Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python CodeMeta · Conference of the European Chapter of the Association for Computational LinguisticsJan 1SAGE: Steerable Agentic Data Generation for Deep Search with Execution FeedbackAlphabet · Findings of the Association for Computational Linguistics: EACLJan 1SCALAR: Scientific Citation-based Live Assessment of Long-context Academic ReasoningAlibaba · Conference of the European Chapter of the Association for Computational LinguisticsJan 1Capacity-Latency Tradeoffs in CXL Memory Expander at HyperscaleAlphabet · IEEE Computer Architecture LettersJan 1IRPO: Implicit Policy Regularized Preference OptimizationLG AI Research · Findings of the Association for Computational Linguistics: EACLJan 1Which course? Discourse! Teaching Discourse and Generation in the Era of LLMsAllen Institute for AI · arXivJan 1Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text — A Hindi–English Case StudyMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Tandem Training for Language ModelsMicrosoft · Conference of the European Chapter of the Association for Computational LinguisticsJan 1SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured ReasoningMicrosoft · Findings of the Association for Computational Linguistics: EACLJan 1AMIYA Shared Task: Arabic Modeling In Your Accent at VarDial 2026Cohere · Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)Jan 1SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African ContextAlphabet · Conference of the European Chapter of the Association for Computational LinguisticsJan 1A Large Language Model System for the Field of Chemical Engineering TechnologyiFlytek · Lecture notes in computer scienceJan 1Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward ModelingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Em-Garde: A Propose-Match Framework for Proactive Streaming Video UnderstandingMicrosoft · Lecture notes in computer scienceJan 1Closing the ELBO Gap in Diffusion Models for Speech Enhancement and DereverberationiFlytek · IEEE Transactions on Audio Speech and Language ProcessingJan 1ProGVC: Progressive-Based Generative Video Compression via Auto-Regressive Context ModelingAlibaba · Lecture notes in computer scienceJan 1Alleviating Contextual Misguidance: Response-Aware Prompt Compression for Long-Context Question AnsweringAlibaba · IEEE Transactions on Audio Speech and Language ProcessingJan 1V-Co: A Closer Look at Visual Representation Alignment via Co-DenoisingAllen Institute for AI, Meta · Lecture notes in computer scienceJan 1SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe PropagationAlphabet · Lecture notes in computer scienceJan 1Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social InteractionMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Demystifying Video ReasoningSenseTime · Lecture notes in computer scienceJan 1FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software RepairSenseTime · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Versatile Editing of Video Content, Actions, and Dynamics Without TrainingGoogle DeepMind · Lecture notes in computer scienceJan 1Shopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce TasksAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector DataAlphabet · Lecture notes in computer scienceJan 1