Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language ModelsAlibaba, Microsoft · neural information processing systems8 citationsJan 1, 2025Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical StudyMicrosoft · neural information processing systems8 citationsJan 1, 2025CARE: Decoding-Time Safety Alignment via Rollback and Introspection InterventionAlibaba · neural information processing systems8 citationsJan 1, 2025MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow GenerationAlphabet, Google DeepMind · neural information processing systems8 citationsJan 1, 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMsAlphabet · neural information processing systems8 citationsJan 1, 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning TasksMicrosoft · neural information processing systems8 citationsJan 1, 2025Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM GenerationSenseTime · Proceedings of the conference - Association for Computational Linguistics. Meeting8 citationsJan 1, 2025Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?Alibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting8 citationsJan 1, 2025Don’t Half-listen: Capturing Key-part Information in Continual Instruction TuningZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting8 citationsJan 1, 2025JsonTuning: Towards Generalizable, Robust, and Controllable Instruction TuningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)8 citationsJan 1, 2025MDCure: A Scalable Pipeline for Multi-Document Instruction-FollowingAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting8 citationsJan 1, 2025Unintended Harms of Value-Aligned LLMs: Psychological and Empirical InsightsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting8 citationsJan 1, 2025CARMO: Dynamic Criteria Generation for Context Aware Reward ModellingMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)8 citationsJan 1, 2025StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIsAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)8 citationsJan 1, 2025IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-WebAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)8 citationsJan 1, 2025AI-Assisted Human Evaluation of Machine TranslationMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)8 citationsJan 1, 2025Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMsUpstage · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)8 citationsJan 1, 2025AIM 2024 Sparse Neural Rendering Challenge: Methods and ResultsAlphabet · Lecture notes in computer science8 citationsJan 1, 2025mFollowIR: A Multilingual Benchmark for Instruction Following in RetrievalAllen Institute for AI · Lecture notes in computer science8 citationsJan 1, 2025Exploring Graph Neural Backdoors in Vehicular Networks: Fundamentals, Methodologies, Applications, and Future PerspectivesNVIDIA · IEEE Open Journal of Vehicular Technology8 citationsJan 1, 2025Soccer-CLIP: Vision Language Model for Soccer Action SpottingLG AI Research · IEEE Access8 citationsJan 1, 2025WiLongH: A Custom Hand-Held Platform for Long-Range HaLow Mesh Networks in Human-to-Human CommunicationTechnology Innovation Institute · IEEE Open Journal of the Communications Society8 citationsJan 1, 2025Weakly Supervised LiDAR Semantic Segmentation via Scatter Image AnnotationAlibaba · IEEE Transactions on Multimedia8 citationsJan 1, 2025Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMsAlibaba · neural information processing systems8 citationsJan 1, 2025Massively Parallel Minimum Spanning Tree in General Metric SpacesAlphabet · Society for Industrial and Applied Mathematics eBooks8 citationsJan 1, 2025