12 papers
Continuous Speculative Decoding for Autoregressive Image Generation
Zili Wang, Zheng Zhang, Kun Ding +3
Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation, but their inherently sequential nature results in slow inference speed. Sp…
Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding
Lin Chen, Bolin Ni, Qi Yang +5
Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visu…
Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
Zili Wang, Jiajun Chai, Lin Chen +3
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as the standard paradigm for improving reasoning capability of large language models, while Multi-Token Prediction…
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
Yingjian Zhu, Xinming Wang, Kun Ding +3
Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-VQA). Despite recent advancements, pre…
VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agents
Zhengbo Zhang, Jinbo Su, Zhaowen Zhou +14
The rapid advancement of Multimodal Large Language Models (MLLMs) has enabled browsing agents to acquire and reason over multimodal information in the real world. But existing benc…
Taming Modality Entanglement in Continual Audio-Visual Segmentation
Yuyang Hong, Qi Yang, Tao Zhang +5
Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previ…