8 papers
ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs
Zhiyuan Yao, Zheren Fu, Zhixiao Zheng +3
Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image. In this paper, we identify an internal s…
Multi-Block Diffusion Language Models
Yijie Jin, Jiajun Xu, Yuxuan Liu +8
Block Diffusion Language Models (BD-LMs) improve diffusion-based text generation with KV caching and flexible-length generation. A natural next step is to extend them from Single-B…
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
Chenkai Xu, Yijie Jin, Jiajun Li +8
Diffusion Large Language Models (dLLMs) have demonstrated significant potential for high-speed inference. However, current confidence-driven decoding strategies are constrained by…
Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
Xi Cao, Yuan Sun, Jiajun Li +3
DNN-based language models excel across various NLP tasks but remain highly vulnerable to textual adversarial attacks. While adversarial text generation is crucial for NLP security,…
SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
Dengcan Liu, Jiahao Li, Zheren Fu +4
Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. Howev…
APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
Yuzhen Zhou, Jiajun Li, Yusheng Su +15
Reinforcement learning (RL) has become a cornerstone in advancing large-scale pre-trained language models (LLMs). Successive generations, including GPT-o series, DeepSeek-R1, Kimi-…