World Action Models (WAMs) unify world modeling and action generation for robotic control by integrating flow-matching velocities, yet suffer from high multi-step denoising latency. Recent studies have explored speculative inference to accelerate WAMs by drafting and verifying denoising steps in parallel. However, existing methods either require training task-specific draft models or overlook critical WAM denoising dynamics when reusing past velocities as drafts. We revisit the denoising dynamics of WAMs and identify a dual nonuniformity that breaks standard velocity-reuse assumptions: velocity smoothness is nonuniform as adjacent velocity residuals differ sharply at early and final steps, so reuse there yields large residuals, which nonuniform integration time steps further translate into local state errors that accumulate into the final action distribution. Accordingly, we formalize this by theoretically deriving a trajectory error tolerance bound that characterizes how velocity residuals and integration time steps affect the final action distribution. Based on this, we propose WAMotor, the first speculative inference method tailored to the dual nonuniformity in WAMs. It selects reliable anchor velocities by deferring speculation and employs time-step-aware verification that scales acceptance thresholds by integration time step size. WAMotor offers plug-and-play benefits, enabling seamless integration with prior WAMs. Extensive evaluations on LIBERO, RoboTwin 2.0, and LIBERO-Plus show that WAMotor achieves 2.86$\times$--4.28$\times$ end-to-end speedups while maintaining task success rates. Our code is available at: https://github.com/Overdue-Lin/WAMotor
Zhiyang Li, Ao Ke Université de Montréal, Yukun Cao University of Science and Technology of China, Xike Xie
原文摘要
Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and scene graphs provide precisely complementary solutions to these respective deficiencies by providing rich external knowledge and capturing fine-grained visual details. However, prior works typically treat them in isolation, overlooking their synergistic potential. To bridge this gap, we propose KG-ViP, a unified framework that empowers MLLMs by fusing scene graphs and commonsense graphs. The core of the KG-ViP framework is a novel retrieval-and-fusion pipeline that utilizes the query as a semantic bridge to progressively integrate both graphs, synthesizing a unified structured context that facilitates reliable multi-modal reasoning. Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Mengjie Li Yonsei University, Yuan Feng, Xike Xie, William J. Song Yonsei University
原文摘要
The growing sequence length of large language models poses significant challenges for key-value (KV) caches. Existing state-of-the-art cache eviction methods primarily analyze the inference behavior of attention heads in successful retrieval-reasoning cases, often overlooking diverse behaviors in failure cases, such as bias and distraction. This oversight limits the potential to leverage heterogeneous head behaviors for improved eviction performance. Inspired by the confusion matrix, we introduce an Attention Behavior Matrix to comprehensively analyze attention head behaviors in both success and failure scenarios. By maximizing the signal-to-noise ratio — strengthening valid reasoning pathways in success cases while inhibiting noise from bias and distraction in failure cases — we propose REtrieval-reAsoning and Logic-constructed (REAL) KV cache eviction, the first method to leverage multi-behavior analysis. Comprehensive evaluations show that REAL achieves remarkable performance across various models and benchmarks; notably, on LongBench v2, it achieves comparable accuracy to the strongest baseline, HeadKV-R2, while requiring 32x less space. By offering a novel perspective on behavior analysis, we pave the way for a shift from success-only to comprehensive, failure-aware methods in long-context modeling. Our code is available at https://github.com/yonseicasl/REAL.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表