Author name cluster

Susmit Jha

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.

20 papers

2 author rows

AAAI Conference 2026 Conference Paper

On the Dataless Training of Neural Networks

Alvaro Velasquez
Susmit Jha
Ismail R. Alkhouri

This paper surveys studies on the use of neural networks for optimization in the training-data-free setting. Specifically, we examine the dataless application of neural network architectures in optimization by re-parameterizing problems using fully connected (or MLP), convolutional, graph, and quadratic neural networks. Although MLPs have been used to solve linear programs a few decades ago, this approach has recently gained increasing attention due to its promising results across diverse applications, including those based on combinatorial optimization, inverse problems, and partial differential equations. The motivation for this setting stems from two key (possibly over-lapping) factors: (i) data-driven learning approaches are still underdeveloped and have yet to demonstrate strong results, as seen in combinatorial optimization, and (ii) the availability of training data is inherently limited, such as in medical image reconstruction and other scientific applications. In this paper, we define the dataless setting and categorize it into two variants based on how a problem instance—defined by a single datum—is encoded onto the neural network: (i) architecture-agnostic methods and (ii) architecture-specific methods. Additionally, we discuss similarities and clarify distinctions between the dataless neural network (dNN) settings and related concepts such as zero-shot learning, one-shot learning, lifting in optimization, and over-parameterization.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Privacy Preserving In-Context-Learning Framework for Large Language Models

Bishnu Bhusal
Manoj Acharya
Ramneet Kaur
Colin Samplawski
Anirban Roy
Adam D. Cobb
Rohit Chadha
Susmit Jha

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information leakage, where adversaries can extract sensitive information embedded in the prompts. In this work, we introduce a novel private prediction framework for generating high-quality synthetic text with strong privacy guarantees. Our approach leverages the Differential Privacy (DP) framework to ensure worst-case theoretical bounds on information leakage without requiring any fine-tuning of the underlying models. The proposed method performs inference on private records and aggregates the resulting per-token output distributions. This enables the generation of longer and coherent synthetic text while maintaining privacy guarantees. Additionally, we propose a simple blending operation that combines private and public inference to further enhance utility. Empirical evaluations demonstrate that our approach outperforms previous state-of-the-art methods on in-context-learning (ICL) tasks, making it a promising direction for privacy-preserving text generation while maintaining high utility.

PDF Details DOI

IS Journal 2026 Journal Article

Relevance Structures are a Necessary Prerequisite for Artificial Metacognition

Alexander M. Berenbeim
Ramneet Kaur
Adam Cobb
Brian Matejek
Anirban Roy
Susmit Jha
Nathaniel D. Bastian

AI-enabled systems deployed in dynamic, open-world, safety- and mission-critical environments often lack mechanisms for reliable self-monitoring and self-regulation under shift and perturbation. Artificial Metacognition (AM) addresses this by enabling systems to assess and adapt their own inference and learning processes. We show that relevance structures, which are order-theoretic substrates for comparing generalization and specialization and for quantifying under-coverage versus overreach, are structurally unavoidable for computable self-regulation. In turn, relevance structures provide an operational control theory for metacognitive tasks. We introduce exploratory, parsimonious, and balanced relevance scores and embed them into version-space algebra to regulate hypothesis search and inductive strategy selection. The resulting framework yields competence-aware learning systems that can both correct and explain their behavior by explicitly balancing exploration and parsimony. We illustrate relevance structures and their application with a medical visual question answering study on the SLAKE dataset.

Details DOI

TMLR Journal 2025 Journal Article

SAFE-NID: Self-Attention with Normalizing-Flow Encodings for Network Intrusion Detection

Brian Matejek
Ashish Gehani
Nathaniel D. Bastian
Daniel J Clouse
Bradford J Kline
Susmit Jha

Machine learning models are increasingly adopted to monitor network traffic and detect intrusions. In this work, we introduce SAFE-NID, a novel machine learning approach for real-time packet-level traffic monitoring and intrusion detection that includes a safeguard to detect zero day attacks as out-of-distribution inputs. Unlike traditional models, which falter against zero-day attacks and concept drift, SAFE-NID leverages a lightweight encoder-only transformer architecture combined with a novel normalizing flows-based safeguard. This safeguard not only quantifies uncertainty but also identifies out-of-distribution (OOD) inputs, enabling robust performance in dynamic threat landscapes. Our generative model learns class-conditional representations of the internal features of the deep neural network. We demonstrate the effectiveness of our approach by converting publicly available network flow-level intrusion datasets into packet-level ones. We release the labeled packet-level versions of these datasets with over 50 million packets each and describe the challenges in creating these datasets. We withhold from the training data certain attack categories to simulate zero-day attacks. Existing deep learning models, which achieve an accuracy of over 99% when detecting known attacks, only correctly classify 1% of the novel attacks. Our proposed transformer architecture with normalizing flows model safeguard achieves an area under the receiver operating characteristic curve of over 0.97 in detecting these novel inputs, outperforming existing combinations of neural architectures and model safeguards. The additional latency in processing each packet by the safeguard is a small fraction of the overall inference task. This dramatic improvement in detecting zero-day attacks and distribution shifts emphasizes SAFE-NID’s novelty and utility as a reliable and efficient safety monitoring tool for real-world network intrusion detection.

PDF Details

UAI Conference 2025 Conference Paper

Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference

Colin Samplawski
Adam D. Cobb
Manoj Acharya
Ramneet Kaur
Susmit Jha

Despite their widespread use, large language models (LLMs) are known to hallucinate incorrect information and be poorly calibrated. This makes the uncertainty quantification of these models of critical importance, especially in high-stakes domains, such as autonomy and healthcare. Prior work has made Bayesian deep learning-based approaches to this problem more tractable by performing inference over the low-rank adaptation (LoRA) parameters of a fine-tuned model. While effective, these approaches struggle to scale to larger LLMs due to requiring further additional parameters compared to LoRA. In this work we present $\textbf{Scala}$ble $\textbf{B}$ayesian $\textbf{L}$ow-Rank Adaptation via Stochastic Variational Subspace Inference (ScalaBL). We perform Bayesian inference in an $r$-dimensional subspace, for LoRA rank $r$. By repurposing the LoRA parameters as projection matrices, we are able to map samples from this subspace into the full weight space of the LLM. This allows us to learn all the parameters of our approach using stochastic variational inference. Despite the low dimensionality of our subspace, we are able to achieve competitive performance with state-of-the-art approaches while only requiring ${\sim}1000$ additional parameters. Furthermore, it allows us to scale up to the largest Bayesian LLM to date, with four times as a many base parameters as prior work.

Details

NeurIPS Conference 2025 Conference Paper

SpikingVTG: A Spiking Detection Transformer for Video Temporal Grounding

Malyaban Bal
Brian Matejek
Susmit Jha
Adam Cobb

Video Temporal Grounding (VTG) aims to retrieve precise temporal segments in a video conditioned on natural language queries. Unlike conventional neural frameworks that rely heavily on computationally expensive dense matrix multiplications, Spiking Neural Networks (SNNs)—previously underexplored in this domain—offer a unique opportunity to tackle VTG tasks through bio-plausible spike-based communication and an event-driven accumulation-based computational paradigm. We introduce SpikingVTG, a multi-modal spiking detection transformer, designed to harness the computational simplicity and sparsity of SNNs for VTG tasks. Leveraging the temporal dynamics of SNNs, our model introduces a Saliency Feedback Gating (SFG) mechanism that assigns dynamic saliency scores to video clips and applies multiplicative gating to highlight relevant clips while suppressing less informative ones. SFG enhances performance and reduces computational overhead by minimizing neural activity. We analyze the layer-wise convergence dynamics of SFG-enabled model and apply implicit differentiation at equilibrium to enable efficient, BPTT-free training. To improve generalization and maximize performance, we enable knowledge transfer by optimizing a Cos-L2 representation matching loss that aligns the layer-wise representation and attention maps of a non-spiking teacher with those of our student SpikingVTG. Additionally, we present Normalization-Free (NF)-SpikingVTG, which eliminates non-local operations like softmax and layer normalization, and an extremely quantized 1-bit (NF)-SpikingVTG variant for potential deployment on edge devices. Our models achieve competitive results on QVHighlights, Charades-STA, TACoS, and YouTube Highlights, establishing a strong baseline for multi-modal spiking VTG solutions.

PDF Details

AAAI Conference 2024 Conference Paper

Direct Amortized Likelihood Ratio Estimation

Adam D. Cobb
Brian Matejek
Daniel Elenius
Anirban Roy
Susmit Jha

We introduce a new amortized likelihood ratio estimator for likelihood-free simulation-based inference (SBI). Our estimator is simple to train and estimates the likelihood ratio using a single forward pass of the neural estimator. Our approach directly computes the likelihood ratio between two competing parameter sets which is different from the previous approach of comparing two neural network output values. We refer to our model as the direct neural ratio estimator (DNRE). As part of introducing the DNRE, we derive a corresponding Monte Carlo estimate of the posterior. We benchmark our new ratio estimator and compare to previous ratio estimators in the literature. We show that our new ratio estimator often outperforms these previous approaches. As a further contribution, we introduce a new derivative estimator for likelihood ratio estimators that enables us to compare likelihood-free Hamiltonian Monte Carlo (HMC) with random-walk Metropolis-Hastings (MH). We show that HMC is equally competitive, which has not been previously shown. Finally, we include a novel real-world application of SBI by using our neural ratio estimator to design a quadcopter. Code is available at https://github.com/SRI-CSL/dnre.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs

Adam Cobb
Anirban Roy
Daniel Elenius
Frederick Heim
Brian Swenson
Sydney Whittington
James Walker
Theodore Bapty

We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representation. The evaluation of these designs requires the use of scientific analytical and simulation models ranging from computer-aided design tools for structural and manufacturing analysis, computational fluid dynamics tools for drag and lift computation, battery models for energy estimation, and simulation models for flight control and dynamics. AircraftVerse contains $27{, }714$ diverse air vehicle designs - the largest corpus of designs with this level of complexity. Each design comprises the following artifacts: a symbolic design tree describing topology, propulsion subsystem, battery subsystem, and other design details; a STandard for the Exchange of Product (STEP) model data; a 3D CAD design using a stereolithography (STL) file format; a 3D point cloud for the shape of the design; and evaluation results from high fidelity state-of-the-art physics models that characterize performance metrics such as maximum flight distance and hover-time. We also present baseline surrogate models that use different modalities of design representation to predict design performance metrics, which we provide as part of our dataset release. Finally, we discuss the potential impact of this dataset on the use of learning in aircraft design, and more generally, in the emerging field of deep learning for scientific design. AircraftVerse is accompanied by a datasheet as suggested in the recent literature, and it is released under Creative Commons Attribution-ShareAlike (CC BY-SA) license. The dataset with baseline models are hosted at http: //doi. org/10. 5281/zenodo. 6525446, code at https: //github. com/SRI-CSL/AircraftVerse, and the dataset description at https: //uavdesignverse. onrender. com/.

PDF Details

JMLR Journal 2023 Journal Article

Principled Out-of-Distribution Detection via Multiple Testing

Akshayaa Magesh
Venugopal V. Veeravalli
Anirban Roy
Susmit Jha

We study the problem of out-of-distribution (OOD) detection, that is, detecting whether a machine learning (ML) model's output can be trusted at inference time. While a number of tests for OOD detection have been proposed in prior work, a formal framework for studying this problem is lacking. We propose a definition for the notion of OOD that includes both the input distribution and the ML model, which provides insights for the construction of powerful tests for OOD detection. We also propose a multiple hypothesis testing inspired procedure to systematically combine any number of different statistics from the ML model using conformal p-values. We further provide strong guarantees on the probability of incorrectly classifying an in-distribution sample as OOD. In our experiments, we find that threshold-based tests proposed in prior work perform well in specific settings, but not uniformly well across different OOD instances. In contrast, our proposed method that combines multiple statistics performs uniformly well across different datasets and neural networks architectures. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

IJCAI Conference 2022 Conference Paper

Detecting Out-Of-Context Objects Using Graph Contextual Reasoning Network

Manoj Acharya
Anirban Roy
Kaushik Koneripalli
Susmit Jha
Christopher Kanan
Ajay Divakaran

This paper presents an approach for detecting out-of-context (OOC) objects in images. Given an image with a set of objects, our goal is to determine if an object is inconsistent with the contextual relations and detect the OOC object with a bounding box. In this work, we consider common contextual relations such as co-occurrence relations, the relative size of an object with respect to other objects, and the position of the object in the scene. We posit that contextual cues are useful to determine object labels for in-context objects and inconsistent context cues are detrimental to determining object labels for out-of-context objects. To realize this hypothesis, we propose a graph contextual reasoning network (GCRN) to detect OOC objects. GCRN consists of two separate graphs to predict object labels based on the contextual cues in the image: 1) a representation graph to learn object features based on the neighboring objects and 2) a context graph to explicitly capture contextual cues from the neighboring objects. GCRN explicitly captures the contextual cues to improve the detection of in-context objects and identify objects that violate contextual relations. In order to evaluate our approach, we create a large-scale dataset by adding OOC object instances to the COCO images. We also evaluate on recent OCD benchmark. Our results show that GCRN outperforms competitive baselines in detecting OOC objects and correctly detecting in-context objects. Code and data: https: //nusci. csl. sri. com/project/trinity-ooc

PDF Details DOI

IJCAI Conference 2022 Conference Paper

ExplainIt! : A Tool for Computing Robust Attributions of DNNs

Sumit Jha
Alvaro Velasquez
Rickard Ewetz
Laura Pullum
Susmit Jha

Responsible integration of deep neural networks into the design of trustworthy systems requires the ability to explain decisions made by these models. Explainability and transparency are critical for system analysis, certification, and human-machine teaming. We have recently demonstrated that neural stochastic differential equations (SDEs) present an explanation-friendly DNN architecture. In this paper, we present ExplainIt, an online tool for explaining AI decisions that uses neural SDEs to create visually sharper and more robust attributions than traditional residual neural networks. Our tool shows that the injection of noise in every layer of a residual network often leads to less noisy and less fragile integrated gradient attributions. The discrete neural stochastic differential equation model is trained on the ImageNet data set with a million images, and the demonstration produces robust attributions on images in the ImageNet validation library and on a variety of images in the wild. Our online tool is hosted publicly for educational purposes.

PDF Details DOI

AAAI Conference 2022 Conference Paper

iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection

Ramneet Kaur
Susmit Jha
Anirban Roy
Sangdon Park
Edgar Dobriban
Oleg Sokolsky
Insup Lee

Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence on inputs outside their training distribution. The deployment of DNNs in safety-critical domains requires detection of out-of-distribution (OOD) data so that DNNs can abstain from making predictions on those. A number of methods have been recently developed for OOD detection, but there is still room for improvement. We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection. It relies on a novel base non-conformity measure and a new aggregation method, used in the inductive conformal anomaly detection framework, thereby guaranteeing a bounded false detection rate. We demonstrate the efficacy of iDECODe by experiments on image and audio datasets, obtaining state-of-the-art results. We also show that iDECODe can detect adversarial examples. Code, pre-trained models, and data are available at https: //github. com/ramneetk/iDECODe.

PDF Details

ICML Conference 2022 Conference Paper

Principal Component Flows

Edmond Cunningham
Adam D. Cobb
Susmit Jha

Normalizing flows map an independent set of latent variables to their samples using a bijective transformation. Despite the exact correspondence between samples and latent variables, their high level relationship is not well understood. In this paper we characterize the geometric structure of flows using principal manifolds and understand the relationship between latent variables and samples using contours. We introduce a novel class of normalizing flows, called principal component flows (PCF), whose contours are its principal manifolds, and a variant for injective flows (iPCF) that is more efficient to train than regular injective flows. PCFs can be constructed using any flow architecture, are trained with a regularized maximum likelihood objective and can perform density estimation on all of their principal manifolds. In our experiments we show that PCFs and iPCFs are able to learn the principal manifolds over a variety of datasets. Additionally, we show that PCFs can perform density estimation on data that lie on a manifold with variable dimensionality, which is not possible with existing normalizing flows.

Details

AAAI Conference 2022 Conference Paper

Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations

Sumit Kumar Jha
Rickard Ewetz
Alvaro Velasquez
Arvind Ramanathan
Susmit Jha

Neural SDEs with Brownian motion as noise lead to smoother attributions than traditional ResNets. Various attribution methods such as saliency maps, integrated gradients, DeepSHAP and DeepLIFT have been shown to be more robust for neural SDEs than for ResNets using the recently proposed sensitivity metric. In this paper, we show that neural SDEs with adaptive attribution-driven noise lead to even more robust attributions and smaller sensitivity metrics than traditional neural SDEs with Brownian motion as noise. In particular, attribution-driven shaping of noise leads to 6. 7%, 6. 9% and 19. 4% smaller sensitivity metric for integrated gradients computed on three discrete approximations of neural SDEs with standard Brownian motion noise: stochastic ResNet-50, WideResNet-101 and ResNeXt-101 models respectively. The neural SDE model with adaptive attribution-driven noise leads to 25. 7% and 4. 8% improvement in the SIC metric over traditional ResNets and Neural SDEs with Brownian motion as noise. To the best of our knowledge, we are the first to propose the use of attributions for shaping the noise injected in neural SDEs, and demonstrate that this process leads to more robust attributions than traditional neural SDEs with standard Brownian motion as noise.

PDF Details

ICLR Conference 2022 Conference Paper

Trigger Hunting with a Topological Prior for Trojan Detection

Xiaoling Hu 0002
Xiao Lin
Michael Cogswell
Yi Yao
Susmit Jha
Chao Chen 0012

Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the problem of Trojan detection, namely, identifying Trojaned models – models trained with poisoned data. One popular approach is reverse engineering, i.e., recovering the triggers on a clean image by manipulating the model’s prediction. One major challenge of reverse engineering approach is the enormous search space of triggers. To this end, we propose innovative priors such as diversity and topological simplicity to not only increase the chances of finding the appropriate triggers but also improve the quality of the found triggers. Moreover, by encouraging a diverse set of trigger candidates, our method can perform effectively in cases with unknown target labels. We demonstrate that these priors can significantly improve the quality of the recovered triggers, resulting in substantially improved Trojan detection accuracy as validated on both synthetic and publicly available TrojAI benchmarks.

Details

IJCAI Conference 2021 Conference Paper

On Smoother Attributions using Neural Stochastic Differential Equations

Sumit Jha
Rickard Ewetz
Alvaro Velasquez
Susmit Jha

Several methods have recently been developed for computing attributions of a neural network's prediction over the input features. However, these existing approaches for computing attributions are noisy and not robust to small perturbations of the input. This paper uses the recently identified connection between dynamical systems and residual neural networks to show that the attributions computed over neural stochastic differential equations (SDEs) are less noisy, visually sharper, and quantitatively more robust. Using dynamical systems theory, we theoretically analyze the robustness of these attributions. We also experimentally demonstrate the efficacy of our approach in providing smoother, visually sharper and quantitatively robust attributions by computing attributions for ImageNet images using ResNet-50, WideResNet-101 models and ResNeXt-101 models.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Estimating the Density of States of Boolean Satisfiability Problems on Classical and Quantum Computing Platforms

Tuhin Sahai
Anurag Mishra
Jose Miguel Pasini
Susmit Jha

Given a Boolean formula φ(x) in conjunctive normal form (CNF), the density of states counts the number of variable assignments that violate exactly e clauses, for all values of e. Thus, the density of states is a histogram of the number of unsatisﬁed clauses over all possible assignments. This computation generalizes both maximum-satisﬁability (MAX- SAT) and model counting problems and not only provides insight into the entire solution space, but also yields a measure for the hardness of the problem instance. Consequently, in real-world scenarios, this problem is typically infeasible even when using state-of-the-art algorithms. While ﬁnding an exact answer to this problem is a computationally intensive task, we propose a novel approach for estimating density of states based on the concentration of measure inequalities. The methodology results in a quadratic unconstrained binary optimization (QUBO), which is particularly amenable to quantum annealing-based solutions. We present the overall approach and compare results from the D-Wave quantum annealer against the best-known classical algorithms such as the Hamze-de Freitas-Selby (HFS) algorithm and satisﬁability modulo theory (SMT) solvers.

PDF Details

ICLR Conference 2020 Conference Paper

On the Need for Topology-Aware Generative Models for Manifold-Based Defenses

Uyeong Jang
Susmit Jha
Somesh Jha

ML algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. However, recently researchers have demonstrated that ML algorithms, especially DNNs, are vulnerable to adversarial examples (slightly perturbed samples that cause mis-classification). Existence of adversarial examples has hindered deployment of ML algorithms in safety-critical sectors, such as security. Several defenses for adversarial examples exist in the literature. One of the important classes of defenses are manifold-based defenses, where a sample is "pulled back" into the data manifold before classifying. These defenses rely on the manifold assumption (data lie in a manifold of lower dimension than the input space). These defenses use a generative model to approximate the input distribution. This paper asks the following question: do the generative models used in manifold-based defenses need to be topology-aware? Our paper suggests the answer is yes. We provide theoretical and empirical evidence to support our claim.

Details

NeurIPS Conference 2019 Conference Paper

Attribution-Based Confidence Metric For Deep Neural Networks

Susmit Jha
Sunny Raj
Steven Fernandes
Sumit Jha
Somesh Jha
Brian Jalaian
Gunjan Verma
Ananthram Swami

We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training distribution and are, hence, susceptible to adversarial attacks. This fragility is compounded by a lack of effectively computable measures of model confidence that correlate well with the accuracy of DNNs. These factors have impeded the adoption of DNNs in high-assurance systems. The proposed ABC metric addresses these challenges. It does not require access to the training data, the use of ensembles, or the need to train a calibration model on a held-out validation set. Hence, the new metric is usable even when only a trained model is available for inference. We mathematically motivate the proposed metric and evaluate its effectiveness with two sets of experiments. First, we study the change in accuracy and the associated confidence over out-of-distribution inputs. Second, we consider several digital and physically realizable attacks such as FGSM, CW, DeepFool, PGD, and adversarial patch generation methods. The ABC metric is low on out-of-distribution data and adversarial examples, where the accuracy of the model is also low. These experiments demonstrate the effectiveness of the ABC metric to make DNNs more trustworthy and resilient.

PDF Details

NeurIPS Conference 2018 Conference Paper

Learning Task Specifications from Demonstrations

Marcell Vazquez-Chanlatte
Susmit Jha
Ashish Tiwari
Mark Ho
Sanjit Seshia

Real-world applications often naturally decompose into several sub-tasks. In many settings (e. g. , robotics) demonstrations provide a natural way to specify the sub-tasks. However, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the sub-tasks can be safely recombined or limit the types of composition available. Motivated by this deficit, we consider the problem of inferring Boolean non-Markovian rewards (also known as logical trace properties or specifications) from demonstrations provided by an agent operating in an uncertain, stochastic environment. Crucially, specifications admit well-defined composition rules that are typically easy to interpret. In this paper, we formulate the specification inference task as a maximum a posteriori (MAP) probability inference problem, apply the principle of maximum entropy to derive an analytic demonstration likelihood model and give an efficient approach to search for the most likely specification in a large candidate pool of specifications. In our experiments, we demonstrate how learning specifications can help avoid common problems that often arise due to ad-hoc reward composition.

PDF Details