AIConfPaper
← Search

Tuan Anh Le

20 accepted papers

2024

Demonstrating Arena 3.0: Advancing Social Navigation in Collaborative and Highly Dynamic Environments

Linh Kästner, Volodymyir Shcherbyna, Huajian Zeng, Tuan Anh Le, Maximilian Ho-Kyung Schreff, Halid Osmaev +5
RSS 2024poster

Building upon our previous contributions, this paper introduces Arena 3.0, an extension of Arena-Bench, Arena 1.0, and Arena 2.0 focusing on the development, simulation, and benchmarking of social navigation approaches in collaborative environments. We significantly enhance the realism of human beha…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning

Wasu Top Piriyakulkij, Cassidy Langenfeld, Tuan Anh Le, Kevin Ellis
NeurIPS 2024poster

We give a model of how to infer natural language rules by doing experiments. The model integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic inference, interleaving online belief updates with experiment design under information-theoretic criteria. We conduct a human-m…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

Neural Amortized Inference for Nested Multi-Agent Reasoning

Kunal Jha, Tuan Anh Le, Chuanyang Jin, Yen-Ling Kuo, Joshua B. Tenenbaum, Tianmin Shu
AAAI 2024technical

Multi-agent interactions, such as communication, teaching, and bluffing, often rely on higher-order social inference, i.e., understanding how others infer oneself. Such intricate reasoning can be effectively modeled through nested multi-agent reasoning. Nonetheless, the computational complexity esca…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

Robust Inverse Graphics via Probabilistic Inference

Tuan Anh Le, Pavel Sountsov, Matthew Douglas Hoffman, Ben Lee, Brian Patton, Rif A. Saurous
ICML 2024poster

How do we infer a 3D scene from a single image in the presence of corruptions like rain, snow or fog? Straightforward domain randomization relies on knowing the family of corruptions ahead of time. Here, we propose a Bayesian approach---dubbed robust inverse graphics (RIG)---that relies on a strong…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images

Matthew D. Hoffman, Tuan Anh Le, Pavel Sountsov, Christopher Suter, Ben Lee, Vikash K. Mansinghka +1
AISTATS 2023poster

The problem of inferring object shape from a single 2D image is underconstrained. Prior knowledge about what objects are plausible can help, but even given such prior knowledge there may still be uncertainty about the shapes of occluded parts of objects. Recently, conditional neural radiance field (…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2023

Training Chain-of-Thought via Latent-Variable Inference

Du Phan, Matthew Douglas Hoffman, david dohan, Sholto Douglas, Tuan Anh Le, Aaron T Parisi +4
NeurIPS 2023poster

Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a "chain-of-thought" (CoT) prompt. One can also improve LLMs' performance on a specific task by supervised fine-tuning, i.e., by using gradient ascent on some tunab…

Cited by 5Source ↗PDF ↗Scholar ↗
2022

Arena-Bench: A Benchmarking Suite for Obstacle Avoidance Approaches in Highly Dynamic Environments

Linh Kästner, Teham Bhuiyan, Tuan Anh Le, Elias Treis, Johannes Cox, Boris Meinardus +6
RA-L 2022

The ability to autonomously navigate safely, especially within dynamic environments, is paramount for mobile robotics. In recent years, DRL approaches have shown superior performance in dynamic obstacle avoidance. However, these learning-based approaches are often developed in specially designed sim

Cited by 43Source ↗code ↗Scholar ↗
2022

Drawing out of Distribution with Neuro-Symbolic Generative Models

Yichao Liang, Joshua B. Tenenbaum, Tuan Anh Le, Siddharth N
NeurIPS 2022accept

Learning general-purpose representations from perceptual inputs is a hallmark of human intelligence. For example, people can write out numbers or characters, or even draw doodles, by characterizing these tasks as different instantiations of the same generic underlying process---compositional arrange…

Cited by 6Source ↗PDF ↗Scholar ↗
2022

Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface

Tuan Anh Le, Katherine M. Collins, Luke Hewitt, Kevin Ellis, Siddharth N, Samuel Gershman +1
ICLR 2022poster

Modeling complex phenomena typically involves the use of both discrete and continuous variables. Such a setting applies across a wide range of problems, from identifying trends in time-series data to performing effective compositional scene understanding in images. Here, we propose Hybrid Memoised W…

Cited by 5Source ↗PDF ↗Scholar ↗
2021

Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems

Linh Kästner, Teham Buiyan, Lei Jiao, Tuan Anh Le, Xinlin Zhao, Zhengcheng Shen +1
IROS 2021poster

Recently, mobile robots have become important tools in various industries, especially in logistics. Deep reinforcement learning emerged as an alternative planning method to replace overly conservative approaches and promises more efficient and flexible navigation. However, deep reinforcement learnin…

Cited by 47Source ↗code ↗Scholar ↗
2020

Amortized Population Gibbs Samplers with Neural Sufficient Statistics

Hao Wu, Heiko Zimmermann, Eli Sennesh, Tuan Anh Le, Jan-Willem Van De Meent
ICML 2020poster

We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frame structured variational inference as adaptive importance sampling. APG samplers construct high-dimensional proposals by iterating over updates to lower-dimensional blocks of variables. We train each condition…

Cited by 7Source ↗PDF ↗Scholar ↗
2019

Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow

Tuan Anh Le, Adam R. Kosiorek, N. Siddharth, Yee Whye Teh, Frank Wood
UAI 2019poster

Stochastic control-flow models (SCFMs) are a class of generative models that involve branching on choices from discrete random variables. Amortized gradient-based learning of SCFMs is challenging as most approaches targeting discrete variables rely on their continuous relaxations—which can be intrac…

Cited by 54Source ↗PDF ↗Scholar ↗
2018

Deep Variational Reinforcement Learning for POMDPs

Maximilian Igl, Luisa Zintgraf, Tuan Anh Le, Frank Wood, Shimon Whiteson
ICML 2018oral

Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of rewards and incomplete and noisy observati…

Cited by 350Source ↗PDF ↗code ↗Scholar ↗
2018

Tighter Variational Bounds are Not Necessarily Better

Tom Rainforth, Adam Kosiorek, Tuan Anh Le, Chris Maddison, Maximilian Igl, Frank Wood +1
ICML 2018oral

We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter E…

Cited by 246Source ↗PDF ↗Scholar ↗
2016

Bayesian Optimization for Probabilistic Programs

Tom Rainforth, Tuan Anh Le, Jan-Willem van de Meent, Michael A Osborne, Frank Wood
NeurIPS 2016poster

We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables. By using a series of code transformations, the evidence of any probabilistic program, and therefore of any graphical model, can be optimized with respect to an arbitrary su…

Cited by 34Source ↗PDF ↗code ↗Scholar ↗