14 papers
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
Xi Xiao, Chen Liu, Chih-Ting Liao +9
Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text. Despite inheriting strong reason…
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
Xiaomin Yu, Yi Xin, Yuhui Zhang +12
Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of d…
RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics
Danqi Liao, Chen Liu, Xingzhi Sun +8
Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex…
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
Chen Liu, Xingzhi Sun, Xi Xiao +8
Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling…
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation
Xi Xiao, Chenrui Ma, Yunbei Zhang +7
Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by trea…
RuleSmith: Multi-Agent LLMs for Automated Game Balancing
Ziyao Zeng, Chen Liu, Tianyu Liu +5
Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, the first framework that achieves…