Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and MethodAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence5 citationsMar 17Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI AgentsMicrosoft · arXiv (Cornell University)1 citationMar 17Exploring a user-centered approach for movement-based features in interaction designMicrosoft · International Journal of Human-Computer Studies1 citationMar 17Understanding Pruning Regimes in Vision-Language Models Through Domain-Aware Layer SelectionMicrosoft · arXiv (Cornell University)Mar 17Conditional Execution of Transpiler Passes Based on Per-Script Feature DetectionAlphabet · arXiv (Cornell University)Mar 17Semantic One-Dimensional Tokenizer for Image Reconstruction and GenerationAlibaba · arXiv (Cornell University)Mar 17ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated EnvironmentsMicrosoft · arXiv (Cornell University)Mar 17Accelerating the Particle-In-Cell code ECsim with OpenACCNVIDIA · arXiv (Cornell University)Mar 17ODIN-Based CPU-GPU Architecture with Replay-Driven Simulation and EmulationNVIDIA · arXiv (Cornell University)Mar 17Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward ModelsAlibaba · arXiv (Cornell University)Mar 17Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real UsersAllen Institute for AI · arXiv (Cornell University)Mar 17Online Experiential Learning for Language ModelsMicrosoft · arXiv (Cornell University)Mar 17TurnWise: The Gap between Single- and Multi-turn Language Model CapabilitiesAllen Institute for AI · arXiv (Cornell University)Mar 17REAL: Regression-Aware Reinforcement Learning for LLM-as-a-JudgeAlphabet · arXiv (Cornell University)Mar 17HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language ReasoningAlibaba · arXiv (Cornell University)Mar 17Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual InconsistencyAlphabet · arXiv (Cornell University)Mar 17Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward ModelsAlibaba · arXiv (Cornell University)Mar 17Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document RetrievalAlibaba · arXiv (Cornell University)Mar 17GOT-JEPA: Generic Object Tracking With Model Adaptation and Occlusion Handling Using Joint-Embedding Predictive ArchitectureMicrosoft · IEEE Transactions on Circuits and Systems for Video TechnologyMar 17A multi-conditional prior-guided dual spiral CNN-Mamba network for face sketch-photo synthesisCloudWalk Technology · Journal of King Saud University - Computer and Information SciencesMar 17Design Patterns for Integrating AI-driven Automation in Multi-Cloud CRM/ERP EcosystemsMicrosoft · Journal of Information Systems Engineering & ManagementMar 17Lamba: A pretrained model for latency prediction over distributed databasesAlibaba · The VLDB JournalMar 17The Infrastructure-Model Symbiosis: Rethinking Platform Architecture for Billion-Scale Prediction WorkloadsMeta · Journal of Information Systems Engineering & ManagementMar 17app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment ScaffoldingDatabricks · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)Mar 17SynCirc: Efficient Syn thesis of Depth-Optimized Circ uits From High-Level LanguagesTechnology Innovation Institute · IEEE Transactions on Computers1 citationMar 16