collaborators

5 papers

cs.LG2026

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective

Yangyi Huang, Ruotian Peng, Zeju Qiu +4

Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking t…

cs.LG2025

Evaluating Parameter Efficient Methods for RLVR

Qingyu Yin, Yulun Wu, Zhennan Shen +6

We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language mo…

cs.CV2025

C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection

Siheng Wang, Zhengdao Li, Yanshu Li +12

Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and ins…

cs.CL2025

MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure

Jiale Kang, Qingyu Yin

Low-Rank Adaptation (LoRA) is a widely adopted technique for parameter-efficient fine-tuning, but its slow convergence has spurred the development of numerous variants. Nevertheles…

cs.CL2025

ModRWKV: Transformer Multimodality in Linear Time

Jiale Kang, Ziyin Yue, Qingyu Yin +4

Currently, most multimodal studies are based on large language models (LLMs) with quadratic-complexity Transformer architectures. While linear models like RNNs enjoy low inference…