Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
PaT: Planning-after-Trial for Efficient Test-Time Code GenerationMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy AssimilationMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping AssistantsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1Adaptive Data Collection for Latin-American Community-sourced Evaluation of Stereotypes (LACES)Alphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question AnsweringAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1Towards Stable and Effective Reinforcement Learning for Mixture-of-ExpertsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation EvaluationZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1MERIT Feedback Elicits Better Bargaining in LLM NegotiatorsLG AI Research · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1The olmOCR Project: Building Fully Open OCR using VLMsAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast AsiaAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1Nested Browser-Use Learning for Agentic Information SeekingAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text DetectionAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process RewardsMeta · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1Generating Literature-Driven Scientific Theories at ScaleAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World RepositoriesAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1BrowseConf: Confidence-Guided Test-Time Scaling for Web AgentsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM HallucinationsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1CoEvolve: Training LLM Agents via Agent-Data Mutual EvolutionAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web ReasoningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1Self-Explaining Hate Speech Detection with Moral RationalesAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1CI-Work: Benchmarking Contextual Integrity in Enterprise LLM AgentsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting1 citationJan 1How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative ReasoningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification StrategyAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1OmniDance: Multimodal Driven Dance Video Generation with Large-Scale Internet DataAlibaba · Lecture notes in computer science1 citationJan 1