activity
20242026
collaborators

7 papers

cs.CL2026

MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues

Zheyuan Liu, Dongwhi Kim, Yixin Wan +4

Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk de…

cs.CL2025

Superficial Self-Improved Reasoners Benefit from Model Merging

Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu +4

As scaled language models (LMs) approach human-level reasoning capabilities, self-improvement emerges as a solution to synthesizing high-quality data corpus. While previous researc…

cs.LG2025

What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning

Yaning Jia, Chunhui Zhang, Xingjian Diao +4

Curriculum learning (CL) - ordering training data from easy to hard - has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs…

cs.CL2025

Steering Multimodal Large Language Models Decoding for Context-Aware Safety

Zheyuan Liu, Zhangchen Xu, Guangyao Dou +4

Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisions remains limited. Existing me…

cs.CL2025

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models

Zheyuan Liu, Guangyao Dou, Xiangchi Yuan +3

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal s…

cs.CL2025

Growing Through Experience: Scaling Episodic Grounding in Language Models

Chunhui Zhang, Sirui, Wang +3

Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approa…