Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
TRAP: Understanding and Mitigating Privacy Memorization in Language ModelsNVIDIA · arXiv (Cornell University)Sep 26Self-Confirming Superposition Traps in Reinforcement LearningMeta · arXiv (Cornell University)Sep 26Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language ModelsSakana AI · arXiv (Cornell University)Sep 25Training-Free Pronunciation Transcription via Text-Constrained Acoustic RescoringSakana AI · arXiv (Cornell University)Sep 25Quantum error mitigation from information dynamicsAlphabet · arXiv (Cornell University)Sep 25Efficient Extraction for Effectful E-GraphsAlphabet · arXiv (Cornell University)Sep 25KCensus: Synthesizing Latency-Optimal Consensus Fast Paths (Extended Version)NVIDIA · arXiv (Cornell University)Sep 25Verification of Compiler-to-Accelerator Mappings for Machine Learning AcceleratorsMeta · arXiv (Cornell University)Sep 25Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized GuidanceSakana AI · arXiv (Cornell University)Sep 25MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy DistillationAlibaba · arXiv (Cornell University)Sep 25The Power of Indirection: Scaling Switches Beyond Silicon BoundariesMicrosoft · arXiv (Cornell University)Sep 25A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent MemoryMeta · arXiv (Cornell University)Sep 25Generalizing equilibrium propagation to Lagrangian systems with arbitrary boundary conditions & equivalence with Hamiltonian echo learningGoogle DeepMind · Neuromorphic Computing and EngineeringSep 25Component Benchmark: Hierarchical Model Profiling for Large-scale Recommendation SystemsMeta · arXiv (Cornell University)Sep 25DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume RenderingNVIDIA · arXiv (Cornell University)Sep 25Hsod: hybrid strategy object detection in piping and instrumentation diagrams and process flow diagramsiFlytek · Journal on Image and Video ProcessingSep 25A Framework for Value-Aligned Modeling and Robust ExperimentationAlphabet · ACM Conference on Recommender Systems (RecSys)Sep 25Soft Curriculum Learning for Optimizing Fresh and Generalized RecommendationsAlphabet · ACM Conference on Recommender Systems (RecSys)Sep 25From Exploitation to Balance: Efficient Retargeting Recommendation via DPO-Guided Slot AllocationAlibaba · ACM Conference on Recommender Systems (RecSys)Sep 25Space Efficient Item Embeddings for Large Recommender SystemsAlphabet · ACM Conference on Recommender Systems (RecSys)Sep 25TSSR-Beta: Enhancing Billion-Scale E-Commerce Semantic Retrieval via Representation-Level InteractionAlibaba · ACM Conference on Recommender Systems (RecSys)Sep 25M2R: End-to-End Implicit Scenario Discovery for Multi-Scenario and Multi-Crowd Ranking at TaobaoAlibaba · ACM Conference on Recommender Systems (RecSys)Sep 25The Third Workshop on Agentic and Generative AI for E-CommerceMeta · ACM Conference on Recommender Systems (RecSys)Sep 25Online and Adaptive Recommender SystemAlphabet · ACM Conference on Recommender Systems (RecSys)Sep 25Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video RecommendationAlphabet · ACM Conference on Recommender Systems (RecSys)Sep 25