Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Towards better language representation in Natural Language ProcessingMicrosoft · International Journal of Learner Corpus Research2 citationsApr 1, 2025Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind SpotsMicrosoft · arXiv (Cornell University)1 citationApr 1, 2025Next Generation AISakana AI · NTT technical review1 citationApr 1, 2025Exploring cross-dataset generalization of Speech Emotion Recognition modelsMicrosoft · The Journal of the Acoustical Society of AmericaApr 1, 2025Memory-efficient fixpoint computationMeta · Formal Methods in System DesignApr 1, 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe SystemsGoogle DeepMind, Microsoft · arXiv (Cornell University)251 citationsMar 31, 2025Effectively Controlling Reasoning Models through Thinking InterventionNVIDIA · arXiv (Cornell University)66 citationsMar 31, 2025Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies AheadMicrosoft · arXiv (Cornell University)50 citationsMar 31, 2025FVEval: Understanding Language Model Capabilities in Formal Verification of Digital HardwareNVIDIA · Design, Automation, and Test in Europe25 citationsMar 31, 2025Are LLMs Ready for Practical Adoption for Assertion Generation?Microsoft · Design, Automation, and Test in Europe11 citationsMar 31, 2025SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient ScalingsMeta · Design, Automation, and Test in Europe10 citationsMar 31, 2025Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) ChallengeNVIDIA · arXiv (Cornell University)9 citationsMar 31, 2025MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM AccelerationMicrosoft · arXiv (Cornell University)8 citationsMar 31, 2025Can Test-Time Scaling Improve World Foundation Model?NVIDIA · arXiv (Cornell University)7 citationsMar 31, 2025Rethinking Key-Value Cache Compression Techniques for Large Language Model ServingSenseTime · arXiv (Cornell University)5 citationsMar 31, 2025Speculative Testing at Google with Transition PredictionAlphabet · IEEE International Conference on Software Testing, Verification and Validation (ICST)4 citationsMar 31, 2025Extensible Experimentation Platform: Effective A/B Test Analysis at ScaleMicrosoft · IEEE International Conference on Software Architecture Companion (ICSA-C)3 citationsMar 31, 2025SVLA: A Unified Speech-Vision-Language Assistant with Multimodal Reasoning and Speech GenerationTechnology Innovation Institute · arXiv (Cornell University)2 citationsMar 31, 2025High-Throughput SAT SamplingNVIDIA · Design, Automation, and Test in Europe1 citationMar 31, 2025ChipVQA: Benchmarking Visual Language Models for Chip DesignNVIDIA · Design, Automation, and Test in Europe1 citationMar 31, 2025FLASH: An Efficient Hardware Accelerator Leveraging Approximate and Sparse FFT for Homomorphic EncryptionAlibaba · Design, Automation, and Test in Europe1 citationMar 31, 2025WaveFormer: A 3D Transformer with Wavelet-Driven Feature Representation for Efficient Medical Image SegmentationMicrosoft · arXiv (Cornell University)Mar 31, 2025TxISC: Transactional File Processing in Computational SSDsAlibaba · Design, Automation, and Test in EuropeMar 31, 2025Towards Trustworthy GUI Agents: A SurveyMicrosoft · arXiv (Cornell University)40 citationsMar 30, 2025A matter of principle? AI alignment as the fair treatment of claimsGoogle DeepMind · Philosophical Studies34 citationsMar 30, 2025