Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SEA-SafeguardBench: Culturally Grounded Safety Benchmark for Southeast Asian LanguagesAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-DepthsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1NeMo@IWSLT 2026: Cascaded System for Simultaneous Speech TranslationNVIDIA · International Conference on Spoken Language Translation (IWSLT)Jan 1TabGuard: Agentic LLM Orchestration for Adaptive Tabular Anomaly Detection via Dynamic Validator Selection and GenerationMicrosoft · Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)Jan 1SAD: A Large-Scale Strategic Argumentative Dialogue DatasetAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Rectified Sparse Attention for Efficient Long-Sequence GenerationMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1IMPACT: Importance-Aware Activation Space ReconstructionMeta · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the BeginningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic SearchAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified CriteriaAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM AgentsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1M2PO: Multi-Perspective Multi-Pair Preference Optimization for Machine TranslationAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1DuET: Dual Execution for Test Output Prediction with Generated Code and PseudocodeLG AI Research · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1TEN: Table Explicitization, NeurosymbolicallyMicrosoft · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1RSDA: Restoring Stale Data Affinity via Dynamic Renovation Strategy for Mitigating Data ScarcityAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Re3: Relevance & Recency Retrieval for Mitigating Temporal HallucinationiFlytek · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text GenerationAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Completing and Validating the Re-Aligned Switchboard Dialog Act CorpusAlphabet · Linguistic Annotation WorkshopJan 1Did You Forget What I Asked? Prospective Memory Failures in Large Language ModelsMicrosoft · Workshop on Trustworthy NLP (TrustNLP)Jan 1Understanding the Behaviors of Environment-aware Information RetrievalAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient ReasoningAlphabet · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Systematic Performance Degradation in Indic Vision-Language Models: Evidence from Hindi and TeluguAllen Institute for AI · Workshop on Advances in Language and Vision Research (ALVR)Jan 1Table-as-Search: Agentic Information Seeking is Table CompletionAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1V-GameGym: Visual Game Generation for Code Large Language ModelsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Is Your Language Model Ready for Monetization Decisions?Microsoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1