Key papers

• Test-Time Scaling via Error Localization (2026)
  Rajiv Shailesh Chitale et al.
  5.49
• STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU (2026)
  Victor J. B. Jung et al.
  5.01
• Flash EQ-Linear: Accelerating Equivariant Linear Layers via Group-wise Discrete Fourier Transform (2026)
  Zhongchen Zhao et al.
  5.01
• Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference (2026)
  Wenchen Han et al.
  4.39
• Precomputing the Future-Offset Average in TriAttention (2026)
  Amarnath Mukherjee (Hozhoke et al.
  4.39
• Securing LLMs in the Wild: Privacy and Security Challenges at the Edge (2026)
  Ren-Yi Huang et al.
  4.39
• MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model (2026)
  Charilaos Papaioannou et al.
  4.39
• Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention (2026)
  Parviz Haggi-Mani et al.
  4.39
• Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers (2026)
  James O' Neill et al.
  4.39
• Kolmogorov--Arnold Networks for Small Language Models (2026)
  Felippe Alves et al.
  4.39
• In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention (2026)
  Katsuyuki Hagiwara
  4.39
• RTL-Sequencer: Towards Scalable RTL Timing Prediction with the Sequence-based Paradigm (2026)
  Ziyan Guo et al.
  4.39
• JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models (2026)
  Haoran Sun et al.
  4.39
• Improving Improved Kernel PLS (2026)
  Ole-Christian Galbo Engstr{\o}m
  4.39
• GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries (2026)
  Miguel P. Bento et al.
  4.39
• Scaling Point-in-Time Language Models (2026)
  Bryan Kelly et al.
  3.51
• T^2MLR: Transformer with Temporal Middle-Layer Recurrence (2026)
  Ziyang Cai et al.
  3.51
• PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption (2026)
  Sahaj Majavdia et al.
  3.51
• Long-Context Fine-Tuning with Limited VRAM (2026)
  Vladimir Fedosov et al.
  2.00
• FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers (2026)
  Peiyu Zang et al.
  2.00
• Decoupled Attention Fusion: Accelerating RAG with Efficient KV Cache Reuse (2026)
  Xiabao Wu et al.
  2.00
• Transferable Latency Prediction for Fast LLM Screening on Heterogeneous Edge Devices (2026)
  Xiaolong Tu et al.
  2.00
• AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems (2026)
  Nilesh Prasad Pandey et al.
  2.00
• The Hard Decision Layer: Evidence for Committed Inference in Transformers (2026)
  Ashwath Vaithinathan Aravindan et al.
  2.00
• FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs (2026)
  Kahou Tam et al.
  2.00
• On the Depth Scalability of Logic Gate Networks (2026)
  Taegun An et al.
  2.00
• Shallower ReLU Network Representations via Exact Linear Algebra (2026)
  Kilian Rue{\ss} et al.
  2.00
• Neural Feature Governance: Extending Atom Prevalence (2026)
  Idris Karel Seunda Ekwe et al.
  2.00
• CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting (2026)
  Awsaf Tausif Adib et al.
  2.00
• Learning What Matters: Supervising Sparse Attention Routing with Causal Evidence Sets (2026)
  Jim Allchin
  2.00
• A Defense of the Quadratic Model (2026)
  Alexandru Meterez et al.
  2.00
• RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memory (2026)
  Zahra Yousefijamarani et al.
  2.00
• Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection (2026)
  Debarshi Kundu et al.
  2.00
• Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling (2026)
  William Gaudelier et al.
  2.00
• RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention (2026)
  Anderson R. Santos
  2.00
• Unified Static-Dynamic Pruning for Efficient LLM Inference (2026)
  Jinhyeok Kim et al.
  2.00
• Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators (2026)
  Afzal Ahmad et al.
  2.00
• IFCLoRA: Topology-Aware Rank Allocation for Parameter-Efficient Fine-Tuning (2026)
  Wei Zhang et al.
  2.00
• Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting (2026)
  Wan Zhang et al.
  2.00
• Indexing: the Beginning and the End (2026)
  Alexander Kozachinskiy et al.
  2.00
• Interior interpretability with attention rollout: contraction and propagation profiles in Transformers (2026)
  Umberto Biccari et al.
  2.00
• HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding (2026)
  Chao Fang et al.
  2.00
• \k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating (2026)
  Jianghui Wang et al.
  2.00
• Pretraining Recurrent Networks without Recurrence (2026)
  Akarsh Kumar et al.
  1.94
• Do Transformers Actually Help Intrusion Detection? A Temporal Sequence Evaluation on CIC-IDS2017 (2026)
  Zach Moczkodan (Royal Military College of Canada et al.
  1.94
• PostDeg: Placement Beats Parameterization in LayerNorm GNNs (2026)
  Yash Tomar et al.
  1.94
• An Empirical Study of OpenPangu Quantization on Ascend NPUs (2026)
  Tong Shi et al.
  1.94
• SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation (2026)
  Shilin Ma et al.
  1.89
• 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
• SwiftMem: Fast Agentic Memory via Query-aware Indexing (2026)
  Anxin Tian et al.
  1.67
• CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation (2025)
  Jinyu Liu et al.
  1.56
• Numerical Fragility in Transformers: A Layer-wise Theory for Risk Estimation and Selective Stabilization (2025)
  Jinwoo Baek
  1.50
• Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation (2025)
  Jean Barbier et al.
  1.50
• LiMuon: Light and Fast Muon Optimizer for Large Models (2025)
  Feihu Huang et al.
  1.44
• Spatially-Enhanced Temporal Fusion Transformer: Interpretable Multi-Output Prediction for Parametric Dynamical Systems with Time-Varying Inputs (2025)
  Shuwen Sun et al.
  1.22
• Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation (2025)
  Jean Barbier et al.
  1.00