Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long GenerationMicrosoft · neural information processing systems10 citationsJan 1, 2025Exact Expressive Power of Transformers with PaddingAllen Institute for AI · neural information processing systems10 citationsJan 1, 2025A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object DetectionAlibaba · IEEE Transactions on Multimedia10 citationsJan 1, 2025Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmonyAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence10 citationsJan 1, 2025Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMsAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)10 citationsJan 1, 2025Revisiting In-Context Learning with Long Context Language ModelsGoogle DeepMind · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)10 citationsJan 1, 2025From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented LanguagesAlphabet · Ukrainian Natural Language Processing Workshop (UNLP)10 citationsJan 1, 2025Literature-Grounded Novelty Assessment of Scientific IdeasAllen Institute for AI · Workshop on Scholarly Document Processing (SDP)10 citationsJan 1, 2025Attention Speaks Volumes: Localizing and Mitigating Bias in Language ModelsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting10 citationsJan 1, 2025A Theory of Response Sampling in LLMs: Part Descriptive and Part PrescriptiveMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting10 citationsJan 1, 2025Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent InteractionsAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)10 citationsJan 1, 2025BPDec: Unveiling the Potential of Masked Language Modeling Decoder in BERT Model PretrainingAlphabet · Lecture notes in computer science10 citationsJan 1, 2025Ambiguity Detection and Uncertainty Calibration for Question Answering with Large Language ModelsTechnology Innovation Institute · Workshop on Trustworthy NLP (TrustNLP)10 citationsJan 1, 2025MoLA: MoE LoRA with Layer-wise Expert AllocationAllen Institute for AI, Alphabet · Findings of the Association for Computational Linguistics: NAACL10 citationsJan 1, 2025Privacy-Preserving Epidemiological Modeling on Mobile GraphsTechnology Innovation Institute · IEEE Transactions on Information Forensics and Security10 citationsJan 1, 2025Imprints: Mitigating Watermark Removal Attacks With Defensive WatermarksiFlytek · IEEE Transactions on Information Forensics and Security10 citationsJan 1, 2025BMB: Balanced Memory Bank for Long-Tailed Semi-Supervised LearningMeta · IEEE Transactions on Multimedia10 citationsJan 1, 2025When Worse is Better: Navigating the Compression Generation Trade-off In Visual TokenizationAllen Institute for AI, Meta · neural information processing systems10 citationsJan 1, 2025PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient ConflictsAlphabet · neural information processing systems9 citationsJan 1, 2025Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural NetsMeta · neural information processing systems9 citationsJan 1, 2025AttentionPredictor: Temporal Patterns Matter for KV Cache CompressionMicrosoft · neural information processing systems9 citationsJan 1, 2025VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional AnnotationsAlibaba · neural information processing systems9 citationsJan 1, 2025FFN Fusion: Rethinking Sequential Computation in Large Language ModelsNVIDIA · neural information processing systems9 citationsJan 1, 2025Watermarking Autoregressive Image GenerationMeta · neural information processing systems9 citationsJan 1, 2025WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenariosAlphabet, Meta, Microsoft · neural information processing systems9 citationsJan 1, 2025