pith. sign in

Xiaolong Ma

Identifiers

  • name variant Xiaolong Ma 0.60 · backfill

Papers (21)

  1. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement cs.CL · 2026 · author #9
  2. ERNIE-Image Technical Report cs.CV · 2026 · author #27
  3. PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts cs.CL · 2026 · author #3
  4. Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation cs.LG · 2026 · author #7
  5. SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization cs.LG · 2026 · author #2
  6. From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs cs.LG · 2026 · author #14
  7. Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking cs.CV · 2026 · author #7
  8. Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models cs.LG · 2026 · author #5
  9. Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning cs.LG · 2024 · author #7
  10. Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM cs.LG · 2019 · author #2
  11. 26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone cs.LG · 2019 · author #2
  12. ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning cs.LG · 2019 · author #1
  13. Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM cs.NE · 2019 · author #4
  14. StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs cs.NE · 2018 · author #4
  15. Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICs cs.DC · 2018 · author #4
  16. C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing cs.CV · 2018 · author #2
  17. Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework cs.LG · 2018 · author #6
  18. Image Dataset for Visual Objects Classification in 3D Printing cs.CV · 2018 · author #2
  19. An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing cs.NE · 2018 · author #1
  20. CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices cs.CV · 2017 · author #11
  21. Person Re-Identification by Unsupervised Video Matching cs.CV · 2016 · author #1

Mentions

  • 2606.11926 #9 · arxiv_oai · confidence 0.70 Xiaolong Ma
  • 2605.25347 #27 · arxiv_oai · confidence 0.70 Xiaolong Ma
  • 2601.06163 #7 · arxiv_oai · confidence 0.70 Xiaolong Ma
  • 2601.06162 #5 · arxiv_oai · confidence 0.70 Xiaolong Ma

Frequent Coauthors