For Efficient AI

logitech Gemini 2.5 2506.01206v1 Mamba Speculative Decoding State-Space Model Efficient Inference 2506.01215v1 LLM, Long-Context Retrieval Systems 2505.23416v1 kvzip kv-cache long-context cache-compression memory-optimization latency-reduction flashattention llm large-language-models ai-systems nlp 2506.04708v1 STAND Test-Time Scaling Inference Acceleration Logit N-gram Gumbel-Top-K Large Language Models GPU Efficiency AI Research Review Performance Optimization 2310.16818v2 DreamCraft3D BSD Hybrid-SDS 2401.02954v1 LLM DeepSeek 2401.06066v1 2401.14196v2 Code LLM Code Completion Fill-in-the-Middle Cross-File Code Generation Software Engineering AI 2406.11931v1 Mixture of Experts Open Source Transformer Long Context HumanEval Math Reasoning GPT-4 Alternative Model Scaling YaRN FIM (Fill In Middle) Instruction Tuning RLHF Language Modeling 2407.01906v2 ESFT MoE SparseLLM ParameterEfficientTuning ExpertSelection DeepSeekV2 2408.08152v1 FormalProof AutomatedTheoremProving Lean4 LLMforProof ProofSearch WholeProof MCTS RMaxTS IntrinsicReward TruncateAndResume MathReasoning AI4Math LanguageModel ReinforcementLearning DeepSeekProver 2408.14158v2 Distributed Training PCIe GPU Cluster All-Reduce, HFReduce Communication Optimization Cost Efficiency Power Efficiency PyTorch System Architecture 2408.15664v1 Mixture-of-Experts Load Balancing Loss-Free Learning DeepSeek-MoE Routing MaxVio 2410.13848v1 Multimodal Learning Vision-Language Model Dual Encoder Image Generation Unified Transformer VLM Janus 2411.07975v2 Multimodal AI Rectified Flow Representation Alignment Unified Model FID SigLIP ConvNeXt 2412.10302v1 Vision-Language Models High-Resolution Image Processing Dynamic Tiling Mixture of Experts (MoE) KV-Cache Compression Multi-head Latent Attention (MLA) Visual Grounding OCR Parameter Efficiency LLM Inference Optimization Edge AI Open Source Models Document Understanding Infographic QA Chart and Table QA Visual Reasoning Multilingual VQA Conversational AI with Images 2412.19437v2 FP8 Open-source LLM Model Efficiency CausalLM AI Research 2501.12948v1 Reinforcement Learning GRPO Knowledge Distillation Causal LM Self-Evolution SOTA Benchmarking 2501.17811v1 Janus-Pro Dual-Encoder Text-to-Image Image Understanding Adapter Networks Visual Tokenization GenEval MMBench DPG-Bench DeepSeek-LLM Efficient Training Synthetic Data 첼로 스칼라티 로드자전거 자가정비 홈미캐닉 시마노105 2502.07316v4 Code Reasoning Chain-of-Thought I/O Prediction Execution Feedback Data-Centric AI 2502.11089v2 Sparse Attention Transformer Optimization Efficient LLM GPU Acceleration FlashAttention Memory Efficiency Inference Speedup Trainable Sparsity Triton Kernel Deep Learning Language Models 데이터센터 배터리 LFP CATL BYD AI ESG 중국 2504.02495v2 Reward Modeling Generative Reward Model LLM Evaluation Preference Modeling Reinforcement Learning from Human Feedback (RLHF)