Zexin Wang
3 papers · 2024–2026 · 2 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
model compression
(1)
instruction following
(1)
reward hacking
(1)
vision-language model
(1)
multimodal representation
(1)
large vision-language model
(1)
model acceleration
(1)
parameter compression
(1)
cross-modal fusion
(1)
pareto optimal
(1)
token compression
(1)
multimodal named entity recognition
(1)
iterative reasoning
(1)
efficiency evaluation
(1)
pareto-optimal trade-off
(1)
training-free acceleration
(1)
curriculum reinforcement learning
(1)
reinforcement learning from verifiable reward
(1)
Papers
PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning
ACL 2026
EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models
ACL 2025
Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition
COLING 2024