Latest Research in Machine Learning

Top Research Topics in Machine Learning

• Machine Learning — 47 papers
• Distributed, Parallel, and Cluster Computing — 27 papers
• Hardware Architecture — 22 papers
• Artificial Intelligence — 20 papers
• Computation and Language — 19 papers
• Parallel Computing and Optimization Techniques — 8 papers
• Performance — 5 papers
• Computer Vision and Pattern Recognition — 5 papers
• Adversarial Robustness in Machine Learning — 3 papers
• Security and Verification in Computing — 3 papers

Highest-Cited Papers

1. Adversarial Attack and Detection in Token‐Pruned Large Vision‐Language Models
2. D-Quant: Driftable Entropy Coding for KV Cache Quantization
3. PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving
4. The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
5. The Life of a Token: from Words to Bits on the Wire
6. Xronos: Heterogeneity-Aware Tensor Parallelism for Collaborative LLM Fine-Tuning on Edge CPUs
7. Exploring a Layer-Wise Design Space for KV Cache Eviction
8. Towards Training Private LLMs: Exploring Fine-Tuning Language Models on Apple Silicon with RDMA over Thunderbolt
9. The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound
10. Sub-Two-Bit Ternary Weight Storage with Table-Free Arithmetic Decoding for CPU Inference
11. Niko OS NikoBench: Characterizing the End-to-End Performance, Resource, and Accuracy Tradeoffs of Local Desktop Voice Agents on Commodity Hardware
12. Niko OS NikoBench: Characterizing the End-to-End Performance, Resource, and Accuracy Tradeoffs of Local Desktop Voice Agents on Commodity Hardware
13. Elastic Spectral State Space Models for Train-Once Budgeted Inference
14. GeoMesh: Workload-Balanced and Sign-Compressed Geo-Distributed LLM Training
15. HBFlex: A Flexible Memory System for Bridging Fine-Grained LLM States and Coarse-Grained HBF Parallel Execution
16. ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
17. Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training
18. Information-Geometric Trajectory Routing
19. High-Performance Tensor Formulation of the Viterbi Algorithm for Hidden Semi-Markov Models
20. End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services