Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion ModelsAlibaba · arXiv (Cornell University)Aug 17Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise ReasoningAlibaba · arXiv (Cornell University)Aug 17Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding AgentsAlibaba · arXiv (Cornell University)Aug 17Proofs Promptly: Proof-Oriented Programming with AI Agents (Experience Report)Microsoft · Proceedings of the ACM on Programming LanguagesAug 17Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and RecommendationMeta · arXiv (Cornell University)Aug 16Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval BenchmarkAlibaba · arXiv (Cornell University)Aug 16Designing Quantum Error Correcting Codes to fit decoders via Reinforcement LearningMicrosoft · arXiv (Cornell University)Aug 16WiFiSpectralJam: A Large-Scale Open Wi-Fi Spectral Scan Dataset with Controlled RF JammingTechnology Innovation Institute · arXiv (Cornell University)Aug 16Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and DecayAlphabet · arXiv (Cornell University)Aug 16Efficient Audio-Visual Generation via Synchrony-Aware Cross-Modal Sparse AttentionAlibaba · arXiv (Cornell University)Aug 16CUSP: Cutoff-conditioned Unseen Scientific ProgressAllen Institute for AI, Sakana AI · arXiv (Cornell University)Aug 16From LLM Inference to Agentic Workloads: Characterization and Implications for Serving SystemsAlibaba · arXiv (Cornell University)Aug 15LongRCA Bench: Root-Cause Localization in Long-Horizon Agent TrajectoriesAlibaba · arXiv (Cornell University)Aug 15DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI AuditingMicrosoft · arXiv (Cornell University)Aug 15Gated Recurrent Transformers: Expressive Depth through Recurrent ModulationCerebras Systems · arXiv (Cornell University)Aug 15A Survey of Distributed Asynchronous Many-Task Models and Their ApplicationsNVIDIA · ACM Computing Surveys1 citationAug 14Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre ExpansionLG AI Research · arXiv (Cornell University)Aug 14MoE Expert Execution in Disaggregated LLM Serving with a High-Bandwidth ReRAM Near-Memory ArchitectureAlibaba · arXiv (Cornell University)Aug 14Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-TrainingAlibaba · arXiv (Cornell University)Aug 14A second independent verification of the counterexample to Goemans' unsplittable-flow cost conjecture, and the exact suprema of its three-parameter familyMicrosoft · arXiv (Cornell University)Aug 14Resource-efficient quantum eigenvalue transform with commutator scalingAlphabet · arXiv (Cornell University)Aug 14Breaking the bottleneck in AI clusters with parallel photonic integrationMicrosoft · Nature CommunicationsAug 14Towards general auditory intelligence for machine listening and speakingAlphabet, NVIDIA · Nature Machine IntelligenceAug 14FleCSI: Flexible Computational Science InfrastructureDatabricks, Microsoft, NVIDIA · The Journal of Open Source SoftwareAug 14An Overview Of Warp Prediction In Av2Alphabet · Proceedings - International Conference on Image Processing1 citationAug 13