标签 - 392
NLPNERBERT论文英文写作技巧投稿技巧Sparse AutoencoderFeature Activation CoverageData SynthesisPost-trainingInterpretabilityLLaMAMistralQwenCross-model TransferPAC-Bayesian TheoryAgentSubGraphLagnGraphMidtraining分布式桥接灾难性遗忘持续预训练课程学习代码领域数学领域中间训练Neo4jCypher预训练大型语言模型深度学习Zero-ShotHuggingFaceLLM量化8-bitTransformer训练网络CVVLPALBEF多模态对比学习EMAPDFPromptALBERT预训练模型Kaggle对抗数据增强知识图谱AttentionBLIPBootstrapping关系分类LSTMMemory-NetworkBLIP2Q-Former性能测试BLOOM机器学习调参评估基准大模型SpanAAAI2020NestedCRFBiLSTMCoT语言模型Few-Shot思维链ChatMLCMLDataChatGPT数据处理Instruction-Tuning调研报告LLaMA2训练经验句子表示ACL2021词向量ThroughputLatency推理加速Continuous-BatchingBatch交叉熵损失LossCyclical学习率计算机视觉Keras特征分析Rank-N微调TensorFlowCNNDenseNetCVPR2017模型调参参数优化电商Grokking应用开发架构设计EDA聚类Fine-TuningRLHFPeftTRLLoRAQLoRAPyTorchSelf-TrainingNeurIPS2020Semi-SupervisedFixMatchFLANICLR2022GPTRole产品GitBoostingGBM主题模型Credit-ScoreIVWOE强化学习PPOInstructBLIPInverse-ScalingFMGPT-EngineerBabyAGIAutoGPTAIReAct智能体GPT4VLLMMLCCTranslateTensor-ParallelismTokenizerMOSSChatGLMSoft-PromptCLIPSequence-LabelingEmbeddingRAGMASSSeq2SeqMQAGQAMHA部署多并发uWSGIFlask负载测试PythonRPS多线程多进程DropoutLayer-NormalizationICML2020Pre-LNPost-LNWarm-upMultimodal-LeanringBLIP-2MM-CoT词表TextPrunerNEZHAPointerDLRDropoutKL优化损失函数XGBoost特征重要性int4QuantizationBlock-wise-QuantizationNormalFloatLangChainFinetuning知识库Agentic RLGradient DisentanglementTool-useReasoningMulti-LoRALEASGRPO梯度冲突RLRGFrobertaData-ScalingSFT预训练语言模型SFLMHard-PromptEMNLP2021SRFTSFT-RL融合熵感知权重数学推理策略优化RFT强化微调半监督学习团队管理工作ChatBIText2SQLEnsembleSnapshot-Ensembles搜索智能问答行业分享StructBERTICLR2020经验总结信息提取大语言模型IEDB数据库Text2DB实操经验上下文Deep-Thinking RatioJensen-Shannon DivergenceTest-Time ScalingChain-of-ThoughtLayer-wise AnalysisEarly StoppingSelf-ConsistencyInference EfficiencyGPT-OSSDeepSeek-R1Qwen3PagedAttentionYunque DeepResearchMulti-AgentDynamic MemorySub-goal DrivenSupervisor ModuleGAIABrowseCompPOMDP层次化架构原子能力池腾讯开源RNNSkillLatexHTMLArxivVicunaBaiChuanYi加速ONNX后训练SWE软件智能体CodeLightGBMCatBoost特征选择ChatIE信息抽取ClaudeLLM产品CondaAnacondaClaude CodeAI 编程助手Agent 架构Prompt Engineering上下文管理SkillsMCP工程化cw2vecngramembeddingTransformersTop-KSamplingTop-PBeam-SearchAIGCStacking评估指标F1KSAUCAccuracyVLMFuyuGaiic命名实体提取竞赛自然语言处理Ddrop对抗训练中训练MoERoPEDeepSeekKimiHexo地理高德医疗einsumpromptGPT-4模型调优技巧语义网络图像分类流量预测Spatial-Dropoutskillkimikimi cli实体抽取关系抽取RDFOWLRDFSQASimilarity正则化标签平滑LookaheadOptimizerAdaptationTransfer-learningICL美团技术MobileBERT模型压缩移动端学术会议pipAdamWSGDTFRecordArchitecture应用架构Dataset时间序列交叉验证Transformer-XL长文本SSRVPNLinuxUbuntu可分类卷积分组卷积扩张卷积转置卷积基础知识ZwiftpythonMacosWinEmergentGPT-3