Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech UnderstandingOpenAI · arXiv (Cornell University)Sep 19Block-Sparse Attention with Semantic-Geometric Decoupled RoutingAlibaba · arXiv (Cornell University)Sep 19ISA-Bench: A Benchmark for Computational Reasoning Across Instruction Set ArchitecturesMicrosoft · arXiv (Cornell University)Sep 19LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument SegmentationMeta · arXiv (Cornell University)Sep 19RoutingBench: Can Agentic Routing Analysis Scale to Production Datacenter Networks?Microsoft · arXiv (Cornell University)Sep 19TEMPO: A Tag-Based Framework for Efficient Memory OrderingNVIDIA · arXiv (Cornell University)Sep 19Extracting Electromagnetic Bare Mode Couplings in Large Superconducting Quantum ProcessorsAlphabet · arXiv (Cornell University)Sep 18Pretrained Persona Mixture Models and Tandem Models for Human SimulationAlphabet · arXiv (Cornell University)Sep 18Presage: Prefetch Search via Agent-Guided ExperimentsAlphabet · arXiv (Cornell University)Sep 18Hardness of Online Directed Steiner NetworkMicrosoft · arXiv (Cornell University)Sep 18Scalable Packet Tracking on FPGAs for Erasure-Coded RDMA over Lossy WANsMicrosoft · arXiv (Cornell University)Sep 18Auto-Bidding with Disentangled Advertiser Profiles and Train-Free AdaptationAlibaba · arXiv (Cornell University)Sep 18CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet BuzzwordsMeta · arXiv (Cornell University)Sep 18Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal InteractionAlibaba · arXiv (Cornell University)Sep 18I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio AssistanceMeta · arXiv (Cornell University)Sep 18Denser Planar Color CodesAlphabet · arXiv (Cornell University)Sep 18Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication OverlapAlibaba · arXiv (Cornell University)Sep 18Detecting Pretraining Data in Large Language Models from a Free-Energy PerspectiveiFlytek · arXiv (Cornell University)Sep 18Geometric Mean Pooling for Equal-Weight Multiplicative Coarse-GrainingAlphabet · arXiv (Cornell University)Sep 18When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning TracesGoogle DeepMind · arXiv (Cornell University)Sep 18ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RLAlibaba · arXiv (Cornell University)Sep 18Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large ScaleMeta · arXiv (Cornell University)Sep 18DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal ReasoningMeta · arXiv (Cornell University)Sep 18CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video GenerationAlibaba · arXiv (Cornell University)Sep 18Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at ScaleMeta · arXiv (Cornell University)Sep 18