Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection Paper • 2602.03216 • Published 5 days ago • 12
LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning Paper • 2510.14211 • Published Oct 16, 2025 • 8
QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models Paper • 2509.17428 • Published Sep 22, 2025 • 9