ArXiv TLDR

Yu-Gang Jiang

4 papers · Latest:

Robotics

GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization

GuidedVLA enhances VLA models by specializing action attention heads with auxiliary signals to focus on task-relevant factors, improving generalization and robustness.

2605.12369
Robotics

World Action Models: The Next Frontier in Embodied AI

This survey introduces World Action Models (WAMs), a new embodied AI paradigm unifying predictive state modeling with action generation, providing a systematic overview.

2605.12090
Natural Language Processing

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models

ML-Bench&Guard provides a policy-grounded multilingual safety benchmark and dLLM guardrail for culturally and legally aligned LLM safety.

2605.00689
Computer Vision

ROSE: Retrieval-Oriented Segmentation Enhancement

ROSE is a plug-and-play framework that enhances MLLM segmentation by integrating real-time web retrieval to handle novel and emerging entities.

2604.14147

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.