Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT ImprovementsGoogle DeepMind, Meta · neural information processing systems24 citationsJan 1, 2025SMOL: Professionally Translated Parallel Data for 115 Under-represented LanguagesAlphabet, Google DeepMind · Conference on Machine Translation (WMT)24 citationsJan 1, 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity RewardAlphabet, Google DeepMind · neural information processing systems24 citationsJan 1, 2025MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient EvaluationAlibaba · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)24 citationsJan 1, 2025VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and MusicMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)24 citationsJan 1, 2025Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch MiningAlphabet · neural information processing systems23 citationsJan 1, 2025Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free GuidanceNVIDIA · Conference on Empirical Methods in Natural Language Processing (EMNLP)23 citationsJan 1, 2025MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?LG AI Research · neural information processing systems23 citationsJan 1, 2025InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic LayoutsAlphabet, Google DeepMind · neural information processing systems23 citationsJan 1, 2025UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language InterfaceAlibaba · neural information processing systems23 citationsJan 1, 2025UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction SynthesisMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)23 citationsJan 1, 2025Understanding Reference Policies in Direct Preference OptimizationAllen Institute for AI · Findings of the Association for Computational Linguistics: NAACL23 citationsJan 1, 2025Validating LLM-as-a-Judge Systems under Rating IndeterminacyMicrosoft · neural information processing systems22 citationsJan 1, 2025FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language ModelsAlibaba · neural information processing systems22 citationsJan 1, 2025Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and PitfallsCerebras Systems · Conference on Empirical Methods in Natural Language Processing (EMNLP)22 citationsJan 1, 2025ChatBench: From Static Benchmarks to Human-AI EvaluationMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting22 citationsJan 1, 2025Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation SystemsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting22 citationsJan 1, 2025Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting22 citationsJan 1, 2025Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?Meta · Workshop on Trustworthy NLP (TrustNLP)22 citationsJan 1, 2025HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human InteractionsMicrosoft · arXiv (Cornell University)21 citationsJan 1, 2025Continuous Thought MachinesSakana AI · neural information processing systems21 citationsJan 1, 2025Antidistillation SamplingOpenAI · neural information processing systems21 citationsJan 1, 2025FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical DocumentsDatabricks · neural information processing systems21 citationsJan 1, 202570% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)Microsoft · neural information processing systems21 citationsJan 1, 2025Tracing the Representation Geometry of Language Models from Pretraining to Post-trainingAlphabet, Cohere, Google DeepMind · neural information processing systems21 citationsJan 1, 2025