18 papers
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
Yantao Li, Huanlin Gao, Fang Zhao +12
Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless g…
MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment
Changhao Xiang, Shangyu Xing, Zhen Wu +2
Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual de…
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories
Changhao Xiang, Shilin Zhang, Zheng Ma +8
Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capabili…
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Yuhang Wu, Xiangqing Shen, Fanfan Wang +4
Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated…
LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation
Guanrong Li, Kuo Tian, Jinnan Qi +4
Conversational Recommender Systems (CRS) powered by Large Language Models (LLMs) enable users to articulate explicit and dynamic preferences, overcoming the limitations of fixed te…
GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models
Shangyu Xing, Changhao Xiang, Yuteng Han +6
Geometric shapes play important roles in both physical world and human cognition. While multimodal large language models (MLLMs) have made significant advancements in visual unders…