10 papers
HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games
Zecong Tang, Zian Guan, Yuncheng Guo +3
Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and reliable native-interface cont…
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
Tengju Ru, Weitong Lian, Zecong Tang +6
Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relations, yet remains challenging for existing vision-language models.…
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
Yuhao Zhan, Bingxiang He, Zecong Tang +1
Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery afte…
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Qing Zong, Jiayu Liu, Junhao Shen +9
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedb…
IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation
Lingyi Meng, Zecong Tang, Haoran Li +12
In recent years, unified multimodal models (UMMs) have emerged to support both understanding and generation within a single framework. Mastering dynamic, multi-turn interleaved ima…
Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
Yi Zhang, Yinda Chen, Che Liu +26
We present Pelican-Unify 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unify 1.0 uses a single VLM as a unified understanding…
Imagine a City: CityGenAgent for Procedural 3D City Generation
Zishan Liu, Zecong Tang, RuoCheng Wu +6
The automated generation of interactive 3D cities is a critical challenge with broad applications in autonomous driving, virtual reality, and embodied intelligence. While recent ad…
Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving
Weitong Lian, Zecong Tang, Haoran Li +12
Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, larg…
Drive-P2D: A Progressive Perception-to-Decision Benchmark for VLMs in Autonomous Driving
Zecong Tang, Zixu Wang, Yifei Wang +10
Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reasoning and generalization abiliti…
CLEAR: A Clinically-Grounded Tabular Framework for Radiology Report Evaluation
Yuyang Jiang, Chacha Chen, Shengyuan Wang +8
Existing metrics often lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports, resulting in suboptim…