collaborators

7 papers

cs.CV2026

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…

cs.AI2026

CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback

Bin Chen, Xinye Liao, Yiming Liu +2

Recent LLM search agents use reinforcement learning with verifiable rewards (RLVR) to learn search-augmented reasoning from outcome rewards. On hard problems, these agents rarely s…

cs.LG2026

Rethinking LLM Ensembling from the Perspective of Mixture Models

Jiale Fu, Yuchu Jiang, Peijun Wu +3

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multi…

cs.CL2026

VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models

Chonghan Liu, Yimin Du, Qi An +8

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances.…

cs.CL2026

Flatter Tokens are More Valuable for Speculative Draft Model Training

Jiaming Fan, Daming Cao, Xiangzhong Luo +3

Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach…

cs.CL2026

dCache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching

Yuchu Jiang, Yue Cai, Xiangzhong Luo +4

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional att…