8 papers
Repeated-Game Security for Restaking-Based Verifiable Inference
Zhenhang Shang, Yingzhe Yu, Kani Chen
Restaking-based protocols enable verifiable LLM inference without the high proving cost of zkML or the hardware trust assumptions of TEEs. Their security is commonly justified by a…
CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning
Zibin Meng, Kani Chen
Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged…
RegGuard: Legitimacy and Fairness Enforcement for Optimistic Rollups
Zhenhang Shang, Yingzhe Yu, Kani Chen
Optimistic rollups provide scalable smart-contract execution but remain unsuitable for regulated financial applications due to three structural gaps: semantic legitimacy, cross-lay…
Economic Security of VDF-Based Randomness Beacons: Models, Thresholds, and Design Guidelines
Zhenhang Shang, Kani Chen
Randomness beacons based on Verifiable Delay Functions (VDFs) are increasingly proposed for blockchains and distributed systems, promising publicly verifiable delay and bias resist…
Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates
Zhenhang Shang, Yingzhe Yu, Kani Chen
Fine-tuning is the dominant paradigm for adapting large machine learning models, yet current deployment pipelines provide no way to verify how a released model was updated. In part…
PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction
Zibin Meng, Kani Chen
Human-like agents must express stable dispositions while adapting to roles, relationships, and norms. We present PsyAgent, a schema-first framework that operationalizes the trait-c…
AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles
Wenkai Fan, Shurui Zhang, Xiaolong Wang +7
AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent architecture, aiming to sustain long-hori…
TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
Jianda Mao, Kaibo Wang, Yang Xiang +1
Large-scale pre-trained diffusion models empower users to edit images through text guidance. However, existing methods often over-align with target prompts while inadequately prese…