25 papers
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
Zhekai Chen, Chengqi Duan, Kaiyue Sun +4
The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assist…
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots
Heqing Yang, Yang Yi, Liyao Wang +8
We present EVA-Client, an open-source framework for deployment, data collection, and evaluation of trained manipulation policies on real robots. Sitting between a policy server and…
UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization
Yaozhi Zheng, Yilei Jiang, Manyuan Zhang +5
Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multim…
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning
Hohin Kwan, Hongyu Li, Ray Zhang +5
Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events i…
InterleaveThinker: Reinforcing Agentic Interleaved Generation
Dian Zheng, Harry Lee, Manyuan Zhang +4
Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their archi…
AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
Yexin Liu, Wen-Jie Shu, Zile Huang +6
Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\…