Xianzhi Yu

TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time Scaling

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling

E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models

BoundaryDPT: Pushing the Boundaries of Depth Pruning for Vision Transformers

Benchmarking and Advancing Quantization-Aware Training for Reasoning Models

FuseGPT: Prune-and-Fuse Knowledge Redistribution for Efficient Transformers

Analytical Restructuring of Feed-Forward Networks for Accelerated LLM Inference

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

FlatQuant: Flatness Matters for LLM Quantization

MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE

AttentionPredictor: Temporal Patterns Matter for KV Cache Compression

A Simple Linear Patch Revives Layer-Pruned Large Language Models

FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs for Efficient Inference

FlatQuant: Flatness Matters for LLM Quantization