Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?Allen Institute for AI · arXiv (Cornell University)Sep 6Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel CorpusGoogle DeepMind · arXiv (Cornell University)Sep 6Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal ConfirmationAlibaba · arXiv (Cornell University)Sep 5CMD: An Integrated CGRA Framework with Cluster-Based Distributed Memory DesignAlphabet · arXiv (Cornell University)Sep 5Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language ModelsAlibaba · arXiv (Cornell University)Sep 5Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing JailbreaksiFlytek · arXiv (Cornell University)Sep 5UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation ParadigmsAlibaba · arXiv (Cornell University)Sep 5EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing AgentsNVIDIA · arXiv (Cornell University)Sep 5Beyond the Blue Link: Empirical Evaluation of Generative Engine Optimization in Stochastic Retrieval SystemsNVIDIA · ACM Conference on Hypertext and Social Media (HT)Sep 5Edit-Distance Links: A Hypertextual Reading of Conditional-Tokenization World ModelsNVIDIA · ACM Conference on Hypertext and Social Media (HT)Sep 5AI-Powered Enterprise Database Modernization Framework for Hybrid and Cloud EnvironmentsAlphabet · International Journal of Computer Information Systems and Industrial Management ApplicationsSep 4Bigger Text Encoders Can Hurt CLIP Zero-Shot PerformanceMicrosoft · arXiv (Cornell University)Sep 4Optimal Rates for Agentic Networked Information AggregationAlphabet · arXiv (Cornell University)Sep 4Design Docs Are All You Need: An AI-native Machine-Learning Performance ToolAlphabet · arXiv (Cornell University)Sep 4ConsensusBench: Benchmark of Consensus Nodes for LLM Reasoning via Outcome Reward DensifyingAlibaba · arXiv (Cornell University)Sep 4SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerceAlibaba · arXiv (Cornell University)Sep 4Adaptive Context Parallelism for Production LLM ServingAlibaba · arXiv (Cornell University)Sep 4Machine Unlearning as Private Retroactive AlgorithmsAlphabet · arXiv (Cornell University)Sep 4Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode TimeAlphabet · arXiv (Cornell University)Sep 3When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMsMicrosoft · arXiv (Cornell University)Sep 3Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety RefusalMultiverse Computing · arXiv (Cornell University)Sep 3IPGeoAI: Transformer-Based Geolocation with LLM Semantic FusionMeta · arXiv (Cornell University)Sep 3CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker DistillationAlibaba · arXiv (Cornell University)Sep 3Terminal-Universe: Turning Agent Trajectories into Scalable Terminal EnvironmentsAlibaba · arXiv (Cornell University)Sep 3LLM4AIGQ: LLM-based AI Guidance Query Generation Framework for Multi Interest MiningAlibaba · arXiv (Cornell University)Sep 3