2025

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning

EMNLP 2025

This paper introduces a two-stage SFT+RL framework that improves Video Temporal Grounding accuracy and robustness.

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning

EMNLP 2025

This paper introduces a two-stage SFT+RL framework that improves Video Temporal Grounding accuracy and robustness.

DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models
DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models

ACL 2025

Diffusion-styled Preference Optimization (DPO) is a plug-and-play, policy-agnostic inference-time alignment method that aligns LLMs at the sentence level to reduce latency while improving alignment quality across benchmarks and model scales.

DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models

ACL 2025

Diffusion-styled Preference Optimization (DPO) is a plug-and-play, policy-agnostic inference-time alignment method that aligns LLMs at the sentence level to reduce latency while improving alignment quality across benchmarks and model scales.

2024

Pad: Personalized alignment of llms at decoding-time
Pad: Personalized alignment of llms at decoding-time

Ruizhe Chen, Zuozhu Liu

ICLR 2025

Large Language Models Alignment.

Pad: Personalized alignment of llms at decoding-time

Ruizhe Chen, Zuozhu Liu

ICLR 2025

Large Language Models Alignment.

Learnable Privacy Neurons Localization in Language Models
Learnable Privacy Neurons Localization in Language Models

Ruizhe Chen, Tianxiang Hu, Zuozhu Liu

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024 main) 2024

Large Language Models Safety (Privacy).

Learnable Privacy Neurons Localization in Language Models

Ruizhe Chen, Tianxiang Hu, Zuozhu Liu

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024 main) 2024

Large Language Models Safety (Privacy).

2023

Pharetra Massa Massa Ultricies Mi Nisl Tincidunt
Pharetra Massa Massa Ultricies Mi Nisl Tincidunt

Charles Green*, John Doe*, Robert White, James Wang, Your Name# (* equal contribution, # corresponding author)

International Conference on Learning Representations (ICLR) 2023

Photo by Dessy Dimcheva on Unsplash. Please keep the description of your publication as brief as possible. 1~2 sentences is ideal. Otherwise, it will look too noisy. This is a counterexample to show how the publication will look like when the abstract is too long. The tangerine is a type of citrus fruit that is orange in color, that is considered either a variety of Citrus reticulata, the mandarin orange, or a closely related species, under the name Citrus tangerina, or yet as a hybrid (Citrus × tangerina) of mandarin orange varieties, with some pomelo contribution. According to the Oxford English Dictionary (OED), the word "tangerine" was originally an adjective meaning "Of or pertaining to, or native of Tangier, a seaport in Morocco, on the Strait of Gibraltar" and "a native of Tangier." The name was first used for fruit coming from Tangier, Morocco, described as a mandarin variety. The OED cites this usage from Addison's The Tatler in 1710 with similar uses from the 1800s. The adjective was applied to the fruit, once known scientifically as "Citrus nobilis var. tangeriana" which grew in the region of Tangiers. This usage appears in the 1800s.

Pharetra Massa Massa Ultricies Mi Nisl Tincidunt

Charles Green*, John Doe*, Robert White, James Wang, Your Name# (* equal contribution, # corresponding author)

International Conference on Learning Representations (ICLR) 2023

Photo by Dessy Dimcheva on Unsplash. Please keep the description of your publication as brief as possible. 1~2 sentences is ideal. Otherwise, it will look too noisy. This is a counterexample to show how the publication will look like when the abstract is too long. The tangerine is a type of citrus fruit that is orange in color, that is considered either a variety of Citrus reticulata, the mandarin orange, or a closely related species, under the name Citrus tangerina, or yet as a hybrid (Citrus × tangerina) of mandarin orange varieties, with some pomelo contribution. According to the Oxford English Dictionary (OED), the word "tangerine" was originally an adjective meaning "Of or pertaining to, or native of Tangier, a seaport in Morocco, on the Strait of Gibraltar" and "a native of Tangier." The name was first used for fruit coming from Tangier, Morocco, described as a mandarin variety. The OED cites this usage from Addison's The Tatler in 1710 with similar uses from the 1800s. The adjective was applied to the fruit, once known scientifically as "Citrus nobilis var. tangeriana" which grew in the region of Tangiers. This usage appears in the 1800s.

Fast model debias with machine unlearning
Fast model debias with machine unlearning

Ruizhe Chen, Jianfei Yang, Zuozhu Liu

Advances in Neural Information Processing Systems 2023

DL Fairness, Large Language Models Fairness, Machine Unlearning via Influence Function

Fast model debias with machine unlearning

Ruizhe Chen, Jianfei Yang, Zuozhu Liu

Advances in Neural Information Processing Systems 2023

DL Fairness, Large Language Models Fairness, Machine Unlearning via Influence Function

2022

Publication without cover image

Your Name, James Wang, Some Other Name, John Doe

International Conference on Learning Representations (ICLR) 2023

When the cover image is not provided, it will generate a random colorful bubble images as the cover image using the bubble_visual_hash.js script.

Publication without cover image

Your Name, James Wang, Some Other Name, John Doe

International Conference on Learning Representations (ICLR) 2023

When the cover image is not provided, it will generate a random colorful bubble images as the cover image using the bubble_visual_hash.js script.