Pengliang Ji
7 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (22) π§ Keyword Pioneer π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (13)
π
Renaissance Researcher
(5)
π₯
Mega-Team
(20)
Conferences
NIPS (3)
ICCV (2)
ACL (1)
CORL (1)
Top co-authors
Keywords
large language model
(2)
model compression
(1)
contrastive learning
(1)
continual learning
(1)
catastrophic forgetting
(1)
zero-shot learning
(1)
benchmark evaluation
(1)
transfer learning
(1)
knowledge distillation
(1)
knowledge editing
(1)
depth estimation
(1)
test-time adaptation
(1)
model fitting
(1)
sharpness-aware minimization
(1)
loss landscape
(1)
3d pose estimation
(1)
3d human pose estimation
(1)
shape estimation
(1)
generative model
(1)
language model
(1)
Papers
Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts
ACL 2025
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
NIPS 2024
Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
NIPS 2024
Make Continual Learning Stronger via C-Flat
NIPS 2024
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
CORL 2024
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation
ICCV 2023
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
ICCV 2023