works on

From the 2 of 34 linked papers with an AI index.

collaborators

34 papers

cs.AI2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.CL2026

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…