Zhuoshi Pan
12 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (4) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (23) π Cross-Pollinator (11)
π
Renaissance Researcher
(6)
β‘
Prolific Year
(7)
Conferences
ACL (7)
EMNLP (3)
ICLR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
mathematical reasoning
(3)
large language model
(3)
chain-of-thought reasoning
(2)
model security
(1)
attention mechanism
(1)
language model
(1)
efficient computing
(1)
efficient inference
(1)
length extrapolation
(1)
token classification
(1)
adversarial attack
(1)
diffusion model
(1)
vision-language model
(1)
synthetic datum
(1)
data selection
(1)
token selection
(1)
supervised fine-tuning
(1)
inference optimization
(1)
data poisoning
(1)
image generation
(1)
Papers
REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
ACL 2026
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
ACL 2026
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
ACL 2026
LEMMA: Learning from Errors for MatheMatical Advancement in LLMs
ACL 2025
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
EMNLP 2025
MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer
EMNLP 2025
SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
ICLR 2025
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
EMNLP 2025
MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
ACL 2025
InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes Under Herd Behavior
ACL 2025
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
NIPS 2024
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
ACL 2024