Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting27 citationsJan 1, 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion ModelsAlphabet · neural information processing systems26 citationsJan 1, 2025ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMsMicrosoft · neural information processing systems26 citationsJan 1, 2025Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal ConsistencyAlibaba · neural information processing systems26 citationsJan 1, 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMsMeta · neural information processing systems26 citationsJan 1, 2025SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded TasksAllen Institute for AI · neural information processing systems26 citationsJan 1, 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial ReasoningAlphabet, Google DeepMind · neural information processing systems26 citationsJan 1, 2025Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCoAlphabet · neural information processing systems26 citationsJan 1, 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World ApplicationsAlibaba, Alphabet · neural information processing systems26 citationsJan 1, 2025A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks AlignmentMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting26 citationsJan 1, 2025Contextualized Evaluations: Judging Language Model Responses to Underspecified QueriesAllen Institute for AI · Transactions of the Association for Computational Linguistics26 citationsJan 1, 2025AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion GenerationMicrosoft · Findings of the Association for Computational Linguistics: NAACL26 citationsJan 1, 2025GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and ReasoningTechnology Innovation Institute · IEEE Access26 citationsJan 1, 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video UnderstandingAlibaba, Meta · neural information processing systems25 citationsJan 1, 2025Learning 3D Persistent Embodied World ModelsGoogle DeepMind · neural information processing systems25 citationsJan 1, 2025ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and RobustnessNVIDIA · neural information processing systems25 citationsJan 1, 2025Test-Time Scaling of Diffusion Models via Noise Trajectory SearchNVIDIA, OpenAI · neural information processing systems25 citationsJan 1, 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through ThinkingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)25 citationsJan 1, 2025ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability KnowledgeAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)25 citationsJan 1, 2025Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging TasksAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting25 citationsJan 1, 2025Neuro-Symbolic Integration Brings Causal and Reliable Reasoning ProofsAlibaba · Findings of the Association for Computational Linguistics: NAACL25 citationsJan 1, 2025Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model MergingAlibaba · neural information processing systems25 citationsJan 1, 2025SpoofCeleb: Speech Deepfake Detection and SASV in the WildMeta · IEEE Open Journal of Signal Processing25 citationsJan 1, 2025LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient RenderingAlphabet, Google DeepMind · neural information processing systems24 citationsJan 1, 2025Temporal Chain of Thought: Long-Video Understanding by Thinking in FramesAlphabet, Google DeepMind · neural information processing systems24 citationsJan 1, 2025