Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
DiSCo: Disentangled Attribute Manipulation Retrieval via Semantic Reconstruction and Consistency RegularizationAlibaba · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025Chart-HQA: A Benchmark for Hypothetical Question Answering in ChartsAlibaba · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025EditEval: Towards Comprehensive and Automatic Evaluation for Text-guided Video EditingAlibaba · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025MelodyEdit: Zero-shot Music Editing with Disentangled Inversion ControlAlibaba · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025Speech Token Prediction via Compressed-to-fine Language Modeling for Speech GenerationAlibaba · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech EnhancementAlibaba · arXiv (Cornell University)Oct 23, 2025Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific DataAlibaba · IEEE Transactions on Big DataOct 23, 2025Self-distilled learning of adaptive interval 3D lookup tables on real-time image enhancementAlibaba · Pattern RecognitionOct 23, 2025ULMGNN: Fragmented layer grouping in GUI designs through graph learning based on multimodal informationAlibaba · NeurocomputingOct 23, 2025HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule ApplicationAlibaba · arXiv (Cornell University)Oct 22, 2025Search Self-play: Pushing the Frontier of Agent Capability without SupervisionAlibaba · arXiv (Cornell University)Oct 21, 2025TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent ApplicationsAlibaba · arXiv (Cornell University)Oct 21, 2025Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language ModelAlibaba · arXiv (Cornell University)Oct 20, 2025Language Confusion Gate: Language-Aware Decoding Through Model Self-DistillationAlibaba · arXiv (Cornell University)Oct 20, 2025Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward ModelingAlibaba · arXiv (Cornell University)Oct 20, 2025VACE: All-in-One Video Creation and EditingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)68 citationsOct 19, 2025LlaVA-CoT: Let Vision Language Models Reason Step-By-StepAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)52 citationsOct 19, 2025EasyControl: Adding Efficient and Flexible Control for Diffusion TransformerAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)20 citationsOct 19, 2025CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in LiteracyAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025Advancing Textual Prompt Learning with Anchored AttributesAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)13 citationsOct 19, 2025Audio-Visual LLM for Video UnderstandingAlibaba · IEEE International Conference on Computer Vision Workshops10 citationsOct 19, 2025Animate Anyone 2: High-Fidelity Character Image Animation with Environment AffordanceAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025Low-Light Image Enhancement Using Event-Based Illumination EstimationAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)7 citationsOct 19, 2025DocThinker: Explainable Multimodal Large Language Models with Rule-Based Reinforcement Learning for Document UnderstandingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)6 citationsOct 19, 2025Mdp 3 : a Training-Free Approach for List-Wise Frame Selection in Video-LlmsAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)5 citationsOct 19, 2025