Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/8ICLR 2026Oral

Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding

Yuxuan Zhou · Fei Huang · Heng Li · Fengyi Wu · Tianyu Wang · jianwei zhang · Junyang Lin · Zhi-Qi Cheng

效率与系统代码OpenReview

一作ACL 2026Findings· Findings of ACL

G o V i G : Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning

Fengyi Wu · Yifei Dong · Yilong Dai · Guangyu Chen · Qifeng Wu · Huiting Huang · Hang Wang · Qi Dai · Alexander G Hauptmann · Zhi-Qi Cheng

摘要

We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to generate contextually coherent navigation instructions solely from egocentric visual observations of initial and goal states. Unlike prior work relying on structured inputs, such as semantic an...

多模态推理评测与基准OpenReview 项目页

作者位次 #2/12IROS 2026Poster· Benchmarking Robustness in Visual Navigation

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

Yifei Dong · Fengyi Wu · Qi He · Lingdong Kong · Li Heng · Minghan Li · Zebang Cheng · Yuxuan Zhou · Jingdong Sun · Qi Dai · Alexander Hauptmann · Zhi-Qi Cheng

多模态评测与基准社会与人本Vision-Based NavigationSoftware Tools for Benchmarking and ReproducibilitySimulation and AnimationOpenReview

Fengyi Wu

获取完整研究档案

联系方式

2026 顶会论文

Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding

G o V i G : Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

常见合作者