Author name cluster

Heng Yang

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.

12 papers

2 author rows

JBHI Journal 2026 Journal Article

$\text{P}^\text{2}$RS: A Quantitative Rating Scale for Pain Assessment based on Pulse Wave Characterization

Yue He
Yi Sun
Ke Sun
Wei Bin
Quan Wang
Heng Yang
Xinxin Li

For pain intensity assessment, currently there are mainly 11 rating scales, from primitive Visual Analog Scale (VAS) to elaborate Measure of Intermittent and Constant Osteoarthritis Pain (ICOAP). However, they all depend on a self-report mechanism, making their results so subjective that the consistency, comparability and reference value are barely satisfactory. Inspired by the phenomenon that discomfort may give rise to the throbbing of radial artery, we develop an objective rating scale innovatively, quantifying the severity of pain by the degree of “lateral instability” of an arterial pulse wave. In attempting to monitor this lateral instability, a sort of ultra-small piezoresistive pressure sensor is fabricated in an area of 0. 4 × 0. 4 $\text{mm}^\text{2}$. With 18 of such sensors, we build a flexible tactile sensing dense-array with a pitch of only 0. 65 mm. Overlying the radial artery perpendicularly to the blood flow direction, the dense-array succeeds in observing the cross-section of a pulse wave. The barycenter of the cross-section of each wave cycle is taken as the feature point to represent its lateral shape and drift. The standard deviation of the barycenters' horizontal coordinates is thereby calculated as the pulsatile perceptual rating scale ( $\text{P}^\text{2}$ RS) to reflect the degree of lateral instability, that is, our scale of pain intensity. Among 86 clinical samples, the pain threshold is 0. 11, which is concluded by a binary classification model based on a support vector machine. In terms of its consistency with previous rating scales, the average correlation coefficient reaches 0. 804 among 43 pain samples.

Details DOI

UAI Conference 2025 Conference Paper

Adapting Prediction Sets to Distribution Shifts Without Labels

Kevin Kasa
Zhiyu Zhang
Heng Yang
Graham W. Taylor

Recently there has been a surge of interest to deploy confidence set predictions rather than point predictions in machine learning. Unfortunately, the effectiveness of such prediction sets is frequently impaired by distribution shifts in practice, and the challenge is often compounded by the lack of ground truth labels at test time. Focusing on a standard set-valued prediction framework called conformal prediction (CP), this paper studies how to improve its practical performance using only unlabeled data from the shifted test domain. This is achieved by two new methods called $\texttt{ECP}$ and $\texttt{E{\small A}CP}$, whose main idea is to adjust the score function in CP according to its base model’s own uncertainty evaluation. Through extensive experiments on a number of large-scale datasets and neural network architectures, we show that our methods provide consistent improvement over existing baselines and nearly match the performance of fully supervised methods.

Details

AAAI Conference 2025 Conference Paper

Bridging Sequence-Structure Alignment in RNA Foundation Models

Heng Yang
Renzhi Chen
Ke Li

The alignment between RNA sequences and structures in foundation models (FMs) has yet to be thoroughly investigated. Existing FMs have struggled to establish sequence-structure alignment, hindering the seamless flow of genomic information between RNA sequences and structures. In this study, we introduce OmniGenome, an RNA FM trained to align RNA sequences with respect to secondary structures through structure-contextualized modelling. This alignment enables free and bidirectional mappings between sequences and structures by utilizing a flexible RNA modelling paradigm that supports versatile input and output modalities, i.e., sequence and/or structure as input/output. We implement RNA design and zero-shot secondary structure prediction as case studies to evaluate the Seq2Str and Str2Seq mapping capabilities of OmniGenome. Results on the EternaV2 benchmark show that OmniGenome solved 74% of puzzles, whereas existing FMs solved only up to 3% of the puzzles due to the lack of sequence-structure alignment. We leverage four comprehensive in-silico genome modelling benchmarks to evaluate performance across a diverse set of downstream genome tasks, where the results show that OmniGenome achieves state-of-the-art performance on RNA and DNA benchmarks, even without any training on DNA genomes.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion

Minkyoung Cho
Yulong Cao
Jiachen Sun
Qingzhao Zhang 0001
Marco Pavone 0001
Jeong Joon Park
Heng Yang
Z. Morley Mao

An important paradigm in 3D object detection is the use of multiple modalities to enhance accuracy in both normal and challenging conditions, particularly for long-tail scenarios. To address this, recent studies have explored two directions of adaptive approaches: MoE-based adaptive fusion, which struggles with uncertainties arising from distinct object configurations, and late fusion for output-level adaptive fusion, which relies on separate detection pipelines and limits comprehensive understanding. In this work, we introduce Cocoon, an object- and feature-level uncertainty-aware fusion framework. The key innovation lies in uncertainty quantification for heterogeneous representations, enabling fair comparison across modalities through the introduction of a feature aligner and a learnable surrogate ground truth, termed feature impression. We also define a training objective to ensure that their relationship provides a valid metric for uncertainty quantification. Cocoon consistently outperforms existing static and adaptive methods in both normal and challenging conditions, including those with natural and artificial corruptions. Furthermore, we show the validity and efficacy of our uncertainty metric across diverse datasets.

Details

ICLR Conference 2025 Conference Paper

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models

Ziqi Lu
Heng Yang
Danfei Xu
Boyi Li 0001
Boris Ivanovic
Marco Pavone 0001
Yue Wang 0041

Emerging 3D geometric foundation models, such as DUSt3R, offer a promising approach for in-the-wild 3D vision tasks. However, due to the high-dimensional nature of the problem space and scarcity of high-quality 3D data, these pre-trained models still struggle to generalize to many challenging circumstances, such as limited view overlap or low lighting. To address this, we propose LoRA3D, an efficient self-calibration pipeline to *specialize* the pre-trained models to target scenes using their own multi-view predictions. Taking sparse RGB images as input, we leverage robust optimization techniques to refine multi-view predictions and align them into a global coordinate frame. In particular, we incorporate prediction confidence into the geometric optimization process, automatically re-weighting the confidence to better reflect point estimation accuracy. We use the calibrated confidence to generate high-quality pseudo labels for the calibrating views and fine-tune the models using low-rank adaptation (LoRA) on the pseudo-labeled data. Our method does not require any external priors or manual labels. It completes the self-calibration process on a **single standard GPU within just 5 minutes**. Each low-rank adapter requires only **18MB** of storage. We evaluated our method on **more than 160 scenes** from the Replica, TUM and Waymo Open datasets, achieving up to **88\% performance improvement** on 3D reconstruction, multi-view pose estimation and novel-view rendering. For more details, please visit our project page at https://520xyxyzq.github.io/lora3d/.

Details

ICRA Conference 2025 Conference Paper

Online Aggregation of Trajectory Predictors

Alex Tong
Apoorva Sharma
Sushant Veer
Marco Pavone 0001
Heng Yang

Trajectory prediction, the task of forecasting future agent behavior from past data, is central to safe and efficient autonomous driving. A diverse set of methods (e. g. , rule-based or learned with different architectures and datasets) have been proposed, yet it is often the case that the performance of these methods is sensitive to the deployment environment (e. g. , how well the design rules model the environment, or how accurately the test data match the training data). Building upon the principled theory of online convex optimization but also going beyond convexity and stationarity, we present a lightweight and model-agnostic method to aggregate different trajectory predictors online. We propose treating each individual trajectory predictor as an “expert” and maintaining a probability vector to mix the outputs of different experts. Then, the key technical approach lies in leveraging online data - the true agent behavior to be revealed at the next timestepto form a convex-or-nonconvex, stationary-or-dynamic loss function whose gradient steers the probability vector towards choosing the best mixture of experts. We instantiate this method to aggregate trajectory predictors trained on different cities in the nuScenes dataset and show that it performs just as well, if not better than, any singular model, even when deployed on the out-of-distribution LYFT dataset.

Details

ICML Conference 2024 Conference Paper

Discounted Adaptive Online Learning: Towards Better Regularization

Zhiyu Zhang 0003
David Bombara
Heng Yang

We study online learning in adversarial nonstationary environments. Since the future can be very different from the past, a critical challenge is to gracefully forget the history while new data comes in. To formalize this intuition, we revisit the discounted regret in online convex optimization, and propose an adaptive (i. e. , instance optimal), FTRL-based algorithm that improves the widespread non-adaptive baseline – gradient descent with a constant learning rate. From a practical perspective, this refines the classical idea of regularization in lifelong learning: we show that designing better regularizers can be guided by the principled theory of adaptive online optimization. Complementing this result, we also consider the (Gibbs & Candes, 2021)-style online conformal prediction problem, where the goal is to sequentially predict the uncertainty sets of a black-box machine learning model. We show that the FTRL nature of our algorithm can simplify the conventional gradient-descent-based analysis, leading to instance-dependent performance guarantees.

Details

NeurIPS Conference 2024 Conference Paper

Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning

Aneesh Muppidi
Zhiyu Zhang
Heng Yang

A key challenge in lifelong reinforcement learning (RL) is the loss of plasticity, where previous learning progress hinders an agent's adaptation to new tasks. While regularization and resetting can help, they require precise hyperparameter selection at the outset and environment-dependent adjustments. Building on the principled theory of online convex optimization, we present a parameter-free optimizer for lifelong RL, called TRAC, which requires no tuning or prior knowledge about the distribution shifts. Extensive experiments on Procgen, Atari, and Gym Control environments show that TRAC works surprisingly well—mitigating loss of plasticity and rapidly adapting to challenging distribution shifts—despite the underlying optimization problem being nonconvex and nonstationary.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction

Apoorva Sharma
Sushant Veer
Asher Hancock
Heng Yang
Marco Pavone
Anirudha Majumdar

Inductive Conformal Prediction (ICP) provides a practical and effective approach for equipping deep learning models with uncertainty estimates in the form of set-valued predictions which are guaranteed to contain the ground truth with high probability. Despite the appeal of this coverage guarantee, these sets may not be efficient: the size and contents of the prediction sets are not directly controlled, and instead depend on the underlying model and choice of score function. To remedy this, recent work has proposed learning model and score function parameters using data to directly optimize the efficiency of the ICP prediction sets. While appealing, the generalization theory for such an approach is lacking: direct optimization of empirical efficiency may yield prediction sets that are either no longer efficient on test data, or no longer obtain the required coverage on test data. In this work, we use PAC-Bayes theory to obtain generalization bounds on both the coverage and the efficiency of set-valued predictors which can be directly optimized to maximize efficiency while satisfying a desired test coverage. In contrast to prior work, our framework allows us to utilize the entire calibration dataset to learn the parameters of the model and score function, instead of requiring a separate hold-out set for obtaining test-time coverage guarantees. We leverage these theoretical results to provide a practical algorithm for using calibration data to simultaneously fine-tune the parameters of a model and score function while guaranteeing test-time coverage and efficiency of the resulting prediction sets. We evaluate the approach on regression and classification tasks, and outperform baselines calibrated using a Hoeffding bound-based PAC guarantee on ICP, especially in the low-data regime.

PDF Details

ICML Conference 2023 Conference Paper

Phase-aware Adversarial Defense for Improving Adversarial Robustness

Dawei Zhou 0004
Nannan Wang 0001
Heng Yang
Xinbo Gao 0001
Tongliang Liu

Deep neural networks have been found to be vulnerable to adversarial noise. Recent works show that exploring the impact of adversarial noise on intrinsic components of data can help improve adversarial robustness. However, the pattern closely related to human perception has not been deeply studied. In this paper, inspired by the cognitive science, we investigate the interference of adversarial noise from the perspective of image phase, and find ordinarily-trained models lack enough robustness against phase-level perturbations. Motivated by this, we propose a joint adversarial defense method: a phase-level adversarial training mechanism to enhance the adversarial robustness on the phase pattern; an amplitude-based pre-processing operation to mitigate the adversarial perturbation in the amplitude pattern. Experimental results show that the proposed method can significantly improve the robust accuracy against multiple attacks and even adaptive attacks. In addition, ablation studies demonstrate the effectiveness of our defense strategy.

Details

NeurIPS Conference 2022 Conference Paper

Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization

De Cheng
Yixiong Ning
Nannan Wang
Xinbo Gao
Heng Yang
Yuxuan Du
Bo Han
Tongliang Liu

In label-noise learning, estimating the transition matrix plays an important role in building statistically consistent classifier. Current state-of-the-art consistent estimator for the transition matrix has been developed under the newly proposed sufficiently scattered assumption, through incorporating the minimum volume constraint of the transition matrix T into label-noise learning. To compute the volume of T, it heavily relies on the estimated noisy class posterior. However, the estimation error of the noisy class posterior could usually be large as deep learning methods tend to easily overfit the noisy labels. Then, directly minimizing the volume of such obtained T could lead the transition matrix to be poorly estimated. Therefore, how to reduce the side-effects of the inaccurate noisy class posterior has become the bottleneck of such method. In this paper, we creatively propose to estimate the transition matrix under the forward-backward cycle-consistency regularization, of which we have greatly reduced the dependency of estimating the transition matrix T on the noisy class posterior. We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution. Extensive experimental results consistently justify the effectiveness of the proposed method, on reducing the estimation error of the transition matrix and greatly boosting the classification performance.

PDF Details

NeurIPS Conference 2020 Conference Paper

One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

Heng Yang
Luca Carlone

We propose the first general and practical framework to design certifiable algorithms for robust geometric perception in the presence of a large amount of outliers. We investigate the use of a truncated least squares (TLS) cost function, which is known to be robust to outliers, but leads to hard, nonconvex, and nonsmooth optimization problems. Our first contribution is to show that –for a broad class of geometric perception problems– TLS estimation can be reformulated as an optimization over the ring of polynomials and Lasserre’s hierarchy of convex moment relaxations is empirically tight at the minimum relaxation order (i. e. , certifiably obtains the global minimum of the nonconvex TLS problem). Our second contribution is to exploit the structural sparsity of the objective and constraint polynomials and leverage basis reduction to significantly reduce the size of the semidefinite program (SDP) resulting from the moment relaxation, without compromising its tightness. Our third contribution is to develop scalable dual optimality certifiers from the lens of sums-of-squares (SOS) relaxation, that can compute the suboptimality gap and possibly certify global optimality of any candidate solution (e. g. , returned by fast heuristics such as RANSAC or graduated non-convexity). Our dual certifiers leverage Douglas-Rachford Splitting to solve a convex feasibility SDP. Numerical experiments across different perception problems, including single rotation averaging, shape alignment, 3D point cloud and mesh registration, and high-integrity satellite pose estimation, demonstrate the tightness of our relaxations, the correctness of the certification, and the scalability of the proposed dual certifiers to large problems, beyond the reach of current SDP solvers.

PDF Details