Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy OptimizationAlphabet · neural information processing systems8 citationsJan 1, 2025Tracing Back the Malicious Clients in Poisoning Attacks to Federated LearningAlphabet · neural information processing systems8 citationsJan 1, 2025Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted ConstraintsAlibaba · neural information processing systems7 citationsJan 1, 2025From Style to Facts: Mapping the Boundaries of Knowledge Injection with FinetuningAlphabet · neural information processing systems7 citationsJan 1, 2025SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning ModelsAlphabet · neural information processing systems7 citationsJan 1, 2025Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like ModelsGoogle DeepMind · neural information processing systems7 citationsJan 1, 2025Do different prompting methods yield a common task representation in language models?Meta · neural information processing systems7 citationsJan 1, 2025Lost in Transmission: When and Why LLMs Fail to Reason GloballyMicrosoft · neural information processing systems7 citationsJan 1, 2025When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical PerspectiveAlphabet · neural information processing systems7 citationsJan 1, 2025RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question AnsweringAlibaba · neural information processing systems7 citationsJan 1, 2025State Entropy Regularization for Robust Reinforcement LearningAlphabet · neural information processing systems7 citationsJan 1, 2025Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image GenerationNVIDIA · neural information processing systems7 citationsJan 1, 2025BlurDM: A Blur Diffusion Model for Image DeblurringNVIDIA · neural information processing systems7 citationsJan 1, 2025Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using ConcordiaAlphabet, Google DeepMind · neural information processing systems7 citationsJan 1, 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World ModelingMeta · neural information processing systems7 citationsJan 1, 2025ViewPoint: Panoramic Video Generation with Pretrained Diffusion ModelsAlibaba · neural information processing systems7 citationsJan 1, 2025Single-pass Adaptive Image Tokenization for Minimum Program SearchAlphabet · neural information processing systems7 citationsJan 1, 2025AdaSPEC: Selective Knowledge Distillation for Efficient Speculative DecodersMicrosoft · neural information processing systems7 citationsJan 1, 2025Are Large Language Models Sensitive to the Motives Behind Communication?Anthropic · neural information processing systems7 citationsJan 1, 2025LayerIF: Estimating Layer Quality for Large Language Models using Influence FunctionsAlphabet · neural information processing systems7 citationsJan 1, 2025Inference-time Alignment in Continuous SpaceAlibaba, Allen Institute for AI · neural information processing systems7 citationsJan 1, 2025ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification QuestionsAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)7 citationsJan 1, 2025To Mask or to Mirror: Human-AI Alignment in Collective ReasoningAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)7 citationsJan 1, 2025Large Language Models Discriminate Against Speakers of German DialectsAllen Institute for AI · Conference on Empirical Methods in Natural Language Processing (EMNLP)7 citationsJan 1, 2025A Comprehensive Framework to Operationalize Social Stereotypes for Responsible AI EvaluationsAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)7 citationsJan 1, 2025