11 papers · 1 filter
Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
Chao Han, Haozhe Hu, Xiaoyu Shen
Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance d…
UniRank: Unified Rank Allocation for Low-Rank LLM Compression
Chao Han, Haozhe Hu, Yongjie Du +5
Low-rank decomposition is a promising compression paradigm for large language models (LLMs), yet its effectiveness hinges on rank budget allocation across weight matrices: uniform…
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Xinghao Chen, Chak Tou Leong, Wenjin Guo +3
Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent…
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
Anhao Zhao, Junlong Tong, Yingqi Fan +3
Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo esti…
Escaping the KL Agreement Trap in On-Policy Distillation
Haoran Xin, Anhao Zhao, Ying Sun +3
On-policy distillation (OPD) provides dense token-level supervision by asking a teacher to score student-generated rollouts. However, when the student drifts into an unrecoverable…
Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy
Haozhe Hu, Hao Wu, Anhao Zhao +4
Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers…
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
Junzhe Yang, Xiaoyu Shen
The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importa…
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
Hao Chen, Qi Zhang, Liyao Li +7
Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selecti…
Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
Anhao Zhao, Haoran Xin, Yingqi Fan +3
Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (RL). We show that the prevailin…
From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models
Longwei Ding, Anhao Zhao, Fanghua Ye +2
Large language models (LLMs) are increasingly costly to deploy, motivating extensive research on model pruning. However, most existing studies focus on instruction-following LLMs,…
The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models
Xin Qiu, Junlong Tong, Yirong Sun +2
Large-scale models are at the forefront of time series (TS) forecasting, dominated by two paradigms: fine-tuning text-based Large Language Models (LLM4TS) and training Time Series…