Tao Wang

Vol-Mark proposes a robust, reversible-zero watermarking technique for 3D medical volume data, achieving high accuracy in verifying ownership and integrity even after various types of attacks.

This paper proposes a cloud-edge-end collaborative defense framework to secure UAV swarms against various threats like GPS spoofing and multi-hop intrusions, demonstrating its effectiveness through experimental validation.

ResearchLoop introduces an evidence-gated control plane to manage and audit the state of AI-assisted computational research, mitigating the risk of unverified claims.

The paper introduces MemPoison, a novel memory poisoning attack that successfully injects triggerable backdoors into LLM agents' long-term memory through conversational interactions, achieving high attack success rates by bypassing selective memory mechanisms.

The paper proposes MemPoison, a novel memory poisoning attack that injects triggerable backdoors into LLM agents' long-term memory through dialogue interactions, achieving high success rates by bypassing selective memory mechanisms.

This paper proposes a Signal Cost Proxy framework, drawing from signaling theory, to systematically evaluate the contextual appropriateness of empathy in AI interactions.

The paper proposes GIM-World, a geometry-aware implicit memory framework that significantly improves long-horizon video world models by explicitly encoding 3D scene geometry into a compact memory state.

This paper provides new upper bounds and algorithms for the shortest path map equivalence decomposition of a polygonal domain, leading to solutions for two-point shortest path queries, geodesic diameter, and center.

This paper proposes a recovery routing system for coding agents that uses a supervised router and Conformal Risk Control (CRC) layer to determine when to spend more compute or escalate to a stronger model.

This paper tests the influence of Big Five personality on partner selection in multi-agent LLM systems, finding strong and task-stereotyped effects that diverge from human team performance.

This paper introduces ClinFusion, a vision-centric multimodal large language model designed for holistic medical understanding, featuring a Cascade Spatial-Aware Locality Fusion operator and a vision-grounded evaluation framework.

The paper proposes K-line--Quantile Sequential Projection (KQSP), a method to reconcile quantile and K-line crossing inconsistencies in probabilistic K-line forecasting without reordering, specialized architectures, or penalized training objectives.