Longbo Huang
Professor, IIIS at 
Previously Postdoctoral Researcher, EECS at 
University of California at Berkeley
About
Longbo Huang’s Latent Consistency Models enable high-resolution image synthesis through a compressed, few-step inference process. He is a Professor at the Institute for Interdisciplinary Information Sciences at Tsinghua University and an ACM Distinguished Scientist. As director of the Decision Intelligence Lab, his research focuses on RL, deep RL, and the optimization of stochastic networks. Huang also developed LCM-LoRA to accelerate Stable Diffusion and has published on the provable advantages of multi-modal learning over single-modality training. He received his Ph.D. from the University of Southern California and was a postdoctoral researcher at UC Berkeley. He currently serves on the editorial boards of IEEE TPAMI and TMLR.
Experience
Professor, IIIS
2012 – Present
Tsinghua University · Beijing, China
Directs the Decision Intelligence Lab@IIIS (DI Lab).
2012 – Present
Associate Editor
2023 – Present
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
2023 – Present
Associate Editor
2022 – Present
Elsevier Performance Evaluation (PEVA)
2022 – Present
Director
2020 – Present
Decision Intelligence Lab@IIIS (DI Lab) · Beijing, China
2020 – Present
Editor
2019 – Present
IEEE/ACM Transactions on Networking (TON)
2019 – Present
Senior Associate Editor
2017 – Present
ACM Transactions on Modeling and Performance Evaluation of Computing Systems (ToMPECS)
2017 – Present
Papers209
Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
We study reinforcement learning with linear function approximation where the transition probability and reward functions are linear with respect to a feature mapping . Specifically, we consider the episodic inhomogeneous linear Markov Decision Process (MDP), and propose a novel computation-efficient algorithm, LSVI-UCB, which achieves an regret bound where is the episode length, is the feature dimension, and is the number of steps. LSVI-UCB builds on weighted ridge regression and upper confidence value iteration with a Bernstein-type exploration bonus. Our statistical results are obtained with novel analytical tools, including a new Bernstein self-normalized bound with conservatism on elliptical potentials, and refined analysis of the correction term. This is a minimax optimal algorithm for linear MDPs up to logarithmic factors, which closes the gap between the upper bound of in (Jin et al., 2020) and lower bound of for linear MDPs.
Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that employs an Iterated Conditional Value-at-Risk (CVaR) objective under both linear and general function approximations, enriched by human feedback. These new formulations provide a principled way to guarantee safety in each decision making step throughout the control process. Moreover, integrating human feedback into risk-sensitive RL framework bridges the gap between algorithmic decision-making and human participation, allowing us to also guarantee safety for human-in-the-loop systems. We propose provably sample-efficient algorithms for this Iterated CVaR RL and provide rigorous theoretical analysis. Furthermore, we establish a matching lower bound to corroborate the optimality of our algorithms in a linear context.
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.
Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
In the realm of reinforcement learning (RL), accounting for risk is crucial for making decisions under uncertainty, particularly in applications where safety and reliability are paramount. In this paper, we introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general function approximation. Our framework covers a broad class of risk-sensitive RL, and facilitates analysis of the impact of estimation functions on the effectiveness of RSRL strategies and evaluation of their sample complexity. We design two innovative meta-algorithms: RS-DisRL-M, a model-based strategy for model-based function approximation, and RS-DisRL-V, a model-free approach for general value function approximation. With our novel estimation techniques via Least Squares Regression (LSR) and Maximum Likelihood Estimation (MLE) in distributional RL with augmented Markov Decision Process (MDP), we derive the first dependency of the regret upper bound for RSRL with static LRM, marking a pioneering contribution towards statistically efficient algorithms in this domain.
uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
In this paper, we present a novel algorithm, uniINF, for the Heavy-Tailed Multi-Armed Bandits (HTMAB) problem, demonstrating robustness and adaptability in both stochastic and adversarial environments. Unlike the stochastic MAB setting where loss distributions are stationary with time, our study extends to the adversarial setup, where losses are generated from heavy-tailed distributions that depend on both arms and time. Our novel algorithm `uniINF` enjoys the so-called Best-of-Both-Worlds (BoBW) property, performing optimally in both stochastic and adversarial environments without knowing the exact environment type. Moreover, our algorithm also possesses a Parameter-Free feature, i.e., it operates without the need of knowing the heavy-tail parameters a-priori. To be precise, uniINF ensures nearly-optimal regret in both stochastic and adversarial environments, matching the corresponding lower bounds when is known (up to logarithmic factors). To our knowledge, uniINF is the first parameter-free algorithm to achieve the BoBW property for the heavy-tailed MAB problem. Technically, we develop innovative techniques to achieve BoBW guarantees for Parameter-Free HTMABs, including a refined analysis for the dynamics of log-barrier, an auto-balancing learning rate scheduling scheme, an adaptive skipping-clipping loss tuning technique, and a stopping-time analysis for logarithmic regret.
Finite-Time Analysis of Discrete-Time Stochastic Interpolants
The stochastic interpolant framework offers a powerful approach for constructing generative models based on ordinary differential equations (ODEs) or stochastic differential equations (SDEs) to transform arbitrary data distributions. However, prior analyses of this framework have primarily focused on the continuous-time setting, assuming a perfect solution of the underlying equations. In this work, we present the first discrete-time analysis of the stochastic interpolant framework, where we introduce an innovative discrete-time sampler and derive a finite-time upper bound on its distribution estimation error. Our result provides a novel quantification of how different factors, including the distance between source and target distributions and estimation accuracy, affect the convergence rate and also offers a new principled way to design efficient schedules for convergence acceleration. Finally, numerical experiments are conducted on the discrete-time sampler to corroborate our theoretical findings.
On the Sublinear Regret of Continuous K-Max Bandits
The -Max combinatorial multi-armed bandit problem arises in applications such as recommendation and distributed decision making, where the reward is determined by the maximum outcome among selected arms. When outcomes are continuous and only the maximum value together with the winner's index is observed, this problem introduces unprecedented difficulties including discretization errors, non-deterministic tie-breaking, and severe estimation biases. To overcome these barriers, we introduce DCK-UCB, an efficient algorithm combining adaptive discretization with bias-corrected confidence bounds. We prove that DCK-UCB achieves a regret bound, the first sublinear guarantee in this setting. Numerical experiments show strong performance over baseline methods. Furthermore, for the specific case of exponential distributions under full-bandit feedback, we propose the MLE-Exp algorithm that attains a near-optimal regret bound. This work establishes fundamental theoretical guarantees and provides a powerful algorithmic solution for continuous combinatorial bandits.
Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
Generative Flow Networks (GFlowNets) excel at sampling diverse, high-reward objects. In many practical applications where active reward queries are infeasible, these models must be trained using static offline datasets. Prevailing training methods typically rely on a proxy model to provide reward feedback for online sampled trajectories. However, constructing a reliable proxy is often challenging due to data scarcity or high evaluation costs. While existing proxy-free approaches attempt to address this, they often impose coarse constraints that limit the model's ability to explore effectively. To overcome these limitations, we propose Trajectory-Distilled GFlowNet (TD-GFN), a novel proxy-free training framework. TD-GFN utilizes inverse reinforcement learning (IRL) to extract dense, transition-level edge rewards from offline trajectories, providing rich structural guidance for efficient exploration. Crucially, to ensure robustness, these rewards guide the policy indirectly through DAG pruning and prioritized backward sampling. This design ensures that gradient updates rely exclusively on ground-truth terminal rewards from the dataset, thereby preventing error propagation. Empirical results demonstrate that TD-GFN significantly outperforms a broad range of existing baselines in both convergence speed and sample quality, establishing a more robust and efficient paradigm for offline GFlowNet training.
Offline Diffusion Policy for Multi-User Delay-Constrained Scheduling
Effective multi-user delay-constrained scheduling is crucial in various real-world applications, including embodied AI, instant messaging, live streaming, and data center management, where efficient resource allocation is required among users with diverse delay sensitivities. In these scenarios, schedulers must make real-time decisions to satisfy both delay and resource constraints without prior knowledge of system dynamics, which are often time-varying and challenging to estimate. {Current learning-based methods typically require online interactions with actual systems during the training stage. Therefore, these approaches are often difficult or impractical, as they can significantly degrade system performance and incur substantial service costs.} To address these challenges, we propose a novel offline reinforcement learning-based algorithm, named Scheduling By Offline Learning with Critic Guidance and Diffusion Model (SOCD), to learn efficient scheduling policies purely from pre-collected offline data. SOCD innovatively employs a diffusion policy, complemented by a sampling-free critic network for policy guidance. By integrating the Lagrangian multiplier optimization into the offline reinforcement learning, SOCD efficiently trains high-quality constraint-aware policies exclusively from available datasets, eliminating the need for online interactions with the system. Experimental results demonstrate that SOCD is resilient to various system dynamics, including partially observable and large-scale environments, and delivers superior performance compared to existing methods.
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Despite growing automation, turning a paper into a coherent poster, talk video, and blog piece often remains a labor-intensive last mile. Recent systems increasingly generate multiple dissemination formats, but a practical workflow must also keep the outputs editable in native tools and bound into one navigable deliverable for revision and reuse. We present ResearchStudio-Reel, a native-editable dissemination workspace that binds its three artifacts into one interactive deliverable at the experience level, implemented as five skills executable in Claude Code and Codex: one shared extractor, three editable artifact generators, and one interactive convergence layer. A shared asset bundle feeds a PowerPoint poster and video deck, plus a bilingual Word blog; rather than re-rendering the paper into a fourth format, Paper2Reel converges these already-produced artifacts at the experience level, binding poster regions, video segments, and blog passages into one interactive viewer. Artifact-specific release checks make this delivery contract testable, and Paper2Poster additionally uses a measured-fill loop. On the Paper2Poster benchmark, our Claude Code configuration achieves the best scores among automated systems on all three aesthetic sub-criteria and the best or tied-best scores on two of three information sub-criteria. Under two VLMjudges, it exceeds the authors' posters in average aesthetics (3.56 vs. 3.03) and wins on overall quality on 74 and 95 of the 100 papers under the two judges. The full pipeline additionally packages the native-editable source artifacts and their aligned viewer. Project is available at this https URL
Metrics
Citations per year
Coauthors
