Scholar

Jing Li

Google Scholar ID: m07HrzQAAAAJ

Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, 100190, China.

segmentationdeep learningweakly supervised learning

Google Scholar↗

Citations & Impact

All-time

Citations

61

H-index

2

i10-index

1

Publications

3

Co-authors

0

Contact

No contact links provided.

Publications

15 items

Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation

2026

Cited

0

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks

2026

Cited

0

Modality-Decoupled Online Recursive Editing

2026

Cited

0

Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment

2026

Cited

0

TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation

2026

Cited

0

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding

2026

Cited

0

Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework

2026

Cited

0

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination

2026

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)