Ling Pan
Assistant Professor, EE; CS (by courtesy) at 
Hong Kong University of Science and Technology
Previously Postdoctoral Fellow at Mila
About
Ling Pan’s Let the flows tell applies generative flow networks to solve graph combinatorial optimization problems. Pan is an Assistant Professor at the Hong Kong University of Science and Technology in the departments of Electronic and Computer Engineering and Computer Science and Engineering. Her research centers on RL, multi-agent systems, and computational sustainability, including Scaling image and video generation via test-time evolutionary search. She also introduced actor rectification for offline multi-agent RL and developed a deep RL framework for rebalancing dockless bike-sharing systems. Previously, Pan was a postdoctoral fellow at Mila under Yoshua Bengio and completed her PhD at Tsinghua University’s Institute for Interdisciplinary Information Sciences. She has held visiting research positions at Stanford University and the University of Oxford.
Experience
Assistant Professor, EE; CS (by courtesy)
2024 – Present
Hong Kong University of Science and Technology
Leads the Intelligent Decision-Making Lab.
2024 – Present
Journal Track Co-Chair
2026 – 2026
Asian Conference on Machine Learning (ACML)
2026 – 2026
Agent-based Information Retrieval Workshop @ SIGIR
Organizer
2025 – 2025
2025 – 2025
Organizer
2024 – 2024
2024 – 2024
Organizer
2024 – 2024
Safe Generative AI Workshop @ NeurIPS
2024 – 2024
Postdoctoral Fellow
2022 – 2024
Mila
Supervised by Prof. Yoshua Bengio.
2022 – 2024
Organizer
2023 – 2023
GFlowNet Workshop @ Mila
2023 – 2023
CS PhD Student
2017 – 2022
Conducted doctoral research in the Institute for Interdisciplinary Information Sciences.
2017 – 2022
Papers60
Pre-Trained Video Generative Models as World Simulators
Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images), limiting their ability to model interactive and dynamic scenarios. In this paper, we propose Dynamic World Simulation (DWS), a novel approach to transform pre-trained video generative models into controllable world simulators capable of executing specified action trajectories. To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module that seamlessly integrates into any existing model. Instead of focusing on complex visual details, we demonstrate that consistent dynamic transition modeling is the key to building powerful world simulators. Building upon this insight, we further introduce a motion-reinforced loss that enhances action controllability by compelling the model to capture dynamic changes more effectively. Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models, achieving significant improvements in generating action-controllable, dynamically consistent videos across games and robotics domains. Moreover, to facilitate the applications of the learned world simulator in downstream tasks such as model-based reinforcement learning, we propose prioritized imagination to improve sample efficiency, demonstrating competitive performance compared with state-of-the-art methods.
Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning
Multi-user delay constrained scheduling is important in many real-world applications including wireless communication, live streaming, and cloud computing. Yet, it poses a critical challenge since the scheduler needs to make real-time decisions to guarantee the delay and resource constraints simultaneously without prior information of system dynamics, which can be time-varying and hard to estimate. Moreover, many practical scenarios suffer from partial observability issues, e.g., due to sensing noise or hidden correlation. To tackle these challenges, we propose a deep reinforcement learning (DRL) algorithm, named Recurrent Softmax Delayed Deep Double Deterministic Policy Gradient (), which is a data-driven method based on a Partially Observed Markov Decision Process (POMDP) formulation. guarantees resource and delay constraints by Lagrangian dual and delay-sensitive queues, respectively. It also efficiently tackles partial observability with a memory mechanism enabled by the recurrent neural network (RNN) and introduces user-level decomposition and node-level merging to ensure scalability. Extensive experiments on simulated/real-world datasets demonstrate that is robust to system dynamics and partially observable environments, and achieves superior performances over existing DRL and non-DRL-based methods.
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs incorporate diverse data modes in the pre-training stage, and the finetuning dataset often contains demonstration data collected in a kinematically suboptimal or undesirable way, it exists redundant action modes that are irrelevant to the success action modes of the downstream task. Specifically, we observe a critical inference-time fragility among various sampled noises after supervised finetuning of pre-trained VLAs. In this paper, we attribute this instability to the distribution shift between the VLA policy and the policy induced by stable success modes of the downstream task dataset. Thus, we propose TACO, a test-time-scaling (TTS) framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks. The VLA models integrated with TACO can execute the actions with maximum pseudo-count from all sampled action chunks, thereby preventing distribution shifts while preserving the generalization ability of VLAs since the constraint is applied only during inference. Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits compared to RL update, especially for flow or diffusion-based VLAs which are difficult to perform RL update due to denoising process. Extensive experiments across four simulation benchmarks (RoboTwin2.0, Robotwin, LIBERO, SimplerEnv) and a dual-arm platform demonstrate that our method significantly improves the inference stability and success rates in downstream-task adaptations.
Neuroplastic Expansion in Deep Reinforcement Learning
The loss of plasticity in learning agents, analogous to the solidification of neural pathways in biological brains, significantly impedes learning and adaptation in reinforcement learning due to its non-stationary nature. To address this fundamental challenge, we propose a novel approach, Neuroplastic Expansion (NE), inspired by cortical expansion in cognitive science. NE maintains learnability and adaptability throughout the entire training process by dynamically growing the network from a smaller initial size to its full dimension. Our method is designed with three key components: (1) elastic topology generation based on potential gradients, (2) dormant neuron pruning to optimize network expressivity, and (3) neuron consolidation via experience review to strike a balance in the plasticity-stability dilemma. Extensive experiments demonstrate that NE effectively mitigates plasticity loss and outperforms state-of-the-art methods across various tasks in MuJoCo and DeepMind Control Suite environments. NE enables more adaptive learning in complex, dynamic environments, which represents a crucial step towards transitioning deep reinforcement learning from static, one-time training paradigms to more flexible, continually adapting models.
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, existing methods mainly apply uniform optimization constraints across all tokens, ignoring their heterogeneous roles. Prior work shows that high-entropy tokens are closely tied to reasoning, while low-entropy tokens primarily encode factual knowledge, and recent approaches attempt to exploit this distinction by isolating token updates via masking or asynchronous training. We argue that such isolation breaks the sequential dependency structure of autoregressive generation, leading to suboptimal learning. To address this, we propose Archer, an entropy-aware RLVR framework with dual-token constraints that preserves joint optimization while modulating update strength across token types. Our method introduces response-level entropy normalization for stable token classification and applies differentiated clipping ranges and KL regularization to encourage exploration on reasoning tokens while preserving knowledge tokens. Experiments on mathematical reasoning and code generation benchmarks show that Archer consistently outperforms strong baselines across multiple model scales, improving both pass@1 and pass@K performance. These results highlight the importance of respecting sequence-level dependencies when designing fine-grained RL optimization strategies for LLMs.
Complementary RL: Towards Efficient Experience-Driven Agent Learning
Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior experience across episodes. While augmenting agents with historical experience offers a promising remedy, existing approaches suffer from a critical weakness: the experience distilled from history is either stored statically or fail to coevolve with the improving actor, causing a progressive misalignment between the experience and the actor's evolving capability that diminishes its utility over the course of training. Inspired by complementary learning systems in neuroscience, we present Complementary RL to achieve seamless co-evolution of an experience extractor and a policy actor within the RL optimization loop. Specifically, the actor is optimized via sparse outcome-based rewards, while the experience extractor is optimized according to whether its distilled experiences demonstrably contribute to the actor's success, thereby evolving its experience management strategy in lockstep with the actor's growing capabilities. Empirically, Complementary RL outperforms outcome-based agentic RL baselines that do not learn from experience, achieving 10% performance improvement in single-task scenarios and exhibits robust scalability in multi-task settings. These results establish Complementary RL as a paradigm for efficient experience-driven agent learning.
Part II: ROLL Flash - Accelerating RLVR and Agentic Training with Asynchrony
Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems designed to accelerate RL post-training still suffer from low resource utilization and limited scalability. We present ROLL Flash, a system that extends ROLL with native support for asynchronous RL post-training. ROLL Flash is built upon two core design principles: fine-grained parallelism and rollout-train decoupling. Guided by these principles, ROLL Flash provides flexible programming interfaces that enable a fully asynchronous training architecture and support efficient rollout mechanisms, including queue scheduling and environment-level asynchronous execution. Through comprehensive theoretical analysis and extensive experiments, we demonstrate that ROLL Flash significantly improves resource utilization and scalability over synchronous RL post-training. ROLL Flash achieves up to 2.24x speedup on RLVR tasks and 2.72x on agentic tasks, using the same GPU budget as synchronous baselines. Furthermore, we implement several popular off-policy algorithms and verify that asynchronous training can achieve performance on par with synchronous training.
When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
Outcome-supervised reinforcement learning can avoid entropy collapse by strengthening updates to underrepresented tokens in successful responses, enabling steadier reasoning and coding improvement.
Scaling Image and Video Generation via Test-Time Evolutionary Search
As the marginal cost of scaling computation (data and parameters) during model pre-training continues to increase substantially, test-time scaling (TTS) has emerged as a promising direction for improving generative model performance by allocating additional computation at inference time. While TTS has demonstrated significant success across multiple language tasks, there remains a notable gap in understanding the test-time scaling behaviors of image and video generative models (diffusion-based or flow-based models). Although recent works have initiated exploration into inference-time strategies for vision tasks, these approaches face critical limitations: being constrained to task-specific domains, exhibiting poor scalability, or falling into reward over-optimization that sacrifices sample diversity. In this paper, we propose Evolutionary Search (EvoSearch), a novel, generalist, and efficient TTS method that effectively enhances the scalability of both image and video generation across diffusion and flow models, without requiring additional training or model expansion. EvoSearch reformulates test-time scaling for diffusion and flow models as an evolutionary search problem, leveraging principles from biological evolution to efficiently explore and refine the denoising trajectory. By incorporating carefully designed selection and mutation mechanisms tailored to the stochastic differential equation denoising process, EvoSearch iteratively generates higher-quality offspring while preserving population diversity. Through extensive evaluation across both diffusion and flow architectures for image and video generation tasks, we demonstrate that our method consistently outperforms existing approaches, achieves higher diversity, and shows strong generalizability to unseen evaluation metrics. Our project is available at the website this https URL
Metrics
Citations per year
Coauthors
