4 citations · 4 across the 5 of their papers we have counts for
9 papers
Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
Saiyue Lyu, Jerrold Huang, Yunbei Zhang +4
Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We i…
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Jerrold Huang, Junwei Quan, Saiyue Lyu +2
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical…
Safety Must Survive Self-Improvement: Why Failures Persist and How Agents Recover
Yunbei Zhang, Janet Wang, Saiyue Lyu +5
Recursive self-improvement (RSI) allows agents to carry useful changes across generations. Maintaining safety across these generations involves both preventing unsafe behavior from…
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
Yunbei Zhang, Saiyue Lyu, Janet Wang +4
Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contribut…
SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering
Saiyue Lyu, Mariam Dundua, Vishaal Kapoor +5
Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying…
ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series
Saiyue Lyu, Zhitian Zhang, Ruizhi Deng +1
We present a diffusion based model for asynchronous time series prediction, where the goal is to predict the next inter event time and event type. To address the inherent uncertain…
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
Frederick Shpilevskiy, Saiyue Lyu, Krishnamurthy Dj Dvijotham +2
We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial examples, while adapting to the input. Our key insig…
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
Saiyue Lyu, Shadab Shaikh, Frederick Shpilevskiy +2
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoo…
DP-LDMs: Differentially Private Latent Diffusion Models
Michael F. Liu, Saiyue Lyu, Margarita Vinaroz +1
Diffusion models (DMs) are one of the most widely used generative models for producing high quality images. However, a flurry of recent papers points out that DMs are least private…