Jie Zhou
7 papers · Latest:
BAMI: Training-Free Bias Mitigation in GUI Grounding
BAMI is a training-free method that uses coarse-to-fine focus and candidate selection to mitigate precision and ambiguity biases in GUI grounding models.
UVMarvel: an Automated LLM-aided UVM Machine for Subsystem-level RTL Verification
UVMarvel automates UVM testbench creation for subsystem-level RTL verification using LLMs, significantly boosting efficiency and coverage.
Action-Aware Generative Sequence Modeling for Short Video Recommendation
A2Gen improves short video recommendations by modeling user actions as temporal sequences, leading to significant engagement boosts.
UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection
UniGenDet is a unified generative-discriminative framework that co-evolves image generation and detection, achieving state-of-the-art performance.
Do MLLMs Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision
This paper introduces EgoPoint-Bench to benchmark and enhance MLLMs' understanding of pointing gestures in egocentric vision, addressing "Referential Hallucination."
Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
ProactAgent enables lifelong learning agents to proactively retrieve relevant experience and skills only when needed, improving performance and efficiency.
ShapeGen: Robotic Data Generation for Category-Level Manipulation
ShapeGen generates diverse robotic manipulation data in 3D to improve category-level generalizability without requiring a simulator.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.