Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Graph Wave NetworksAlibaba · arXiv (Cornell University)1 citationMay 26, 2025Investigating Aggregated vs. Sequential Command Recommendation in Graphical User InterfacesMeta · Graphics InterfaceMay 26, 2025Rolling Ball Optimizer: Learning by ironing out loss landscape wrinklesTechnology Innovation Institute · arXiv (Cornell University)May 26, 2025An Evaluation of AI-RAN Techniques based on Network Digital Twin with Hardware-in-the-LoopNVIDIA · IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)May 26, 2025OASIS: Object-guided Attention for Text-conditional Diffusion Synthesis of Human Interaction SequencesMeta · International Conference on Automatic Face and Gesture RecognitionMay 26, 2025FP4 All the Way: Fully Quantized Training of LLMsNVIDIA · arXiv (Cornell University)43 citationsMay 25, 2025Fluent but Foreign: Even Regional LLMs Lack Cultural AlignmentMicrosoft · arXiv (Cornell University)15 citationsMay 25, 2025VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy OptimizationAlibaba · arXiv (Cornell University)12 citationsMay 25, 2025SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering CooperationAlibaba · arXiv (Cornell University)9 citationsMay 25, 2025CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIPAlibaba · IEEE International Symposium on Circuits and Systems proceedings9 citationsMay 25, 2025HGCL: Hierarchical Graph Contrastive Learning for User-Item RecommendationAlibaba · arXiv (Cornell University)4 citationsMay 25, 2025Chordless Structure: A Pathway to Simple and Expressive GNNsAlibaba · arXiv (Cornell University)May 25, 2025FrameVoting: A Robust and Fast Method of Using Gaze Estimations to Identify Objects of InterestMeta · IEEE International Symposium on Circuits and Systems proceedingsMay 25, 2025Exploring the limits of strong membership inference attacks on large language modelsMicrosoft · arXiv (Cornell University)22 citationsMay 24, 2025MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation LearningHorizon Robotics · International Journal of Computer Vision7 citationsMay 24, 2025ARMS: A Vision for Actor Reputation Metric Systems in the Open-Source Software Supply ChainMicrosoft · arXiv (Cornell University)5 citationsMay 24, 2025OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ TasksMiniMax · arXiv (Cornell University)4 citationsMay 24, 2025Leveraging Per-Instance Privacy for Machine UnlearningAlphabet, Google DeepMind · arXiv (Cornell University)2 citationsMay 24, 2025Multihead Average Pseudo-Margin Learning for Disaster Tweet ClassificationNVIDIA · Information2 citationsMay 24, 2025MOSLIM:Align with diverse preferences in prompts through reward classificationAlibaba · arXiv (Cornell University)1 citationMay 24, 2025Evaluating Intra-firm LLM Alignment Strategies in Business ContextsAlphabet · arXiv (Cornell University)1 citationMay 24, 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingAlibaba · arXiv (Cornell University)280 citationsMay 23, 2025Bigger is not always better: The importance of human-scale language modeling for psycholinguisticsMeta · Journal of Memory and Language19 citationsMay 23, 2025How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-SieveMicrosoft · arXiv (Cornell University)9 citationsMay 23, 2025HyperFLINT: Hypernetwork‐based Flow Estimation and Temporal Interpolation for Scientific Ensemble VisualizationNVIDIA · Computer Graphics Forum5 citationsMay 23, 2025