Yue Wang

This survey systematically reviews resource consumption threats in large language models (LLMs) to provide a unified view of the problem landscape, from threat induction to mitigation.

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language models, establishing reasoning safety as a critical security dimension.

The paper introduces a new security benchmark and framework to defend LLM agents against 'cognitive poisoning,' where malicious tools build trust through benign feedback before executing a harmful final action.

The paper introduces BAIT, a three-step jailbreak framework that systematically forces large language models to disclose harmful information by leveraging their internal reasoning and consistency tendencies.

The paper introduces PlanAudio, a unified LLM-based framework that directly synthesizes natural, composite audio containing speech and sounds from unconstrained free-form text prompts, outperforming existing methods.

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic tasks and embodiments.

MyoSem introduces an EMG-action semantic alignment framework that transforms low-level muscle signals into a shared semantic space, enabling bidirectional retrieval between EMG data and natural language action descriptions.

The paper introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly improving visual grounding and reasoning capabilities in VLMs.

RoboDream introduces an embodiment-centric world model that synthesizes photorealistic, physically feasible robot demonstrations by decoupling motion generation from environment synthesis, significantly reducing the need for expensive real-world data collection.