Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Person De-reidentification: A Variation-guided Identity Shift ModelingAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings2 citationsJun 10, 2025Img-Diff: Contrastive Data Synthesis for Multimodal Large Language ModelsAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings2 citationsJun 10, 2025Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video SynthesisAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context LearningAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025Incorporating Dense Knowledge Alignment into Unified Multimodal Representation ModelsAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based StrategyAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025Learning Visual Generative Priors without TextAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/ProceedingsJun 10, 2025The Synergy Between Data and Multi-Modal Large Language Models: A Survey From Co-Development PerspectiveAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence5 citationsJun 6, 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation ModelsAlibaba · arXiv (Cornell University)31 citationsJun 5, 2025ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow DevelopmentAlibaba · arXiv (Cornell University)Jun 5, 2025Recognize-and-tell: Generating video captions with textual cue in sceneAlibaba · Expert Systems with Applications1 citationJun 4, 2025CHash: A High Cost-Performance Hash Design for CXL-based Disaggregated Memory SystemAlibaba · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS)Jun 4, 2025Reducing the End-to-End Latency of DNN-Based Recommendation Systems in GPU PoolsAlibaba · IEEE International Parallel and Distributed Processing Symposium (IPDPS)1 citationJun 3, 2025KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud ProviderAlibaba · arXiv (Cornell University)Jun 3, 2025M$^3$FinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation DatasetAlibaba · arXiv (Cornell University)Jun 3, 2025LumosFlow: Motion-Guided Long Video GenerationAlibaba · arXiv (Cornell University)Jun 3, 2025Minimal Impact ControlNet: Advancing Multi-ControlNet IntegrationAlibaba · arXiv (Cornell University)Jun 2, 2025Dynamic Range-Filtering Approximate Nearest Neighbor SearchAlibaba · Proceedings of the VLDB Endowment9 citationsJun 1, 2025Sectric: Towards Accurate, Privacy-Preserving and Efficient Triangle CountingAlibaba · Proceedings of the VLDB Endowment1 citationJun 1, 2025A dynamic adaptive readout method for readout electronics of superconducting quantum computingAlibaba · Review of Scientific Instruments1 citationJun 1, 2025EasyText: Controllable Diffusion Transformer for Multilingual Text RenderingAlibaba · arXiv (Cornell University)May 30, 2025PixelThink: Towards Efficient Chain-of-Pixel ReasoningAlibaba · arXiv (Cornell University)May 29, 2025Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning PatternsAlibaba · arXiv (Cornell University)May 29, 2025SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language ModelsAlibaba · arXiv (Cornell University)May 29, 2025OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source SoftwareAlibaba · arXiv (Cornell University)May 29, 2025