标签 - 392
NLPNERBERT论文英文写作技巧投稿技巧AgentSubGraphLagnGraphSparse AutoencoderFeature Activation CoverageData SynthesisPost-trainingInterpretabilityLLaMAMistralQwenCross-model TransferPAC-Bayesian TheoryMidtraining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EMAALBERT预训练模型PDFPromptKaggle对抗数据增强知识图谱AttentionBLIPBLIP2BootstrappingQ-Former关系分类LSTMMemory-Network机器学习调参性能测试BLOOM评估基准大模型SpanAAAI2020NestedCRFBiLSTMCoT语言模型Few-Shot思维链ChatMLCMLDataInstruction-TuningChatGPT调研报告数据处理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TensorFlow模型调参参数优化电商CNNDenseNetCVPR2017Grokking应用开发架构设计EDA聚类Fine-TuningRLHFPeftTRLLoRAQLoRAPyTorchSelf-TrainingNeurIPS2020Semi-SupervisedFixMatchGPTRoleFLANICLR2022产品BoostingGBM主题模型GitCredit-ScoreIVWOE强化学习PPOInstructBLIPFMInverse-ScalingGPT-EngineerBabyAGIAutoGPTAIReActVLLMMLCCTranslateTensor-Parallelism智能体GPT4TokenizerMOSSChatGLMSoft-PromptCLIPSequence-LabelingEmbeddingRAGMASSSeq2Seq部署多并发uWSGIFlask负载测试PythonRPS多线程多进程DropoutMQAGQAMHAMultimodal-LeanringBLIP-2MM-CoTNEZHALayer-NormalizationICML2020Pre-LNPost-LNWarm-up词表TextPrunerPointerXGBoost特征重要性int4QuantizationBlock-wise-QuantizationNormalFloatDLRDropoutKL优化损失函数Finetuning知识库LangChainAgentic RLGradient DisentanglementTool-useReasoningMulti-LoRALEASGRPO梯度冲突RL预训练语言模型SFLMHard-PromptEMNLP2021RGFrobertaData-ScalingSFTSRFTSFT-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搜索智能问答行业分享EnsembleSnapshot-Ensembles团队管理工作ChatBIText2SQLStructBERTICLR2020经验总结信息提取大语言模型IEDB数据库Text2DB上下文实操经验Deep-Thinking RatioJensen-Shannon DivergenceTest-Time ScalingChain-of-ThoughtLayer-wise AnalysisEarly StoppingSelf-ConsistencyInference EfficiencyGPT-OSSDeepSeek-R1Qwen3Yunque DeepResearchMulti-AgentDynamic MemorySub-goal DrivenSupervisor ModuleGAIABrowseCompPOMDP层次化架构原子能力池腾讯开源RNNPagedAttentionSkillLatexHTMLArxivVicunaBaiChuanYi加速ONNX后训练SWE软件智能体CodeLightGBMCatBoost特征选择Claude CodeAI 编程助手Agent 架构Prompt Engineering上下文管理SkillsMCP工程化ChatIE信息抽取ClaudeLLM产品CondaAnacondacw2vecngramembeddingTransformersTop-KSamplingTop-PBeam-SearchAIGCeinsumStacking评估指标F1KSAUCAccuracy中训练MoERoPEDeepSeekKimiVLMFuyuGaiic命名实体提取竞赛自然语言处理Ddrop对抗训练地理高德Hexo医疗GPT-4prompt模型调优技巧语义网络图像分类流量预测skillkimikimi cliSpatial-Dropout实体抽取关系抽取RDFOWLRDFS正则化标签平滑QASimilarityAdaptationTransfer-learningLookaheadOptimizerICL美团技术MobileBERT模型压缩移动端pip学术会议AdamWSGDDatasetTFRecordArchitecture应用架构Transformer-XL长文本时间序列交叉验证可分类卷积分组卷积扩张卷积转置卷积SSRVPNLinuxUbuntu基础知识ZwiftpythonMacosWinEmergentGPT-3