From the 2 of 34 linked papers with an AI index.
34 papers
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
Haozhe Hu, Hao Wu, Peiran Yin +3
WIDE introduces a token-level dynamic width pruning framework for large language model inference, allowing each token to selectively activate attention heads and feed‑forward chann…
Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT Calibration
Shuhao Li, Guodong Du, Anhao Zhao +3
The paper examines how supervised fine-tuning, reinforcement learning, and on‑policy distillation affect confidence estimates of large language models during chain‑of‑thought reaso…
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…
From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs
Xin Qiu, Junlong Tong, Yao Zhang +3
Time series analysis has recently been coupled with Large Language Models (LLMs) to leverage their reasoning and world knowledge capabilities, yet gains remain limited. We attribut…
UniRank: Unified Rank Allocation for Low-Rank LLM Compression
Chao Han, Haozhe Hu, Fei Ma +2
Low-rank decomposition serves as a promising compression paradigm for large language models, however, rank allocation remains challenging: manual rules lack generalizability, and l…
When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Siyang Lyu, Zhijing Sun, Xinghao Chen +3
Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces inflate both training and inference c…