0

Jian Liang

Papers
21

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
21papers

Authored papers

21

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

arXiv 2026

2026

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

preprint

2025

TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration

arXiv 2025

2025

Adapting Vision-Language Models Without Labels: A Comprehensive Survey

arXiv 2025

2025

MAPO: Mixed Advantage Policy Optimization

arXiv 2025

2025

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

arXiv 2025

2025

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

arXiv 2025

2025

To Trust Or Not To Trust Your Vision-Language Model's Prediction

arXiv 2025

2025

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

arXiv 2025

2025

DeepSeek-V3 Technical Report

arXiv 2024

2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

arXiv 2024

2024

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

arXiv 2024

2024

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation

arXiv 2024

2024

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay

arXiv 2024

2024

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

arXiv 2024

2024

Improving Zero-Shot Generalization for CLIP with Synthesized Prompts

ICCV 2023 1

2023

AdaptGuard: Defending Against Universal Attacks for Model Adaptation

ICCV 2023 1

2023

TALL: Thumbnail Layout for Deepfake Video Detection

ICCV 2023 1

2023

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

arXiv 2022

2022

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

NeurIPS 2021 12

2021

Pareto Domain Adaptation

pareto-domain-adaptation

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 21 papers