Zhonglin Jiang
4 papers · 2025–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
information bottleneck
(1)
image synthesis
(1)
partially observable markov decision process
(1)
model-based reinforcement learning
(1)
diffusion model
(1)
language model
(1)
world model
(1)
attention head
(1)
frequency analysis
(1)
layout-to-image generation
(1)
dialogue system
(1)
key-value cache compression
(1)
emotional support conversation
(1)
long-context inference
(1)
dynamic retrieval
(1)
frequency disentanglement
(1)
degraded image generation
(1)
latent diffusion space
(1)
contextual guidance
(1)
Papers
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
ACL 2026
Convert Language Model into a Value-based Strategic Planner
ACL 2025
Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
EMNLP 2025
FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation
ICCV 2025