Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement LearningAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Agent4CD: Generative Agent for Cognitive Diagnosis in Intelligent EducationiFlytek · IEEE Transactions on Neural Networks and Learning SystemsJan 1Video Generation Models Are General-Purpose Vision LearnersGoogle DeepMind · Lecture notes in computer scienceJan 1DETRAM: End-to-End DEtection, Tracking and Recovery of HumAn MeshesNVIDIA · Lecture notes in computer scienceJan 1Dive Into the Implicit Biases of Low-Rank Vision-Language AlignmentMininglamp Technology · Lecture notes in computer scienceJan 1HIVE: Understanding Post-hallucination Reasoning in Vision Language ModelsMeta · Lecture notes in computer scienceJan 1SPEAR: A Simulator for Photorealistic Embodied AI ResearchNVIDIA · Lecture notes in computer scienceJan 1An Efficient Computing and Communication Framework for Large-Scale Data Processing ClusterNVIDIA · IEEE Transactions on NetworkingJan 1WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent EvaluationMininglamp Technology · Lecture notes in computer scienceJan 1Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent SpaceNVIDIA · Lecture notes in computer scienceJan 1HiEvi-RAG: Hierarchical Evidence-Driven Reasoning for Long Document UnderstandingiFlytek · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion ModelsHugging Face · Lecture notes in computer scienceJan 1Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural TransferAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1ChainSWE: Benchmarking Coding Agents on Multi-Bug Software MaintenanceNVIDIA · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model BehaviorAllen Institute for AI · Transactions of the Association for Computational LinguisticsJan 1Towards High-Resolution Visual Perception via Hierarchical Entity ExplorationAlibaba · Lecture notes in computer scienceJan 1Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path ProcessingAlphabet · Lecture notes in computer scienceJan 1A Multi-agent Framework for Democratizing XR Content Creation in K-12 ClassroomsMeta · Communications in computer and information scienceJan 1M2Note: Continual Evolution of Vision Language Models via Mistake Notebook LearningAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric AbsorptionAlibaba · Lecture notes in computer scienceJan 1Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural DenoisingMicrosoft · Lecture notes in computer scienceJan 1Cognitive Scaffold: From Fluid Context to Crystallized Memory for Long-Horizon DeepResearch AgentsMininglamp Technology · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable PromptingiFlytek · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance TriggerMicrosoft · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1HORIZON: A Benchmark for In-the-wild User Behaviour ModelingMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1