Key papers

• SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification (2026)
  Pragaash Ponnusamy et al.
  4.39
• VibeVoice-ASR-BitNet Technical Report (2026)
  Songchen Xu et al.
  4.39
• The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline (2026)
  Milos Suvakovic et al.
  3.51
• OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale (2026)
  Jingze Shi et al.
  3.23
• Pie: A Programmable Serving System for Emerging LLM Applications (2025)
  In Gim et al.
  3.10
• CausalMix: Data Mixture as Causal Inference for Language Model Training (2026)
  Zinan Tang et al.
  2.00
• Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots (2026)
  Ling Xu et al.
  2.00
• EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots (2026)
  Heqing Yang et al.
  2.00
• Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model (2026)
  Xinyin Ma et al.
  2.00
• HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better (2026)
  Gengluo Li et al.
  2.00
• EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs (2026)
  Jewon Yeom et al.
  1.94
• Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models (2026)
  Lin Zheng et al.
  1.94
• FastKernels: Benchmarking GPU Kernel Generation in Production (2026)
  Gabriele Oliaro et al.
  1.94
• InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching (2025)
  Yilun Wang and Pengfei Chen and Haiyu Huang and Zilong He and Gou Tan and Chuanfu Zhang and Jingkai He and Zibin Zheng
  1.33
• Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning (2025)
  Junhong Lin et al.
  1.28
• ReCode: Unify Plan and Action for Universal Granularity Control (2025)
  Zhaoyang Yu et al.
  1.28
• xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference (2025)
  Maximilian Beck et al.
  1.11
• Field-Programmable Deep Neural Network (DNN) Learning and Inference accelerator: a concept (2018)
  Luiz M Franca-Neto
  —
• LUTNet: Rethinking Inference in FPGA Soft Logic (2019)
  Erwei Wang et al.
  —
• NNStreamer: Efficient and Agile Development of On-Device AI Systems (2021)
  MyungJoo Ham et al.
  —
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning (2022)
  Haokun Liu et al.
  —
• TinySV: Speaker Verification in TinyML with On-device Learning (2024)
  Massimo Pavan et al.
  —
• LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale (2024)
  Jaehong Cho et al.
  —
• Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning (2024)
  Wei An et al.
  —
• Efficient LLM inference solution on Intel GPU (2023)
  Hui Wu et al.
  —
• Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models (2024)
  Keisuke Kamahori et al.
  —
• Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction (2024)
  Zhenmei Shi et al.
  —
• Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning (2024)
  Yifeng Ding et al.
  —
• SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation (2024)
  Aurick Qiao et al.
  —
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models (2024)
  Jiale Cheng et al.
  —