Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Optimizing Federated Learning in the Era of LLMs: Message Quantization and StreamingNVIDIA · International Conference on Foundation and Large Language Models (FLLM)Nov 25, 2025Harnessing Collaboration to Improve the Accuracy of Throughput Prediction in Cellular NetworksMeta · International Conference on Foundation and Large Language Models (FLLM)Nov 25, 2025VeriSciQA: An Auto-Verified Dataset for Scientific Visual Question AnsweringAlibaba · arXiv (Cornell University)Nov 25, 2025Asymptotic yet practical optimization of quantum circuits implementing GF($2^m$) multiplication and division operationsAlphabet · arXiv (Cornell University)Nov 25, 2025M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented GenerationAlibaba · arXiv (Cornell University)Nov 25, 2025Poster: Dynamic Path Allocation in Flat Topologies with PulseNVIDIA · ACM International Conference on emerging Networking EXperiments and Technologies (CoNEXT)Nov 25, 2025Offset-Value Coding in Database Query ExecutionAlphabet · ACM Transactions on Database SystemsNov 25, 2025DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep ResearchAllen Institute for AI · arXiv (Cornell University)126 citationsNov 24, 2025ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language ModelsMeta · arXiv (Cornell University)12 citationsNov 24, 2025PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio GenerationAlibaba · arXiv (Cornell University)11 citationsNov 24, 2025Eevee: Towards Close-up High-resolution Video-based Virtual Try-onAlibaba · arXiv (Cornell University)10 citationsNov 24, 2025STORE: Semantic Tokenization, Orthogonal Rotation and Efficient Attention for Scaling Up Ranking ModelsAlibaba · arXiv (Cornell University)9 citationsNov 24, 2025Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and OptimizationAlibaba · arXiv (Cornell University)7 citationsNov 24, 2025Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person PerspectivesMeta · International Journal of Computer Vision7 citationsNov 24, 2025Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent CollaborationMicrosoft · arXiv (Cornell University)6 citationsNov 24, 2025Understanding Task Transfer in Vision-Language ModelsMicrosoft · arXiv (Cornell University)2 citationsNov 24, 2025Understanding, Accelerating, and Improving MeanFlow TrainingAlphabet · arXiv (Cornell University)2 citationsNov 24, 2025MatMart: Material Reconstruction of 3D Objects via DiffusionAlibaba · arXiv (Cornell University)1 citationNov 24, 2025Oceanus: Scheduling Traffic Flows to Achieve Cost-Efficiency under Uncertainties in Large-Scale Edge CDNsAlibaba · Proceedings of the ACM on Networking1 citationNov 24, 2025The New (Pareto) Frontier of Cloud Routing: High Availability, Precise Control, or Configuration Stability - Choose TwoMeta · Proceedings of the ACM on Networking1 citationNov 24, 2025Unsupervised learning of spatially varying regularization for diffeomorphic image registrationNVIDIA · Medical Image Analysis1 citationNov 24, 2025SimDiff: Simpler Yet Better Diffusion Model for Time Series Point ForecastingAlibaba · arXiv (Cornell University)Nov 24, 2025Annotation-Free Class-Incremental LearningMicrosoft · arXiv (Cornell University)Nov 24, 2025The TRIPS ProjectAlphabet, Microsoft, NVIDIA · Communications of the ACMNov 24, 2025From University Research to Global ImpactAlphabet · Communications of the ACMNov 24, 2025