2026-07-02（周四） 收录 10 篇论文：Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts；ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving；MemSyco-Bench: Benchmarking Sycophancy in Agent Memory…
Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as changes in camera pose and shifts to a different but similar robot (e.g., from Pand...
In prefill-decode (PD) disaggregated LLM serving, each request is assigned to a decode worker after prefill. Existing decode routers balance only load; for mixture-of-experts (MoE) models this is inco...
Memory has emerged as a cornerstone of modern LLM-based agents, supporting their evolution from single-turn assistants to long-term collaborators. However, memory is not always beneficial: retrieved m...
Knowledge-Based Visual Question Answering (KB-VQA) aims to evaluate whether Visual Language Models (VLMs) can retrieve, ground, and reason over external structured knowledge beyond visual evidence. In...
As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video reasoning) and subs...
Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alter...
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated ...
In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of ...
Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the state-prediction separation hypothesis: disent...
Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world modeling,...