Hao Yang

The paper introduces AutoEG, a fully automated multi-agent framework that significantly improves the exploitation of known third-party vulnerabilities in black-box web applications by achieving an 82.41% average success rate.

The paper demonstrates that confronting Large Reasoning Models (LRMs) with conflicting objectives, such as contradictory choices or conflicting alignment values, significantly increases their vulnerability to harmful attacks.

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rather than just malicious user prompts.

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Models (LVLMs).

The paper introduces CityGen, a diffusion-based framework that enables zero-label city adaptation for autonomous driving by synthesizing city-style data conditioned on HD maps and visual prompts, significantly improving cross-city generalization.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

InfoAtlas is a foundation model that estimates statistical mutual information (MI) in a single forward pass, achieving state-of-the-art accuracy with a massive speedup compared to traditional iterative neural estimators.

The paper proposes $HE^2$, a novel communication-light heterogeneous accelerator architecture that significantly improves the efficiency of Fully Homomorphic Encryption (FHE) by optimizing dataflow and minimizing inter-component communication overhead.

The paper proposes $HE^2$, a novel communication-light heterogeneous accelerator architecture that significantly improves the efficiency of Fully Homomorphic Encryption (FHE) by optimizing dataflow and minimizing inter-processor communication overhead.

This paper investigates the fundamental limits and optimal design for Integrated Sensing and Communication (ISAC) systems under noncoherent conditions, deriving a lower bound for noncoherent mutual information and optimizing spatial power allocation.

Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.

The paper introduces Agon, a research orchestrator that validates and checks research claims using large language models and leaves the remaining judgments to human scientists.

The paper introduces IdeaGene-Bench, a benchmark for scientific lineage reasoning and idea generation, which includes 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise GenomeDiff records.

The paper introduces SceneActBench, a benchmark for evaluating vision-language model agents' ability to perform actions on multi-object 3D scenes.

The paper presents CHASE, an application-driven framework that explores physically feasible Cross-layer Heterogeneous System architectures for executing workloads with diverse requirements.

This paper presents DOPS, a hardware-aware framework for optimizing operator scheduling and weight layouts in Large Language Models, achieving significant speedups over prefill-decode disaggregation.