Scholar

Junlin Li

Google Scholar ID: daHqpg8AAAAJ

ByteDance Inc. - Georgia Institute of Technology - Tsinghua University

Video Compression and ProcessingVideo StreamingMachine LearningAIASIC Design

Google Scholar↗

Citations & Impact

All-time

Citations

780

H-index

17

i10-index

21

Publications

20

Co-authors

0

Contact

No contact links provided.

Publications

30 items

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

2026

Cited

0

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

2026

Cited

0

A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

2026

Cited

0

VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought

2026

Cited

0

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

2026

Cited

0

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

2026

Cited

0

Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution

2026

Cited

0

Eliminating VAE for Fast and High-Resolution Generative Detail Restoration

2026

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)