5 papers
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
Yushu Zhao, Zheng Wang, Minjia Zhang
Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input. However, their widespread…
From Context to Skills: Can Language Models Learn from Context Skillfully?
Shuzheng Si, Haozhe Zhao, Yu Lei +10
Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly lear…
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Haozhe Zhao, Shuzheng Si, Zhenhailong Wang +6
Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensi…
Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling
Zhixiang Liang, Beichen Huang, Zheng Wang +1
Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with m…
VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
Shengling Qin, Hao Yu, Chenxin Wu +10
This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when t…