Yu
50 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces MindView, a benchmark for generative multi-view spatial intelligence, and proposes methods to improve target-view generation and evidence utilization.
This paper proposes VISH, a training-free framework for selecting a compact hotword subset from large dynamic inventories.
This paper develops CAESAR, an end-to-end MR framework for evaluating cognitive attacks in collaborative search-and-rescue training.
The paper proposes a new framework for data augmentation that prioritizes regions with strong texture responses for style replacement.
This paper investigates the neighborhood topology of particle swarm optimization (PSO) and its impact on information flow and exploration-exploitation balance.
The paper introduces DeepSciReasoner, a framework for predicting scientific spectra under physical constraints.
The paper proposes two methods for detecting memorization in unconditional diffusion models using sequential monitoring and conformal calibration.
This paper introduces HIFI, a two-stage fine-tuning framework for statistical inference on parameters such as conditional means, which scales to large foundation models and reduces training compute.
This paper investigates security risks in Steering plugins for large language models and proposes a malicious plugin and a runtime defense framework to counter such threats.
A lending protocol with reduced risks is proposed, where lenders and borrowers set competing interest rates.
This paper introduces ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination.
This paper proposes a new recommendation model, LESSRec, that improves the effectiveness of semantic ID-based recommendation by restricting attention to historical tokens at the target token's semantic level and providing an item-level semantic sequence.
This paper presents WxCrop, an agent that predicts crop loss from weather data and agricultural information.
EviSeek is a training-free framework that makes question-derived evidence demands explicit acquisition objectives.
This paper introduces BEAKER, a benchmark for evaluating embodied AI capabilities in self-driving chemical laboratories.
The paper introduces FrontierPhysics, an end-to-end benchmark for evaluating AI agents in physics research.
The paper examines the relationship between occupational AI exposure and job conditions using O*NET data.
The paper presents IMUDINO, a foundation model for inertial sensing that achieves competitive performance across diverse sensing tasks.
The paper introduces Flex-RSI, a benchmark for evaluating the recursive self-improvement of agents on vision and robotics tasks.
This paper proposes a flow-guided target-space alignment method called FlowAlign that improves instance-level correspondence while preserving target-space structure in multimodal alignment problems.
Papers
Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents
Jingdong Zhang, Jionghao Wang, Zhengming Yu, Yancheng Cai +18 more
The paper introduces Flex-RSI, a benchmark for evaluating the recursive self-improvement of agents on vision and robotics tasks.