Yi Pan
7 papers · 2021–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (23) π₯ Mega-Team Β· Squad
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Deep Learning
(5)
Artificial Intelligence
(4)
Machine Learning
(4)
Core AI
(4)
Natural Language Processing
(3)
Application Areas
(3)
Models
(3)
Computer Vision
(2)
Learning Types
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Computer Science
(1)
Reinforcement Learning
(1)
Architectures
(1)
Domain-Specific
(1)
Keywords
large language model
(2)
multi-task learning
(2)
multi-agent reinforcement learning
(1)
online learning
(1)
video generation
(1)
direct preference optimization
(1)
medical imaging
(1)
preference optimization
(1)
policy learning
(1)
video retrieval
(1)
task-oriented dialogue
(1)
model merging
(1)
natural language understanding
(1)
minimax optimization
(1)
dialogue state tracking
(1)
intrinsic motivation
(1)
hierarchical structure
(1)
causal effect
(1)
zeroth-order optimization
(1)
parameter-efficient fine-tuning
(1)
Papers
MuxTune: Efficient Multi-Task LLM Fine-Tuning in Multi-Tenant Datacenters via Spatial-Temporal Backbone Multiplexing
NSDI 2026
AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs
ACL 2025
ECHOPulse: ECG Controlled Echocardio-gram Video Generation
ICLR 2025
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization
EMNLP 2025
ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval
EMNLP 2025
Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning
ICML 2023
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
NAACL 2021