Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Towards Lightweight and Accurate Remote-Sensing Image Super-Resolution via Reparameterized Feature Enhancement NetworkZhipu AI · Remote SensingAug 22Can LLMs Truly Forget? Revealing Unlearning Gaps Through Adversarial EvaluationMicrosoft · arXiv (Cornell University)Aug 21Scalable Quantum Key Distribution via GHZ Entanglement and Qubit ReuseMeta · arXiv (Cornell University)Aug 21Context as an Environment: Programmatic Context Management for Long-Horizon AgentsAlibaba · arXiv (Cornell University)Aug 21Retrieval Needs Multivectors: An Exponential SeparationMicrosoft · arXiv (Cornell University)Aug 21Neuro-Formal Verification: Agentic Language-Agnostic Formal Program ReasoningMicrosoft · arXiv (Cornell University)Aug 21Towards Faithful Simulation of Human Shopping BehaviorAlibaba · arXiv (Cornell University)Aug 21TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR SystemsNVIDIA · arXiv (Cornell University)Aug 21STAR-OPD: Structured Aspect-Cascade-Aware On-Policy Reward Distillation for ABSA Quadruple ExtractionAlibaba · arXiv (Cornell University)Aug 21Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMsMultiverse Computing · arXiv (Cornell University)Aug 21Llama-Mobile: Efficient 2.7-Bit Quantization of VLMsGraphcore · arXiv (Cornell University)Aug 21User Privacy Attacks through Self-Modifying Code ConflictsAlphabet · ACM Transactions on Architecture and Code OptimizationAug 21Eleven quick tips for Biomedical Federated LearningMicrosoft · PLoS Computational BiologyAug 21Portability of Fortran's 'do concurrent' on GPUs IINVIDIA · arXiv (Cornell University)Aug 20Making Deployments Safe at Meta: Health Checks for Continuous Change-SafetyMeta · arXiv (Cornell University)Aug 20Clifford-efficient sparse state preparation for molecular wavefunctionsMicrosoft · arXiv (Cornell University)Aug 20CacheRoute: Planned Prefix-Affinity Routing for Large-Scale LLM ServingMeta · arXiv (Cornell University)Aug 20Securing Filesystems for Confidential ComputingMicrosoft · arXiv (Cornell University)Aug 20FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet ConfigurationMeta · arXiv (Cornell University)Aug 20One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business WorkflowsMicrosoft · arXiv (Cornell University)Aug 20When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language ModelsAlphabet · arXiv (Cornell University)Aug 20Inadvertent Context Leakage in Language ModelsGoogle DeepMind · arXiv (Cornell University)Aug 20EnvHarness: Awakening Static Worlds for Agent LearningAlphabet · arXiv (Cornell University)Aug 20Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-ExpertsUpstage · arXiv (Cornell University)Aug 20SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerceAlibaba · arXiv (Cornell University)Aug 20