Jin Song Dong

SpreadMark's innovative dense pseudo-random codeword embedding makes watermarking significantly more resilient to attacks, outperforming traditional methods in both robustness and imperceptibility.

LLMs can now diagnose diseases with the transparency of formal logic, offering verifiable reasoning chains that clinicians can audit and refine.

Forget red-teaming, POLARIS automatically turns safety policies into attack strategies, finding more LLM vulnerabilities with verifiable traceability.

Reference patches, typically discarded in software-engineering agent training, can be distilled into latent process graphs to guide trajectory curation, leading to more effective and efficient learning.

Stop writing incomplete tests: TestGeneralizer can automatically expand your existing tests to cover 31% more scenarios and catch more bugs.

LLMs can now predict project-wide code edits with significantly improved accuracy and efficiency by intelligently interleaving neural prediction with existing IDE tools.

Stop rewriting security rules for every SIEM platform: ARuleCon automates the process with 15% higher fidelity than existing LLMs.

Code-generating LLMs may ace static benchmarks, but developers are actually *slower* when using them because they disrupt mental flow, highlighting the need for benchmarks that capture the temporal dynamics of coding.

The trustworthiness of LLM-enabled applications hinges not on further model improvements, but on establishing system-level threat monitoring to detect post-deployment anomalies.

Self-evolving LLM agents can be persistently compromised by injecting malicious payloads into their long-term memory, turning them into "zombie agents" that execute unauthorized actions across sessions.