV 2024 MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation ACL 2024 MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning EMNLP 2024 MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens NeurIPS 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records ACL 2024 Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization ICLR 2024 SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant ECCV 2024 ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding CVPR 2024 "X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-modal Reasoning" ECCV 2024 Cold-Start Data Selection for Better Few-shot Language Model Fine-tuning: A Prompt-based Uncertainty Propagation Approach ACL 2023 Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation ICCV 2023 GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation ICCV 2023 Mask-Free OVIS: Open-Vocabulary Instance Segmentation Without Manual Mask Annotations CVPR 2023 Neighborhood-Regularized Self-Training for Learning with Few Labels AAAI 2023 Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting NeurIPS 2023 Tackling Data Heterogeneity in Federated Learning with Class Prototypes AAAI 2023 ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding CVPR 2023 UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild NeurIPS 2023 Burn after Reading: Online Adaptation for Cross-Domain Streaming Data ECCV 2022 DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents COLING 2022 Field Extraction from Forms with Unlabeled Data ACL 2022 Open Vocabulary Object Detection with Pseudo Bounding-Box Labels ECCV 2022 SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles CVPR 2022 Use All the Labels: A Hierarchical Multi-Label Contrastive Learning Framework CVPR 2022 Visual Emotion Representation Learning via Emotion-Aware Pre-training IJCAI 2022 Proposal Learning for Semi-Supervised Object Detection WACV 2021 WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos CVPR 2021 Human Action Segmentation With Hierarchical Supervoxel Consistency CVPR 2015 Actionness Ranking with Lattice Conditional Ordinal Random Fields CVPR 2014