Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
AIR: Complex Instruction Generation via Automatic Iterative RefinementAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)9 citationsJan 1, 2025Context-Aware Reasoning On Parametric Knowledge for Inferring Causal VariablesMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)9 citationsJan 1, 2025MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inferenced-Matrix · neural information processing systems9 citationsJan 1, 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential PrivacyAlphabet · neural information processing systems9 citationsJan 1, 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D RewardsMicrosoft · neural information processing systems9 citationsJan 1, 2025PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language ReasoningMicrosoft · neural information processing systems9 citationsJan 1, 2025When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual ReasonersAlibaba · neural information processing systems9 citationsJan 1, 2025Multimodal Tabular Reasoning with Privileged Structured InformationAlibaba · neural information processing systems9 citationsJan 1, 2025Gatekeeper: Improving Model Cascades Through Confidence TuningAlphabet, Google DeepMind · neural information processing systems9 citationsJan 1, 2025Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViTNVIDIA · neural information processing systems9 citationsJan 1, 2025Behavior Injection: Preparing Language Models for Reinforcement LearningOpenAI · neural information processing systems9 citationsJan 1, 2025Datasets, Documents, and Repetitions: The Practicalities of Unequal Data QualityAllen Institute for AI, Anthropic, OpenAI · neural information processing systems9 citationsJan 1, 2025Benchmarking the Ability of a Controller to Execute Quantum Error Corrected Non-Clifford CircuitsNVIDIA · IEEE Transactions on Quantum Engineering9 citationsJan 1, 2025ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained ExplorationAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1, 2025InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-trainingAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1, 2025HPSS: Heuristic Prompting Strategy Search for LLM EvaluatorsZhipu AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)9 citationsJan 1, 2025Pretraining Context Compressor for Large Language Models with Embedding-Based MemoryMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1, 2025Analyzing and Mitigating Inconsistency in Discrete Speech Tokens for Neural Codec Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1, 2025Enhancing the Robustness of Vision-Language Foundation Models by Alignment PerturbationAlibaba · IEEE Transactions on Information Forensics and Security9 citationsJan 1, 2025Enabling Eye Tracking for Crowd-Sourced Data Collection With Project AriaMeta · IEEE Access9 citationsJan 1, 2025Defense against Prompt Injection Attacks via Mixture of EncodingsMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)9 citationsJan 1, 2025Geo6D: Geometric-Constraints-Guided Direct Object 6D Pose Estimation NetworkSenseTime · IEEE Transactions on Multimedia9 citationsJan 1, 2025Knowledge Graph Reasoning With Self-Supervised Reinforcement LearningAlphabet · IEEE Transactions on Audio Speech and Language Processing9 citationsJan 1, 2025RadImageGAN – A Multi-modal Dataset-Scale Generative AI for Medical ImagingNVIDIA · Lecture notes in computer science9 citationsJan 1, 2025Not Every Patch is Needed: Toward a More Efficient and Effective Backbone for Video-Based Person Re-IdentificationAlibaba · IEEE Transactions on Image Processing9 citationsJan 1, 2025