Author name cluster

Da Huang

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.

7 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making

Shanshan Li
Da Huang
Yu He
Yanwei Fu
Yu-Gang Jiang
Xiangyang Xue

In daily life, people often move through spaces to find objects that meet their needs, posing a key challenge in embodied AI. Traditional Demand-Driven Navigation (DDN) handles one need at a time but does not reflect the complexity of real-world tasks involving multiple needs and personal choices. To bridge this gap, we introduce Task-Preferenced Multi-Demand-Driven Navigation (TP-MDDN), a new benchmark for long-horizon navigation involving multiple sub-demands with explicit task preferences. To solve TP-MDDN, we propose AWMSystem, an autonomous decision-making system composed of three key modules: BreakLLM (instruction decomposition), LocateLLM (goal selection), and StatusMLLM (task monitoring). For spatial memory, we design MASMap, which combines 3D point cloud accumulation with 2D semantic mapping for accurate and efficient environmental understanding. Our Dual-Tempo action generation framework integrates zero-shot planning with policy-based fine control, and is further supported by an Adaptive Error Corrector that handles failure cases in real time. Experiments demonstrate that our approach outperforms state-of-the-art baselines in both perception accuracy and navigation robustness.

PDF Details

NeurIPS Conference 2024 Conference Paper

Long-form factuality in large language models

Jerry Wei
Chengrun Yang
Xinying Song
Yifeng Lu
Nathan Hu
Jie Huang
Dustin Tran
Daiyi Peng

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model’s long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user’s preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators—on a set of∼16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at https: //github. com/google-deepmind/long-form-factuality.

PDF Details DOI

ICML Conference 2023 Conference Paper

Brainformers: Trading Simplicity for Efficiency

Yanqi Zhou
Nan Du 0002
Yanping Huang
Daiyi Peng
Chang Lan
Da Huang
Siamak Shakeri
David R. So

Transformers are central to recent successes in natural language processing and computer vision. Transformers have a mostly uniform backbone where layers alternate between feed-forward and self-attention in order to build a deep network. Here we investigate this design choice and find that more complex blocks that have different permutations of layer primitives can be more efficient. Using this insight, we develop a complex block, named Brainformer, that consists of a diverse sets of layers such as sparsely gated feed-forward layers, dense feed-forward layers, attention layers, and various forms of layer normalization and activation functions. Brainformer consistently outperforms the state-of-the-art dense and sparse Transformers, in terms of both quality and efficiency. A Brainformer model with 8 billion activated parameters per token demonstrates 2x faster training convergence and 5x faster step time compared to its GLaM counterpart. In downstream task evaluation, Brainformer also demonstrates a 3% higher SuperGLUE score with fine-tuning compared to GLaM with a similar number of activated parameters. Finally, Brainformer largely outperforms a Primer dense model derived with NAS with similar computation per token on fewshot evaluations.

Details

IROS Conference 2023 Conference Paper

Evolving Physical Instinct for Morphology and Control Co-Adaption

Xinglin Chen
Da Huang
Minglong Li
Yishuai Cai
Zhuoer Wen
Zhongxuan Cai
Wenjing Yang 0002

The capability of a robot to perform tasks depends not only on precise motion control, but also on a well-suited body morphology. Adapting both morphology and control of robots to improve their task performance has been a widely studied and long-standing issue. While the bio-inspired bi-level optimization framework has gained popularity in recent years, it suffers from high computation complexity due to the time-consuming and inefficient learning process for each morphology. In fact, in nature, besides the adaptive morphology and the intelligent brain, animals also possess an important gift, which is physical instinct. These instincts allow animals to respond quickly to their surroundings in the neonatal period, facilitating skills acquisition. Inspired by this, we propose an evolvable instinct controller to enhance the morphology-control co-adaption. The instinct controller suggests rough motion inclinations, which require minimal domain knowledge and entail less sophisticated design. Its purpose is to assist the main controller in learning fine-grained and robust control efficiently. We implemented this idea in the context of legged locomotion and designed the instinct controller using phase-based FSMs. We propose the instinct-based co-adaption algorithm and construct GPU parallel simulation experiments on different morphology prototypes. The results indicate that combining the co-adaption process with instinct evolution leads to the development of superior morphologies and robust controllers compared with the conventional co-adaption approach, with minimal additional time cost.

Details

ICRA Conference 2023 Conference Paper

Memory-based Exploration-value Evaluation Model for Visual Navigation

Yongquan Feng
Liyang Xu
Minglong Li
Ruochun Jin
Da Huang
Shaowu Yang
Wenjing Yang 0002

We propose a hierarchical visual navigation solution, called Memory-based Exploration-value Evaluation Model (MEEM), to improve the agent's navigation performance. MEEM employs a hierarchical policy to tackle the challenge of sparse rewards, holds an episodic memory to store the historical information of the agent, and applies an Exploration-value Evaluation Model to calculate an exploration-value for action planning at each location in the observable area. We experimentally verify MEEM by navigation performance comparison on two datasets including the grid-map dataset and the 3D scenes Gibson dataset, where our approach achieves state-of-the-art performance on both. Specifically, the overall success rate of MEEM is 95% on the grid-map dataset while the best competitor reaches 68% only. As for the Gibson dataset, the success rate of ours and the best competitor SemExp are 69. 8% and 54. 4%, respectively. Ablation analysis on the tile-map dataset indicates that all three components of MEEM have positive effects.

Details

NeurIPS Conference 2023 Conference Paper

Symbolic Discovery of Optimization Algorithms

Xiangning Chen
Chen Liang
Da Huang
Esteban Real
Kaiyuan Wang
Hieu Pham
Xuanyi Dong
Thang Luong

We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program space. To bridge the large generalization gap between proxy and target tasks, we also introduce program selection and simplification strategies. Our method discovers a simple and effective optimization algorithm, $\textbf{Lion}$ ($\textit{Evo$\textbf{L}$ved S$\textbf{i}$gn M$\textbf{o}$me$\textbf{n}$tum}$). It is more memory-efficient than Adam as it only keeps track of the momentum. Different from adaptive optimizers, its update has the same magnitude for each parameter calculated through the sign operation. We compare Lion with widely used optimizers, such as Adam and Adafactor, for training a variety of models on different tasks. On image classification, Lion boosts the accuracy of ViT by up to 2\% on ImageNet and saves up to 5x the pre-training compute on JFT. On vision-language contrastive learning, we achieve 88. 3\% $\textit{zero-shot}$ and 91. 1\% $\textit{fine-tuning}$ accuracy on ImageNet, surpassing the previous best results by 2\% and 0. 1\%, respectively. On diffusion models, Lion outperforms Adam by achieving a better FID score and reducing the training compute by up to 2. 3x. For autoregressive, masked language modeling, and fine-tuning, Lion exhibits a similar or better performance compared to Adam. Our analysis of Lion reveals that its performance gain grows with the training batch size. It also requires a smaller learning rate than Adam due to the larger norm of the update produced by the sign function. Additionally, we examine the limitations of Lion and identify scenarios where its improvements are small or not statistically significant.

PDF Details

NeurIPS Conference 2022 Conference Paper

TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets

Chengrun Yang
Gabriel Bender
Hanxiao Liu
Pieter-Jan Kindermans
Madeleine Udell
Yifeng Lu
Quoc V Le
Da Huang

The best neural architecture for a given machine learning problem depends on many factors: not only the complexity and structure of the dataset, but also on resource constraints including latency, compute, energy consumption, etc. Neural architecture search (NAS) for tabular datasets is an important but under-explored problem. Previous NAS algorithms designed for image search spaces incorporate resource constraints directly into the reinforcement learning (RL) rewards. However, for NAS on tabular datasets, this protocol often discovers suboptimal architectures. This paper develops TabNAS, a new and more effective approach to handle resource constraints in tabular NAS using an RL controller motivated by the idea of rejection sampling. TabNAS immediately discards any architecture that violates the resource constraints without training or learning from that architecture. TabNAS uses a Monte-Carlo-based correction to the RL policy gradient update to account for this extra filtering step. Results on several tabular datasets demonstrate the superiority of TabNAS over previous reward-shaping methods: it finds better models that obey the constraints.

PDF Details