Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Folding Context into Executable States: Structured Strategy Folding for Long-Horizon Reasoning AgentAllen Institute for AI · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1LAK-LoRA: Layer-Wise Adaptive Expert Allocation and Principal Component–Based Feature Separation for Medical Multi-Task LearningAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Adaptive Reasoning for Efficient Generative RetrievalAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1VC-IF: Introducing Visual-Constraint Instruction Following for Multi-Turn, Multi-Constraint Vision-Language ModelsAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1CAD-Mark: Context-Aware Distributional Watermarking for Robust LLM-Generated Text DetectionMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Wayfinder: An Agentic Ensemble-and-Postcheck System for WMT26 GenMTAlibaba · Conference on Machine Translation (WMT)Jan 1HSEARCH-R1: Learning Compact Value Models for LLM-guided Hierarchical Search via RLAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Effects of False Positive and False Negative Early Warnings for Hand Tracking Failures on User Trust and Confidence in Virtual RealityAlphabet · IEEE Transactions on Visualization and Computer GraphicsJan 1The Blocker Beasts and How to Tame Them: Schema-Driven Extraction in the Connective AI Layer of Network OperationMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Findings of the WMT26 Shared Task on Automated Translation Quality Evaluation Systems: Compact Open Models are Competitive Quality EvaluatorsNVIDIA · Conference on Machine Translation (WMT)Jan 1SAGE: An Extensible Benchmark for Service Agent Graph-guided EvaluationAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1DuCEI: When to Introduce Metadata in Cross-Entity Interaction for Entity DisambiguationLG AI Research · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1AgSynth: A Multi-Agent Reverse Synthesis Framework for Multimodal Mathematical Reasoning Data GenerationAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1VisCopilot: Assisting Data-Driven Article Authoring with Fact-Based and Intent-Aligned AutocompletionAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1P-Search: A Parallel Plan–Act–Verify Framework with Decoupled GRPO for Deep ResearchAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1LSH-RL: Long-Short Horizon Reinforcement Learning for Persona-Level Role-Playing AgentsMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1ParaShard: Knowledge Sharding for Effective Parametric Retrieval-Augmented GenerationAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Branch Later, Compute Less, Think Better: Adaptive Depth Parallelism for Efficient Parallel Prefix-TuningAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1How Instruction Hierarchy Breaks Under Pairwise Multi-Conflict PressureLG AI Research · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1When to Change the Canvas? Safe Adaptive Variable-Length Decoding for Diffusion Language ModelsAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1SPAR: Experience-Driven Strategy Evolution in Multi-Session B2B SalesAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1SampKV: Saliency-Aware Mixed-Precision KV Cache for Efficient Diffusion Language Model InferenceMicrosoft, NVIDIA · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1AdaSpec: Adaptive Routing by Ranking for Speculative AgentsMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1HalloMTBench: A Large-Scale Human-Verified Benchmark for Diagnosing Hallucination Triggers in LLM TranslationAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1The Cost of Sounding Different: Accent Bias in Audio Language ModelsAllen Institute for AI · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1