◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Junhan Shi

5 papers hereh-index 2168 citations7 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author4

Across the 4 of 5 papers where every author was matched, so the position is known.

fields
  • cs.CL2
  • cs.AI1
  • cs.CV1
  • cs.LG1

identity via Semantic Scholar / OpenAlex

works on
adaptive pruning 1agentic systems 1batch processing 1evidence state management 1inference acceleration 1large language models 1multimodal reasoning 1omni-modal question answering 1speculative decoding 1training-free planning 1

From the 2 of 5 linked papers with an AI index.

most citedZ-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2026

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding

Hong Liu, Rui Cen, Junhan Shi +10

Speculative decoding accelerates large language model inference without changing the target distribution, but no single drafting structure performs best across real-world workloads…

cs.CL2026

D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding

Tianyu Liu, Yuhao Shen, Rui Cen +7

The paper introduces D-Cut, an adaptive method that prunes draft tokens across a batch to focus verification on the most promising tokens, improving the speed of speculative decodi…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.