10 papers · 1 filter
EKT-Router: Expert-Evidence Alignment for Embodied Vision-Language Models
Weilin Ruan, Yingjie Xu, Yangkai Wei +7
Embodied vision-language models must answer questions from partial, evolving observations. Their success depends on both the reasoning capability selected and the evidence availabl…
Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
Weilin Ruan, Bohan Zhou, Jinghao Li +12
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant form…
ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression
Yuechuan Chen, Yanda Guo, Xiaoxi Liu +4
Some observation-window-based KV cache compressors use prompt attention to identify important tokens but allocate uniform or predefined budgets across heads, overlooking input-depe…
MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
Xilin Dang, Weilin Ruan, Xue Yang +4
Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by static parametric knowledge and c…
In-Context Learning for Robots: Methods and Applications
Haojian Huang, Zexi Li, Junhao Guo +36
General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this pro…
GenRouter: Unified Workflow Routing for Agentic Image Generation
Harold Haodong Chen, Zhiyu Hou, Wen-Jie Shu +4
The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfill…
MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
Songxin Lei, Kun Ouyang, Weilin Ruan +4
Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory…
Visual Reasoning over Time Series via Multi-Agent System
Weilin Ruan, Yuxuan Liang
Time series analysis underpins many real-world applications, yet existing time-series-specific methods and pretrained large-model-based approaches remain limited in integrating int…
SEDformer: Event-Synchronous Spiking Transformers for Irregular Telemetry Time Series Forecasting
Ziyu Zhou, Yuchen Fang, Weilin Ruan +3
Telemetry streams from large-scale Internet-connected systems (e.g., IoT deployments and online platforms) naturally form an irregular multivariate time series (IMTS) whose accurat…
TS-Memory: Plug-and-Play Memory for Time Series Foundation Models
Sisuo Lyu, Siru Zhong, Tiegang Chen +6
Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remain…