Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
A mbi SQL: Interactive Ambiguity Detection and Resolution for Text-to-SQLAlibaba · ACM SIGMOD International Conference on Management of Data (SIGMOD)May 26FuxiShuffle: An Adaptive and Resilient Shuffle Service for Distributed Data Processing on Alibaba CloudAlibaba · ACM SIGMOD International Conference on Management of Data (SIGMOD)May 26The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels WorksAlibaba · arXiv (Cornell University)May 25InfoQuant: Shaping Activation Distributions for Low-Bit LLM QuantizationAlibaba · arXiv (Cornell University)May 25DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement LearningAlibaba · arXiv (Cornell University)May 25ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMsAlibaba · arXiv (Cornell University)May 25From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in QuarkAlibaba · arXiv (Cornell University)May 25Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in Click-Through Rate PredictionAlibaba · arXiv (Cornell University)May 24GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel PlanningAlibaba · arXiv (Cornell University)May 24Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path ExplorationAlibaba · arXiv (Cornell University)May 24Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection AttackAlibaba · arXiv (Cornell University)May 24Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM AgentsAlibaba · arXiv (Cornell University)May 23Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc TeamworkAlibaba · arXiv (Cornell University)May 23M3GStyler: Enhancing consistency across multi-view in multi-modality 3D Gaussian style transferAlibaba · Pattern Recognition2 citationsMay 22SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation ExtractionAlibaba · arXiv (Cornell University)May 22From Correctness to Preference: A Framework for Personalized Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)May 22From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDsAlibaba · arXiv (Cornell University)May 22Co-ReAct: Rubrics as Step-Level Collaborators for ReAct AgentsAlibaba · arXiv (Cornell University)May 22ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement LearningAlibaba · arXiv (Cornell University)May 22OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn ConversationsAlibaba · arXiv (Cornell University)May 22Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual AttentionAlibaba · arXiv (Cornell University)May 21Unified Data Selection for LLM ReasoningAlibaba · arXiv (Cornell University)May 21Rethinking Cross-Layer Information Routing in Diffusion TransformersAlibaba · arXiv (Cornell University)May 20Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential RecommendationAlibaba · IEEE Transactions on Knowledge and Data Engineering3 citationsMay 19Matrix Extensions for the RISC-V ISAAlibaba · ACM International Conference on Computing Frontiers: Workshops and Special Sessions (CF Companion)May 19