Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Can Large Language Models Generate Observability-Aware Code?Microsoft · arXiv (Cornell University)Jul 7CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal ModelsMicrosoft · arXiv (Cornell University)Jul 7From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action SpaceAlibaba · arXiv (Cornell University)Jul 7LEGATO 2: Toward Multimodal Sheet Music Recognition and UnderstandingAllen Institute for AI · arXiv (Cornell University)Jul 7Unified Gaussian Primitives for Scene Representation and RenderingMeta · ACM Transactions on GraphicsJul 7Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and MitigationsAlphabet · PRX Quantum8 citationsJul 6Clustered Codebook Quantization for 2D Gaussian-based Image CompressionNVIDIA · arXiv (Cornell University)Jul 6uSTM: A Lightweight and Efficient STM Supporting General Types and Deferred AbortsAlphabet · ACM Symposium on Parallelism in Algorithms and Architectures (SPAA)Jul 6Clustered Codebook Quantization for 2D Gaussian-based Image CompressionNVIDIA · arXiv (Cornell University)Jul 6Brief Announcement: Tiered Memory ComputationNVIDIA · ACM Symposium on Parallelism in Algorithms and Architectures (SPAA)Jul 6Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document SynthesisAlibaba · arXiv (Cornell University)Jul 6Hierarchical Evidence-Driven Reasoning for Long Document UnderstandingiFlytek · arXiv (Cornell University)Jul 6CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix CompletionAlphabet · arXiv (Cornell University)Jul 6LLM-as-a-Verifier: A General-Purpose Verification FrameworkNVIDIA · arXiv (Cornell University)Jul 6Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM TrainingTechnology Innovation Institute · arXiv (Cornell University)Jul 6Active Learning on Adversarially Corrupted GraphsAlphabet · arXiv (Cornell University)Jul 6Multi-Turn On-Policy Distillation with Prefix ReplayMicrosoft · arXiv (Cornell University)Jul 6Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied ReasoningAllen Institute for AI, NVIDIA · arXiv (Cornell University)Jul 6DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive GenerationDeepSeek · arXiv (Cornell University)Jul 6RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust VulnerabilitiesMicrosoft · arXiv (Cornell University)Jul 6Can LLMs Really Recover Microservice Failures? A Recovery-Aware Evaluation of Diagnosis-to-Action ReasoningMicrosoft · arXiv (Cornell University)Jul 6Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language ModelsMicrosoft · arXiv (Cornell University)Jul 6Spatial Audio Rendering for Real-Time Speech Translation in Virtual MeetingsMicrosoft · International Journal of Human-Computer InteractionJul 6Dynamic Cogeneration of Bug Reproduction Test in Agentic Program RepairAlphabet · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)2 citationsJul 5Just-in-Time Catching Test Generation at MetaMeta · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)1 citationJul 5