Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Marco Large Translation Model at WMT2025: Transforming Translation Capability in LLMs via Quality-Aware Training and DecodingAlibaba · Conference on Machine Translation (WMT)Jan 1, 2025Synergistic Tensor and Pipeline ParallelismAlibaba · neural information processing systemsJan 1, 2025CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-stepAlibaba · neural information processing systemsJan 1, 2025When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual ReasonersAlibaba · neural information processing systemsJan 1, 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image SynthesisAlibaba · neural information processing systemsJan 1, 2025InstanceAssemble: Layout-Aware Image Generation via Instance Assembling AttentionAlibaba · neural information processing systemsJan 1, 2025Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language ModelsAlibaba, Microsoft · neural information processing systemsJan 1, 2025Multimodal Tabular Reasoning with Privileged Structured InformationAlibaba · neural information processing systemsJan 1, 2025A Controllable Examination for Long-Context Language ModelsAlibaba · neural information processing systemsJan 1, 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early DecodingAlibaba · neural information processing systemsJan 1, 2025CARE: Decoding-Time Safety Alignment via Rollback and Introspection InterventionAlibaba · neural information processing systemsJan 1, 2025TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender SystemsAlibaba · neural information processing systemsJan 1, 2025LoRASuite: Efficient LoRA Adaptation Across Large Language Model UpgradesAlibaba · neural information processing systemsJan 1, 2025QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural NetworksAlibaba · neural information processing systemsJan 1, 2025Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement LearningAlibaba · neural information processing systemsJan 1, 2025A Simple Linear Patch Revives Layer-Pruned Large Language ModelsAlibaba · neural information processing systemsJan 1, 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play ModulesAlibaba · neural information processing systemsJan 1, 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World ApplicationsAlibaba, Alphabet · neural information processing systemsJan 1, 2025StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style PerturbationsAlibaba · neural information processing systemsJan 1, 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint ModelingAlibaba · IEEE Transactions on Audio Speech and Language ProcessingJan 1, 2025FineReason: Evaluating and Improving LLMs’ Deliberate Reasoning through Reflective Puzzle SolvingAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1, 2025Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1, 2025Analyzing LLMs’ Knowledge Boundary Cognition Across Languages Through the Lens of Internal RepresentationsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1, 2025Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large LanguageAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1, 2025Mutual-Taught for Co-adapting Policy and Reward ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1, 2025