Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Sci-Phi: A Large Language Model Spatial Audio DescriptorMicrosoft · IEEE Open Journal of Signal Processing2 citationsJan 1Edge AI for Internet of Robotic ThingsNVIDIA · IEEE Internet of Things Magazine2 citationsJan 1M o N a C o : More Natural and Complex Questions for Reasoning Across Dozens of DocumentsAllen Institute for AI · Transactions of the Association for Computational Linguistics2 citationsJan 1Quantum simulation of CO2 chemisorption in an amine-functionalized metal–organic frameworkNVIDIA · AIP Advances2 citationsJan 1Scaling Reinforcement Learning for Content Moderation with Large Language ModelsMeta · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose EstimationAlibaba · SSRN Electronic Journal2 citationsJan 1LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose ModelsAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1Do LLMs Really Know What They Don’t Know? Internal States Mainly Reflect Knowledge Recall Rather Than TruthfulnessAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAGMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1Attention Beyond Neighborhoods: Reviving Transformer for Graph ClusteringAlibaba · IEEE Transactions on Circuits and Systems for Video Technology2 citationsJan 1E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence, and EfficiencyAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1MLLM-Based Speech Recognition: When and How is Multimodality Beneficial?NVIDIA · IEEE Transactions on Multimedia2 citationsJan 1Learning Zero-Shot Subject-Driven Video Generation Using 1% ComputeMicrosoft · Lecture notes in computer science2 citationsJan 1Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action MemoryAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic ReasoningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical TextsPreferred Networks · arXiv2 citationsJan 1All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM GenerationsMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1Shanks: Simultaneous Hearing and Thinking for Spoken Language ModelsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?Meta · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified ViewMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1SAEdit: Token-Level Control for Continuous Image Editing via Sparse AutoencoderGoogle DeepMind · Lecture notes in computer science2 citationsJan 1UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic LanguagesMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation FrameworkAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-Tuning LLMsAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence2 citationsJan 1EPOCH: Enabling Preemption Operation for Context Saving in Heterogeneous FPGA SystemsMicrosoft · IEEE Access2 citationsJan 1