Key papers

• DeepLoop: Depth Scaling for Looped Transformers (2026)
  Shuzhen Li et al.
  10.06
• Unified Static-Dynamic Pruning for Efficient LLM Inference (2026)
  Jinhyeok Kim et al.
  5.01
• Trees from Marginals: Autoregressive drafting with factorized priors (2026)
  Yuma Oda et al.
  4.39
• PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning (2026)
  Yazdan Jamshidi et al.
  4.39
• LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention (2026)
  Ziqi Yin et al.
  4.39
• Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning (2026)
  Daniel Vila-Cruz et al.
  4.39
• Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models (2026)
  Chen Li et al.
  4.39
• Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit (2026)
  Xiaomi MiMo Team et al.
  4.39
• Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation (2026)
  Ruize Xia
  4.39
• Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management (2026)
  Xi Cheng et al.
  4.39
• Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations (2026)
  Wenxuan Miao et al.
  4.39
• Heavy-Tailed Flow Matching via Random Clocks (2026)
  Zhouhao Yang et al.
  4.39
• Decoupled Attention Fusion: Accelerating RAG with Efficient KV Cache Reuse (2026)
  Xiabao Wu et al.
  4.39
• Transferable Latency Prediction for Fast LLM Screening on Heterogeneous Edge Devices (2026)
  Xiaolong Tu et al.
  4.39
• AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems (2026)
  Nilesh Prasad Pandey et al.
  4.39
• FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs (2026)
  Kahou Tam et al.
  4.39
• Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation (2026)
  Kaiwen Wang et al.
  4.39
• RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memory (2026)
  Zahra Yousefijamarani et al.
  4.39
• RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention (2026)
  Anderson R. Santos
  4.39
• Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators (2026)
  Afzal Ahmad et al.
  4.39
• A Leakage-Free Stacked Ensemble Method for Multiclass Classification (2026)
  S. P. Sharmila et al.
  4.39
• IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning (2026)
  Wei Zhang et al.
  4.39
• Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization (2026)
  Hao Wang et al.
  4.39
• HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding (2026)
  Chao Fang et al.
  4.39
• \k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating (2026)
  Jianghui Wang et al.
  4.39
• CausalGate: Causal Importance Distillation for Transformer Module Pruning (2026)
  Kiran Nair et al.
  4.39
• LLM-based Source Code Compression via Thresholded Symbol Ranking (2026)
  Angelo Nardone et al.
  4.39
• A JoLT for the KV Cache: Near-Lossless KV Cache Compression via Joint Tucker and JL-Residual Allocation for LLMs (2026)
  Rahul Krishnan et al.
  3.51
• VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs (2026)
  Shahrzad Esmat et al.
  3.51
• PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization (2026)
  Yuchen Yang et al.
  3.51
• Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection (2026)
  Debarshi Kundu et al.
  3.51
• LiMuon: Light and Fast Muon Optimizer for Large Models (2025)
  Feihu Huang et al.
  2.51
• Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers (2026)
  James O' Neill et al.
  2.00
• Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models (2026)
  Xingyu Mou et al.
  2.00
• Predict before you train: Scaling Laws for particle physics foundation models (2026)
  Jan-Lucas Uslu et al.
  2.00
• Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning (2026)
  Scott M. Norton
  2.00
• FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents (2026)
  Lingteng Zeng et al.
  2.00
• Dynamic Parameterization Is Not Dynamic Inference (2026)
  Zongfei Li et al.
  2.00
• Between Gradient and Natural Gradient: A Continuum of LoRA Initializations (2026)
  Dianze Liu et al.
  2.00
• Incast-Free MoE Rate-Based Scheduling (2026)
  Evyatar Cohen et al.
  2.00
• Mergeable Model-Side Aggregation States for Long-Context Language Models (2026)
  Dachuan Song et al.
  2.00
• LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving (2026)
  Ming-Yen Lee et al.
  2.00
• HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models (2026)
  Hei Yi Mak et al.
  2.00
• ServerlessT2I: Efficient Text-to-Image Workflow Serving on a Serverless Platform (2026)
  Xiaoxiao Jiang et al.
  2.00
• From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs (2026)
  Tina Vartziotis et al.
  2.00
• Decoupled Visual Processing: Efficient Multimodal Adaptation via Modality-Specific Transformer Substitution (2026)
  Mingkuan Feng et al.
  2.00
• FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA (2026)
  Donghang Duan et al.
  2.00
• FARI: Robust One-Step Inversion for Watermarking in Diffusion Models (2026)
  Jindong Yang et al.
  2.00
• Metis: Memory Foundation Model (2026)
  Zeyu Zhang et al.
  2.00
• InferScale: GPU-Native KV Injection for Personalized LLM Serving (2026)
  Peter Li et al.
  2.00
• Investigating reservoir computing for branch predictionin pipelined processors using emerging CMOS memristor devices (2026)
  Harvey Samuel George Johnson et al.
  2.00
• RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention (2026)
  Yang Liu et al.
  1.94
• An Empirical Study of OpenPangu Quantization on Ascend NPUs (2026)
  Tong Shi et al.
  1.94
• Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers (2026)
  Xin Gao et al.
  1.94
• MLVC: Multi-platform Learned Video Codec for Real-World Deployment (2026)
  Tanel P\"arnamaa et al.
  1.94
• Layer-wise LoRA fine-tuning: a similarity metric approach (2026)
  Keith Ando Ogawa et al.
  1.72
• CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge (2026)
  Zhiheng Guo et al.
  1.67
• GPU-Accelerated ANNS: Quantized for Speed, Built for Change (2026)
  Hunter McCoy et al.
  1.67
• CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation (2025)
  Jinyu Liu et al.
  1.56
• Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation (2025)
  Xin Yu et al.
  1.50