Author name cluster

Jianglin Lan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAMAS Conference 2026 Conference Paper

Scalable and Safe Multi-Agent Coordination with Reconstructed Level-k Monte Carlo Tree Search

Zhihao Lin
Lin Wu
Zhen Tian
Alessio Lomuscio
Jianglin Lan

Multi-agent coordination without central control requires balancing safety and computational efficiency. We present a novel frameworkthattransformsLevel-𝑘 cognitivereasoningfromadescriptive modelofboundedrationalityintoaconstructiveplanningalgorithm for agent coordination. Our key insight is to replace Level-𝑘 reasoning’s assumption of random Level-0 behavior with safety-oriented baselineswhereallagentscomputeconservativetrajectories. Safety emergesnaturallyfromtherecursivestructure: eachreasoninglevel inherits and strengthens the safety margins of lower levels, creating cascading conservatism that prevents collisions without explicit constraints. Beyond ensuring safety, this hierarchical conservatism also provides a natural foundation for efficient planning. By integrating this reconstructed hierarchy with Monte Carlo Tree Search (MCTS), we achieve significant computational advantages through two complementary mechanisms: a Dynamic Interaction Graph that constrains candidate interactions and reduces complexity from exponential to linear in agent count, and Safety-aware Pruning within MCTS that eliminates infeasible actions before evaluation. Weevaluateourframeworkonsymmetricmulti-agentintersections, demonstrating collision-free coordination and real-time efficiency across scenarios of varying complexity, highlighting its scalability and robustness for safety-critical planning.

PDF

NeurIPS Conference 2025 Conference Paper

HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion

Lin Wu
Zhixiang Chen
Jianglin Lan

Generating realistic 3D human-object interactions (HOIs) remains a challenging task due to the difficulty of modeling detailed interaction dynamics. Existing methods treat human and object motions independently, resulting in physically implausible and causally inconsistent behaviors. In this work, we present HOI-Dyn, a novel framework that formulates HOI generation as a driver-responder system, where human actions drive object responses. At the core of our method is a lightweight transformer-based interaction dynamics model that explicitly predicts how objects should react to human motion. To further enforce consistency, we introduce a residual-based dynamics loss that mitigates the impact of dynamics prediction errors and prevents misleading optimization signals. The dynamics model is used only during training, preserving inference efficiency. Through extensive qualitative and quantitative experiments, we demonstrate that our approach not only enhances the quality of HOI generation but also establishes a feasible metric for evaluating the quality of generated interactions. Project website: https: //wulin97. github. io/hoi-dyn

PDF Details

AAAI Conference 2023 Conference Paper

A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification

Jianglin Lan
Benedikt Brückner
Alessio Lomuscio

We introduce a novel method based on semidefinite program (SDP) for the tight and efficient verification of neural networks. The proposed SDP relaxation advances the present state of the art in SDP-based neural network verification by adding a set of linear constraints based on eigenvectors. We extend this novel SDP relaxation by combining it with a branch-and-bound method that can provably close the relaxation gap up to zero. We show formally that the proposed approach leads to a provably tighter solution than the present state of the art. We report experimental results showing that the proposed method outperforms baselines in terms of verified accuracy while retaining an acceptable computational overhead.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification

Jianglin Lan
Yang Zheng
Alessio Lomuscio

We propose an enhanced semidefinite program (SDP) relaxation to enable the tight and efficient verification of neural networks (NNs). The tightness improvement is achieved by introducing a nonlinear constraint to existing SDP relaxations previously proposed for NN verification. The efficiency of the proposal stems from the iterative nature of the proposed algorithm in that it solves the resulting non-convex SDP by recursively solving auxiliary convex layer-based SDP problems. We show formally that the solution generated by our algorithm is tighter than state-of-the-art SDP-based solutions for the problem. We also show that the solution sequence converges to the optimal solution of the non-convex enhanced SDP relaxation. The experimental results on standard benchmarks in the area show that our algorithm achieves the state-of-the-art performance whilst maintaining an acceptable computational cost.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations

Jianglin Lan
Yang Zheng
Alessio Lomuscio

We present a novel semidefinite programming (SDP) relaxation that enables tight and efficient verification of neural networks. The tightness is achieved by combining SDP relaxations with valid linear cuts, constructed by using the reformulation-linearisation technique (RLT). The computational efficiency results from a layerwise SDP formulation and an iterative algorithm for incrementally adding RLTgenerated linear cuts to the verification formulation. The layer RLT-SDP relaxation here presented is shown to produce the tightest SDP relaxation for ReLU neural networks available in the literature. We report experimental results based on MNIST neural networks showing that the method outperforms the state-of-the-art methods while maintaining acceptable computational overheads. For networks of approximately 10k nodes (1k, respectively), the proposed method achieved an improvement in the ratio of certified robustness cases from 0% to 82% (from 35% to 70%, respectively).

PDF Details