Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Silent Data Corruption in Artificial Intelligence: A Growing Challenge for Large-Scale Machine LearningAlphabet, Meta, Microsoft, NVIDIA · IEEE Micro5 citationsDec 22, 2025AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric ConstraintsMeta · arXiv (Cornell University)Dec 18, 2025Cross-Tokenizer Likelihood Scoring Algorithms for Language Model DistillationMeta · arXiv (Cornell University)Dec 16, 2025TorchTraceAP: A New Benchmark Dataset for Detecting Performance Anti-Patterns in Computer Vision ModelsMeta · arXiv (Cornell University)Dec 16, 2025Audiovisual speech enhancement and voice activity detection using generative and regressive visual featuresMeta · Computer Speech & Language1 citationDec 14, 2025The Infrastructure -Model Symbiosis: Rethinking Platform Architecture for Billion-Scale Prediction WorkloadsMeta · Journal of Information Systems Engineering & ManagementDec 13, 2025BLASST: Dynamic BLocked Attention Sparsity via Softmax ThresholdingMeta, NVIDIA · arXiv (Cornell University)Dec 12, 2025PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR SystemsMeta · SIGGRAPH Asia Conference Papers3 citationsDec 8, 2025A Nonconforming Formulation of ClothMeta · SIGGRAPH Asia Conference Papers1 citationDec 8, 2025Audio Driven Real-Time Facial Animation for Social TelepresenceMeta · SIGGRAPH Asia Conference Papers1 citationDec 8, 2025Staleness-Based Subgraph Sampling for Training GNNs on Large-Scale GraphsMeta · IEEE International Conference on Big Data (BigData)Dec 8, 2025TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process RewardsMeta · arXiv (Cornell University)Dec 8, 2025TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process RewardsMeta · arXiv (Cornell University)Dec 8, 2025Meta Audiobox Aesthetics: Unified Automatic Assessment for Speech, Music and SoundMeta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)24 citationsDec 6, 2025The AudioMOS Challenge 2025Meta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)4 citationsDec 6, 2025Less is More: Data Curation Matters in Scaling Speech EnhancementMeta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)4 citationsDec 6, 2025URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement CompetitionMeta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)1 citationDec 6, 2025Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMsMeta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)1 citationDec 6, 2025Long-Form Fuzzy Speech-to-Text Alignment for 1000+ LanguagesMeta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)Dec 6, 2025CASPER: A Large Scale Spontaneous Speech DatasetMeta · IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)Dec 6, 2025Persona-based Multi-Agent Collaboration for BrainstormingMeta · arXiv (Cornell University)Dec 4, 2025D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation SpaceMeta, Microsoft · arXiv (Cornell University)Dec 3, 2025Force-Dual Modes: Subspace Design from Stochastic ForcesMeta · ACM Transactions on Graphics1 citationDec 1, 2025Empowering artificial intelligence with homomorphic encryption for secure deep reinforcement learningMeta · Nature Machine Intelligence1 citationDec 1, 2025STACK: Spatial Tower Assembly using Controlled KineticsMeta · IEEE International Conference on Visual Communications and Image Processing (VCIP)Dec 1, 2025