Liang Chen

DreamEngine. Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!

G1. G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning

DnD-Transformer. [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation"

CGAN. 李宏毅GAN课程cGAN动漫人物头像生成实现代码(含训练数据)

MMEvalPro. [NAACL 2025] Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs

MLS. Source code of our paper "Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation" @ACL-2022

ParetoMNMT. Source code for paper "On the Pareto Front of Multilingual Neural Machine Translation" @ NeurIPS 2023

Genshin-Impact-NPC-Audio-Texts-Dataset. 收集了原神所有角色的中文语音文本内容

ATP-AMR. Source code for paper "ATP: AMRize Than Parse! Enhancing AMR Parsing with PseudoAMRs" @NAACL-2022

Gradient-Vaccine. (Unofficial) Implementation of ICLR 2021 paper "Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models"

FastV. Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

CTDNN. MMM 2021: Crossed-Time Delay Neural Network for Speaker Recognition

Two-Stage-CAMRP. Source code for paper "A Two-Stage Method for Chinese AMR Parsing" @ CAMRP-2022 & CCL-2022

Off-Target-MNMT. Code For Paper "On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation" @ACL2023

Dialogue_Summarization_Reproduce. Reproduce the result of different dialogue summarization models.

EnvInteractiveLMPapers. Paper collections of methods that using language to interact with environment, including interact with real world, simulated world or WWW(🏄).

Robust-Diffusion. Source code for project report "On The Robustness of Diffusion-Based Text-to-Image Generation" in CV-2022-Fall.

chenllliang.

pkunlp-icler.github.io. TeX

Kimi-VL. Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities

Qwen2-VL. Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

chenliang.github.io. Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

chenllliang.github.io. HTML

Huffman-Code. 用霍夫曼编码对文本文件进行压缩