10 papers
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jindi Lv, Aoyu Li, Yuhao Zhou +6
Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a sev…
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
Jindi Lv, Hao Li, Jie Li +11
Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and…
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
Angen Ye, Boyuan Wang, Chaojun Ni +21
World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches fac…
VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking
Shunyu Liu, Minghao Liu, Huichi Zhou +31
Recent advances have showcased the extraordinary capabilities of Large Language Model (LLM) agents in tackling web-based information-seeking tasks. However, existing efforts mainly…
Multi-Path Collaborative Reasoning via Reinforcement Learning
Jindi Lv, Yuhao Zhou, Zheng Zhu +3
Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determini…
HyperNAS: Enhancing Architecture Representation for NAS Predictor via Hypernetwork
Jindi Lv, Yuhao Zhou, Yuxin Tian +3
Time-intensive performance evaluations significantly impede progress in Neural Architecture Search (NAS). To address this, neural predictors leverage surrogate models trained on pr…