Key papers

• Loop the Loopies! (2026)
  Zitian Gao et al.
  14.05
• Hash-QNeRF: Multiresolution Hash Encoding for Quantum Neural Radiance Fields (2026)
  Digonto Biswas et al.
  5.49
• LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression (2026)
  Chris Xing Tian et al.
  5.01
• Preference Tuning as Spectral Update Reorganization (2026)
  Peiyan Zhang et al.
  5.01
• Flash EQ-Linear: Accelerating Equivariant Linear Layers via Group-wise Discrete Fourier Transform (2026)
  Zhongchen Zhao et al.
  5.01
• SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation (2026)
  Yuan Li et al.
  4.90
• NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs (2026)
  Sihyeon Lee et al.
  4.39
• Differentiable Proxy Learning for Adaptive Quantization Control in H.264 Video Coding (2026)
  Qihan Xu et al.
  4.39
• FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy (2026)
  Le-Anh Tran
  4.39
• Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling (2026)
  Shaokang Wang et al.
  4.39
• GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries (2026)
  Miguel P. Bento et al.
  4.39
• Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization (2026)
  Hao Wang et al.
  4.39
• Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving (2026)
  Nikita Agrawal et al.
  3.51
• Optimized Adaptive Loop Filter in Versatile Video Coding (2026)
  Xuewei Meng et al.
  3.51
• From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers (2026)
  Binbin Lin et al.
  3.51
• ACID: Adaptive Caching for vIDeo generation (2026)
  Om Agrawal et al.
  3.51
• 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
• T^2MLR: Transformer with Temporal Middle-Layer Recurrence (2026)
  Ziyang Cai et al.
  3.51
• VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs (2026)
  Shahrzad Esmat et al.
  3.51
• SpecLA: Efficient Speculative Decoding for Linear-Attention Models (2026)
  Zhibin Wang et al.
  3.51
• Test-Time Registers as Global Priors for Tokenized Image Generation (2026)
  Cheng-Yao Hong et al.
  3.51
• PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer (2026)
  Nikhil Ghosh et al.
  3.51
• Flashbias: Fast Computation Of Attention With Bias (2025)
  Haixu Wu, Minghao Guo, Yuezhou Ma, et al.
  3.29
• Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers (2026)
  James O' Neill et al.
  2.00
• AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally (2026)
  Shaowen Wang et al.
  2.00
• Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing (2026)
  Ali Mahdavi et al.
  2.00
• Token-Operations-Oriented Inference Optimization Techniques for Large Models (2026)
  Shiguo Lian et al.
  1.94
• Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning (2026)
  Junyi Wang et al.
  1.89
• QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference (2026)
  Miao Zhang et al.
  1.78
• Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning (2026)
  Naixin Zhai et al.
  1.67
• Autoregressive Image Generation Needs Only A Few Lines Of Cached Tokens (2025)
  Ziran Qin, Youru Lv, Mingbao Lin, et al.
  1.28
• Unified Sparse-matrix Representations For Diverse Neural Architectures (2025)
  Yuzhou Zhu
  1.28
• Sg-blend: Learning An Interpolation Between Improved Swish And GELU For Robust Neural Representations (2025)
  Gaurav Sarkar, Jay Gala, Subarna Tripathi
  1.22
• CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers (2025)
  Yoshihiro Yamada
  1.17