Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time ComputeAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)1 citationNov 16, 2025RPG: Linux Kernel Fuzzing Guided by Distribution-Specific Runtime Parameter InterfacesAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)Nov 16, 2025R 3 -Bench: Reproducible Real-world Reverse Engineering Dataset for Symbol RecoveryAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)Nov 16, 2025Mooncake: A KVCache-centric Disaggregated Architecture for LLM ServingAlibaba · ACM Transactions on Storage34 citationsNov 15, 2025Neuro-inspired dynamic dual-processing framework for object detectionAlibaba · NeurocomputingNov 15, 2025RETROFIT: Continual Learning with Controlled Forgetting for Binary Security Detection and AnalysisAlibaba · arXiv (Cornell University)Nov 14, 2025EcoAlign: An Economically Rational Framework for Efficient LVLM AlignmentAlibaba · arXiv (Cornell University)Nov 14, 2025Taiji: A DPU Memory Elasticity Solution for In-production Cloud EnvironmentsAlibaba · arXiv (Cornell University)Nov 13, 2025Vmem: A Lightweight Hot-Upgradable Memory Management for In-production Cloud EnvironmentAlibaba · arXiv (Cornell University)Nov 13, 2025AgentEvolver: Towards Efficient Self-Evolving Agent SystemAlibaba · arXiv (Cornell University)Nov 13, 2025Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTSAlibaba · arXiv (Cornell University)Nov 13, 2025Efficient and Effective In-context Demonstration Selection with CoresetAlibaba · arXiv (Cornell University)Nov 12, 2025AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical RevisitingAlibaba · arXiv (Cornell University)Nov 12, 2025SERL: Self-Examining Reinforcement Learning on Open-DomainAlibaba · arXiv (Cornell University)Nov 11, 2025Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context LearningAlibaba · arXiv (Cornell University)Nov 11, 2025RVME: An Efficient Matrix Engine Design Based on Matrix Extension of RISC-VAlibaba · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD)Nov 10, 2025IterResearch: Rethinking Long-Horizon Agents with Interaction ScalingAlibaba · arXiv (Cornell University)Nov 10, 2025GoCkpt: Gradient-Assisted Multi-Step overlapped Checkpointing for Efficient LLM TrainingAlibaba · arXiv (Cornell University)Nov 10, 2025TBGRecall: A Generative Retrieval Model for E-commerce Recommendation ScenariosAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)5 citationsNov 8, 2025Distribution-Guided Auto-Encoder for User Multimodal Interest Cross FusionAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)1 citationNov 8, 2025A Comprehensive Toolkit for Generalized Robust VisionAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025Meta-Adaptive Network for Effective Cold-Start Recommendation via Warm-Aware Representation LearningAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025SolarMAE: A Unified framework for Regional Centralized and Distributed Solar Power Forecasting with Weather Pre-trainingAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025Side Information Memory Network: Expanding the Breadth of User Behavior Sequences in RecommendationAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025Querier-Aware LLM: Generating Personalized Responses to the Same Query from Different QueriersAlibaba · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025