Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory AugmentationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14FUSE: Fine-Grained and Semantic-Aware Learning for Unified Image Understanding and GenerationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14CLIPDet3D: Vision-Language Collaborative Distillation for 3D Object DetectionSenseTime · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based AgentsAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency ConstraintsAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic PyramidAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache OptimizationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Inference-time Scaling for Diffusion-based Audio Super-resolutionMeta · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Accelerating LLM Inference Throughput via Asynchronous KV Cache PrefetchingAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14SCALAR: Scale-wise Controllable Visual Autoregressive LearningAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM AgentsMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait AnimationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual QuestionsMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Efficient and Effective In-context Demonstration Selection with CoresetAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language ModelsAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral AlignmentAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Rethinking Flow and Diffusion Bridge Models for Speech EnhancementHorizon Robotics · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Proactive Constrained Policy Optimization with Preemptive PenaltyMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential RecommendationiFlytek · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM AccelerationOpenAI · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14GIIM: Graph-based Learning of Inter- and Intra-view Dependencies for Multi-view Medical Image DiagnosisNVIDIA · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Improving Long-Context Summarization with Multi-Granularity Retrieval OptimizationMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language ModelsAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14MagicPaint: Operate Anything for Image Inpainting with Diffusion ModelMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14A Study of Finetuning Video Transformers for Multi-view Geometry TasksMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence1 citationMar 14