Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MechStyle: Augmenting Generative AI with Mechanical Simulation to Create Stylized and Structurally Viable 3D ModelsAlphabet · ACM Symposium on Computational Fabrication (SCF)8 citationsNov 14, 2025T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table LookupMicrosoft · arXiv (Cornell University)7 citationsNov 14, 2025EcoAlign: An Economically Rational Framework for Efficient LVLM AlignmentAlibaba · arXiv (Cornell University)5 citationsNov 14, 2025AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache OptimizationAlibaba · arXiv (Cornell University)5 citationsNov 14, 2025Generative Caching for Structurally Similar Prompts and ResponsesMicrosoft · arXiv (Cornell University)4 citationsNov 14, 2025ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language ModelsiFlytek · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)2 citationsNov 14, 2025StyleQoRA: Quality-Aware Low-Rank Adaptation for Few-Shot Multi-Style EditingSenseTime · arXiv (Cornell University)2 citationsNov 14, 2025Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language ModelsMeta · arXiv (Cornell University)2 citationsNov 14, 2025PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMsGoogle DeepMind · arXiv (Cornell University)2 citationsNov 14, 2025RETROFIT: Continual Learning with Controlled Forgetting for Binary Security Detection and AnalysisAlibaba · arXiv (Cornell University)Nov 14, 2025Improved Differentially Private Algorithms for Rank AggregationAlphabet · arXiv (Cornell University)Nov 14, 2025Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph RepresentationsAlphabet, Google DeepMind · arXiv (Cornell University)Nov 14, 2025AgentEvolver: Towards Efficient Self-Evolving Agent SystemAlibaba · arXiv (Cornell University)109 citationsNov 13, 2025Black-Box On-Policy Distillation of Large Language ModelsMicrosoft · arXiv (Cornell University)70 citationsNov 13, 2025A Survey on Deep Generative Models for Robot Learning From Multimodal DemonstrationsMeta, NVIDIA · IEEE Transactions on Robotics45 citationsNov 13, 2025Music Flamingo: Scaling Music Understanding in Audio Language ModelsNVIDIA · arXiv (Cornell University)41 citationsNov 13, 2025OmniVGGT: Omni-Modality Driven Visual Geometry Grounded TransformerAlibaba · arXiv (Cornell University)25 citationsNov 13, 2025Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-TrainingZhipu AI · IEEE Transactions on Knowledge and Data Engineering10 citationsNov 13, 2025Benchmarking Diversity in Image Generation via Attribute-Conditional Human EvaluationAlphabet, Google DeepMind · arXiv (Cornell University)5 citationsNov 13, 2025FengHuang: Next-Generation Memory Orchestration for AI InferencingMicrosoft · arXiv (Cornell University)4 citationsNov 13, 2025LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global PartitioningAlibaba · arXiv (Cornell University)2 citationsNov 13, 2025Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI AgentsAlibaba · arXiv (Cornell University)2 citationsNov 13, 2025Taiji: A DPU Memory Elasticity Solution for In-production Cloud EnvironmentsAlibaba · arXiv (Cornell University)Nov 13, 2025Harnessing Bounded-Support Evolution Strategies for Policy RefinementNVIDIA · arXiv (Cornell University)Nov 13, 2025Vmem: A Lightweight Hot-Upgradable Memory Management for In-production Cloud EnvironmentAlibaba · arXiv (Cornell University)Nov 13, 2025