Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language ModelsAllen Institute for AI · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-TrainingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1CompCQR: Compositional Query Generation for Training-Free Conversational SearchLG AI Research · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1How User-AI Mistreatment Occurs and Matters in Conversational Systems?Microsoft · Workshop on Online Abuse and Harms (WOAH)Jan 1MP-Bench: Evaluating Voice Agents as a Multiparty Conversation ParticipantMeta · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Confidence-Gated Transductive Test Generation for Code RerankingMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1CoMaTrack: Competitive Multi-agent Game-Theoretic Tracking with Vision-Language-Action ModelsAlibaba · Lecture notes in computer scienceJan 1EvDiff: Event-Based Video Reconstruction Using One-Step Diffusion ModelsGoogle DeepMind · Lecture notes in computer scienceJan 1HairWeaver: Photorealistic Hair Motion Synthesis with Sim-to-Real Physics Transfer Guided Video DiffusionMeta · Lecture notes in computer scienceJan 1Real-Time Source-Free Object DetectionMicrosoft · Lecture notes in computer scienceJan 1KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMsAlphabet, Google DeepMind · Lecture notes in computer scienceJan 1OmniPoint: Universal Monocular Metric Pointcloud from Any CameraGoogle DeepMind · Lecture notes in computer scienceJan 1Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement LearningAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language ModelsNVIDIA · Lecture notes in computer scienceJan 1Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language ModelsAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1RenderFormer-V2: Neural Rendering with Heterogeneous Scene PrimitivesMicrosoft · Lecture notes in computer scienceJan 1Human-Level Accuracy, Non-human Strategies: Revealing Model–Human Divergence in Video Physical ReasoningMicrosoft · Lecture notes in computer scienceJan 1EAGER: Enrich-and-Align Generative Query Recommendation from Clicked Items in E-commerce SearchAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?Allen Institute for AI · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1It’s Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in AttentionPreferred Networks · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Towards Geometry-Grounded Dense Semantic Matching with VGGT PriorsMicrosoft · Lecture notes in computer scienceJan 1Accelerating Diffusion Transformers with Gaussian Process Rectified Feature CacheAlibaba · Lecture notes in computer scienceJan 1Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State InteractionsNVIDIA · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking PreservationAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary ReasoningAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1