Kevin Zhang

Yifan Bao, Xinyu Xi, Xinyu Liu et al.

Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation protocol, and refinement strategy for a task. AutoML systems automate parts of this process, but typically search within predefined pipeline, model, and hyperparameter spaces. LLM-based agents offer greater flexibility through retrieval, code generation, and execution feedback, yet their modelling decisions are often unstructured, difficult to verify, and hard to reuse. We introduce \textsc{MOSAIC} (Modular Orchestration for Structured Agentic Intelligence and Composition), a structured agentic framework for memory-grounded model selection and workflow construction. Given a task and dataset, \textsc{MOSAIC} builds a semantic task profile, retrieves prior cases and source-code modules, and constructs a blueprint: an intermediate representation specifying selected modelling components, composition, interface constraints, and execution requirements. This blueprint turns model selection into a staged, context-grounded search and grounds LLM-based code generation in retrieved evidence rather than unconstrained synthesis. Candidate models are validated by execution and refined using diagnostic feedback, training traces, task metrics, and a failure-aware reinforcement learning policy. We instantiate \textsc{MOSAIC} on financial time-series forecasting and generation, where models must satisfy predictive accuracy, distributional fidelity, execution reliability, and downstream financial criteria such as risk and tail behaviour. Experiments against AutoML and agentic baselines show that \textsc{MOSAIC} improves task performance, execution success, and decision traceability, demonstrating the value of treating automated data science as structured, reusable, and execution-grounded model selection.

Anthony Chen, Kevin Zhang, Renrui Zhang et al.

Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities in multi-modality settings. In this work, we focus on point cloud and RGB image data, two modalities that are often presented together in the real world, and explore their meaningful interactions. To improve upon the cross-modal synergy in existing works, we propose PiMAE, a self-supervised pre-training framework that promotes 3D and 2D interaction through three aspects. Specifically, we first notice the importance of masking strategies between the two sources and utilize a projection module to complementarily align the mask and visible tokens of the two modalities. Then, we utilize a well-crafted two-branch MAE pipeline with a novel shared decoder to promote cross-modality interaction in the mask tokens. Finally, we design a unique cross-modal reconstruction module to enhance representation learning for both modalities. Through extensive experiments performed on large-scale RGB-D scene understanding benchmarks (SUN RGB-D and ScannetV2), we discover it is nontrivial to interactively learn point-image features, where we greatly improve multiple 3D detectors, 2D detectors, and few-shot classifiers by 2.9%, 6.7%, and 2.4%, respectively. Code is available at https://github.com/BLVLab/PiMAE.

Gabriel Loaiza-Ganem, Kevin Zhang, Wei Cui et al.

Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machine learning through formal guarantees. However, recent breakthroughs in artificial intelligence (AI) have been driven by unsupervised generative models, such as large language models (LLMs) and image generators, which are not directly compatible with CP or CRC. In this work we introduce conformal generation (Conf-Gen), a general framework adapting CRC to generative tasks while relaxing its theoretical assumptions. Conf-Gen unifies and generalizes previous attempts to apply CP to LLMs, and extends conformal methodology to entirely new domains. We demonstrate the flexibility of Conf-Gen through some novel applications, including obtaining conformal guarantees on: image generators producing non-memorized images, conversational AI systems having asked enough clarifying questions, and the output of AI agents being correct.

Hao Huang, Ziyan Chen, Huanran Chen et al.

Compared to query-based black-box attacks, transfer-based black-box attacks do not require any information of the attacked models, which ensures their secrecy. However, most existing transfer-based approaches rely on ensembling multiple models to boost the attack transferability, which is time- and resource-intensive, not to mention the difficulty of obtaining diverse models on the same task. To address this limitation, in this work, we focus on the single-model transfer-based black-box attack on object detection, utilizing only one model to achieve a high-transferability adversarial attack on multiple black-box detectors. Specifically, we first make observations on the patch optimization process of the existing method and propose an enhanced attack framework by slightly adjusting its training strategies. Then, we analogize patch optimization with regular model optimization, proposing a series of self-ensemble approaches on the input data, the attacked model, and the adversarial patch to efficiently make use of the limited information and prevent the patch from overfitting. The experimental results show that the proposed framework can be applied with multiple classical base attack methods (e.g., PGD and MIM) to greatly improve the black-box transferability of the well-optimized patch on multiple mainstream detectors, meanwhile boosting white-box performance. Our code is available at https://github.com/VDIGPKU/T-SEA.

Kevin Zhang, Neha Patki, Kalyan Veeramachaneni

The goal of this paper is to describe a system for generating synthetic sequential data within the Synthetic data vault. To achieve this, we present the Sequential model currently in SDV, an end-to-end framework that builds a generative model for multi-sequence, real-world data. This includes a novel neural network-based machine learning model, conditional probabilistic auto-regressive (CPAR) model. The overall system and the model is available in the open source Synthetic Data Vault (SDV) library {https://github.com/sdv-dev/SDV}, along with a variety of other models for different synthetic data needs. After building the Sequential SDV, we used it to generate synthetic data and compared its quality against an existing, non-sequential generative adversarial network based model called CTGAN. To compare the sequential synthetic data against its real counterpart, we invented a new metric called Multi-Sequence Aggregate Similarity (MSAS). We used it to conclude that our Sequential SDV model learns higher level patterns than non-sequential models without any trade-offs in synthetic data quality.

Kevin Zhang, Zhiqiang Shen

Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance the representations are so far not well-explored. In this paper, we aim to explore an interactive Masked Autoencoders (i-MAE) framework to enhance the representation capability from two aspects: (1) employing a two-way image reconstruction and a latent feature reconstruction with distillation loss to learn better features; (2) proposing a semantics-enhanced sampling strategy to boost the learned semantics in MAE. Upon the proposed i-MAE architecture, we can address two critical questions to explore the behaviors of the learned representations in MAE: (1) Whether the separability of latent representations in Masked Autoencoders is helpful for model performance? We study it by forcing the input as a mixture of two images instead of one. (2) Whether we can enhance the representations in the latent feature space by controlling the degree of semantics during sampling on Masked Autoencoders? To this end, we propose a sampling strategy within a mini-batch based on the semantics of training samples to examine this aspect. Extensive experiments are conducted on CIFAR-10/100, Tiny-ImageNet and ImageNet-1K to verify the observations we discovered. Furthermore, in addition to qualitatively analyzing the characteristics of the latent representations, we examine the existence of linear separability and the degree of semantics in the latent space by proposing two evaluation schemes. The surprising and consistent results demonstrate that i-MAE is a superior framework design for understanding MAE frameworks, as well as achieving better representational ability. Code is available at https://github.com/vision-learning-acceleration-lab/i-mae.

Kevin Zhang, Mingyang Xie, Maharshi Gor et al. · deepmind

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the same DIP can generalize to arbitrary inverse problems, from denoising to phase retrieval, while offering competitive performance at each task. The central disadvantage of DIP is that, while feedforward neural networks can reconstruct an image in a single pass, DIP must gradually update its weights over hundreds to thousands of iterations, at a significant computational cost. In this work we use meta-learning to massively accelerate DIP-based reconstructions. By learning a proper initialization for the DIP weights, we demonstrate a 10x improvement in runtimes across a range of inverse imaging tasks. Moreover, we demonstrate that a network trained to quickly reconstruct faces also generalizes to reconstructing natural image patches.

Shuhong Chen, Kevin Zhang, Yichun Shi et al.

We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters. Our anime-style domain poses unique challenges to single-view reconstruction; compared to natural images of human heads, character portrait illustrations have hair and accessories with more complex and diverse geometry, and are shaded with non-photorealistic contour lines. In addition, there is a lack of both 3D model and portrait illustration data suitable to train and evaluate this ambiguous stylized reconstruction task. Facing these challenges, our proposed PAniC-3D architecture crosses the illustration-to-3D domain gap with a line-filling model, and represents sophisticated geometries with a volumetric radiance field. We train our system with two large new datasets (11.2k Vroid 3D models, 1k Vtuber portrait illustrations), and evaluate on a novel AnimeRecon benchmark of illustration-to-3D pairs. PAniC-3D significantly outperforms baseline methods, and provides data to establish the task of stylized reconstruction from portrait illustrations.

Stephen Casper, Yuxiao Li, Jiawei Li et al.

Interpretable AI tools are often motivated by the goal of understanding model behavior in out-of-distribution (OOD) contexts. Despite the attention this area of study receives, there are comparatively few cases where these tools have identified previously unknown bugs in models. We argue that this is due, in part, to a common feature of many interpretability methods: they analyze model behavior by using a particular dataset. This only allows for the study of the model in the context of features that the user can sample in advance. To address this, a growing body of research involves interpreting models using \emph{feature synthesis} methods that do not depend on a dataset. In this paper, we benchmark the usefulness of interpretability tools on debugging tasks. Our key insight is that we can implant human-interpretable trojans into models and then evaluate these tools based on whether they can help humans discover them. This is analogous to finding OOD bugs, except the ground truth is known, allowing us to know when an interpretation is correct. We make four contributions. (1) We propose trojan discovery as an evaluation task for interpretability tools and introduce a benchmark with 12 trojans of 3 different types. (2) We demonstrate the difficulty of this benchmark with a preliminary evaluation of 16 state-of-the-art feature attribution/saliency tools. Even under ideal conditions, given direct access to data with the trojan trigger, these methods still often fail to identify bugs. (3) We evaluate 7 feature-synthesis methods on our benchmark. (4) We introduce and evaluate 2 new variants of the best-performing method from the previous evaluation. A website for this paper and its code is at https://benchmarking-interpretability.csail.mit.edu/

Kevin Zhang, Shi Feng, Yuri D. Lensky et al.

With rapid progress in simulation of strongly interacting quantum Hamiltonians, the challenge in characterizing unknown phases becomes a bottleneck for scientific progress. We demonstrate that a Quantum-Classical hybrid approach (QuCl) of mining sampled projective snapshots with interpretable classical machine learning can unveil signatures of seemingly featureless quantum states. The Kitaev-Heisenberg model on a honeycomb lattice under external magnetic field presents an ideal system to test QuCl, where simulations have found an intermediate gapless phase (IGP) sandwiched between known phases, launching a debate over its elusive nature. We use the correlator convolutional neural network, trained on labeled projective snapshots, in conjunction with regularization path analysis to identify signatures of phases. We show that QuCl reproduces known features of established phases. Significantly, we also identify a signature of the IGP in the spin channel perpendicular to the field direction, which we interpret as a signature of Friedel oscillations of gapless spinons forming a Fermi surface. Our predictions can guide future experimental searches for spin liquids.

Hadi Alzayer, Kevin Zhang, Brandon Feng et al.

The reflective nature of the human eye is an underappreciated source of information about what the world around us looks like. By imaging the eyes of a moving person, we can collect multiple views of a scene outside the camera's direct line of sight through the reflections in the eyes. In this paper, we reconstruct a 3D scene beyond the camera's line of sight using portrait images containing eye reflections. This task is challenging due to 1) the difficulty of accurately estimating eye poses and 2) the entangled appearance of the eye iris and the scene reflections. Our method jointly refines the cornea poses, the radiance field depicting the scene, and the observer's eye iris texture. We further propose a simple regularization prior on the iris texture pattern to improve reconstruction quality. Through various experiments on synthetic and real-world captures featuring people with varied eye colors, we demonstrate the feasibility of our approach to recover 3D scenes using eye reflections.

Daniel Jiwoong Im, Kevin Zhang, Nakul Verma et al.

Existing causal inference (CI) models are often restricted to data with low-dimensional confounders and singleton actions. We propose an autoregressive (AR) CI framework capable of handling complex confounders and sequential actions commonly found in modern applications. Our approach accomplishes this using {\em sequencification}, which transforms data from an underlying causal diagram into a sequence of tokens. Sequencification not only accommodates training with data generated from a large class of DAGs, but also extends existing CI capabilities to estimate multiple causal quantities using a {\em single} model. We can directly compute probabilities from interventional distributions, simplifying inference and improving outcome prediction accuracy. We demonstrate that an AR model adapted for CI is efficient and effective in various complex applications such as navigating mazes, playing chess endgames, and evaluating the impact of certain keywords on paper acceptance rates, where we consider causal queries beyond standard reinforcement learning-type questions.

Xiaowei Chi, Peidong Jia, Chun-Kai Fan et al.

Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely on passive observation and therefore struggle with grasping physical causality. This observation leads to our central hypothesis: authentic physical intuition of the world model must be grounded in extensive, causally rich interactions with the real world. To test this hypothesis, we present WoW, a 14-billion-parameter generative world model trained on 2 million robot interaction trajectories. Our findings reveal that the model's understanding of physics is a probabilistic distribution of plausible outcomes, leading to stochastic instabilities and physical hallucinations. Furthermore, we demonstrate that this emergent capability can be actively constrained toward physical realism by SOPHIA, where vision-language model agents evaluate the DiT-generated output and guide its refinement by iteratively evolving the language instructions. In addition, a co-trained Inverse Dynamics Model translates these refined plans into executable robotic actions, thus closing the imagination-to-action loop. We establish WoWBench, a new benchmark focused on physical consistency and causal reasoning in video, where WoW achieves state-of-the-art performance in both human and autonomous evaluation, demonstrating strong ability in physical causality, collision dynamics, and object permanence. Our work provides systematic evidence that large-scale, real-world interaction is a cornerstone for developing physical intuition in AI. Models, data, and benchmarks will be open-sourced.

Chun-Kai Fan, Xiaowei Chi, Xiaozhu Ju et al.

As world models gain momentum in Embodied AI, an increasing number of works explore using video foundation models as predictive world models for downstream embodied tasks like 3D prediction or interactive generation. However, before exploring these downstream tasks, video foundation models still have two critical questions unanswered: (1) whether their generative generalization is sufficient to maintain perceptual fidelity in the eyes of human observers, and (2) whether they are robust enough to serve as a universal prior for real-world embodied agents. To provide a standardized framework for answering these questions, we introduce the Embodied Turing Test benchmark: WoW-World-Eval (Wow,wo,val). Building upon 609 robot manipulation data, Wow-wo-val examines five core abilities, including perception, planning, prediction, generalization, and execution. We propose a comprehensive evaluation protocol with 22 metrics to assess the models' generation ability, which achieves a high Pearson Correlation between the overall score and human preference (>0.93) and establishes a reliable foundation for the Human Turing Test. On Wow-wo-val, models achieve only 17.27 on long-horizon planning and at best 68.02 on physical consistency, indicating limited spatiotemporal consistency and physical reasoning. For the Inverse Dynamic Model Turing Test, we first use an IDM to evaluate the video foundation models' execution accuracy in the real world. However, most models collapse to $\approx$ 0% success, while WoW maintains a 40.74% success rate. These findings point to a noticeable gap between the generated videos and the real world, highlighting the urgency and necessity of benchmarking World Model in Embodied AI.

Chak-Wing Mak, Guanyu Zhu, Boyi Zhang et al.

Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning, but their grasp of the underlying physics remains underexplored. Existing benchmarks attempting to measure this matter rely on synthetic, Visual Question Answer templates or focus on perceptual video quality that is tangential to measuring how well the video abides by physical laws. To address this fragmentation, we introduce PhysicsMind, a unified benchmark with both real and simulation environments that evaluates law-consistent reasoning and generation over three canonical principles: Center of Mass, Lever Equilibrium, and Newton's First Law. PhysicsMind comprises two main tasks: i) VQA tasks, testing whether models can reason and determine physical quantities and values from images or short videos, and ii) Video Generation(VG) tasks, evaluating if predicted motion trajectories obey the same center-of-mass, torque, and inertial constraints as the ground truth. A broad range of recent models and video generation models is evaluated on PhysicsMind and found to rely on appearance heuristics while often violating basic mechanics. These gaps indicate that current scaling and training are still insufficient for robust physical understanding, underscoring PhysicsMind as a focused testbed for physics-aware multimodal models. Our data will be released upon acceptance.

Anchit Jain, Kevin Zhang, Stephen Bates

Time-to-event data is widespread across the life sciences and engineering, but it is typically encountered together with censoring, which complicates the application of standard machine learning methods. Deep Cox models have emerged as a popular method for analyzing time-to-event data because they gracefully handle censoring and can be used with unstructured data such as clinical text reports, genomic sequences, and pathology images. However, their predicted survival probabilities are often poorly calibrated, thus limiting their practical utility. In this paper, we propose a novel post hoc calibration method for Deep Cox models that uses isotonic regression to refine predicted survival probabilities without affecting discriminative power. We establish favorable theoretical guarantees, including a double-robustness property and asymptotic calibration. Experiments on synthetic and real-world clinical data demonstrate the empirical effectiveness of our method.

Wanxin Tian, Shijie Zhang, Kevin Zhang et al.

Self-evolution, the ability of agents to autonomously improve their reasoning and behavior, is essential for the embodied domain with long-horizon, real-world tasks. Despite current advancements in reinforcement fine-tuning (RFT) showing strong performance in enhancing reasoning in LLMs, its potential to enable self-evolving embodied intelligence with multi-modal interactions remains largely unexplored. Specifically, reinforcement fine-tuning faces two fundamental obstacles in embodied settings: (i) the lack of accessible intermediate rewards in multi-step reasoning tasks limits effective learning signals, and (ii) reliance on hand-crafted reward functions restricts generalization to novel tasks and environments. To address these challenges, we present Self-Evolving Embodied Agents-R1, SEEA-R1, the first RFT framework designed for enabling the self-evolving capabilities of embodied agents. Specifically, to convert sparse delayed rewards into denser intermediate signals that improve multi-step reasoning, we propose Tree-based group relative policy optimization (Tree-GRPO) integrates Monte Carlo Tree Search into GRPO. To generalize reward estimation across tasks and scenes, supporting autonomous adaptation and reward-driven self-evolution, we further introduce Multi-modal Generative Reward Model (MGRM). To holistically evaluate the effectiveness of SEEA-R1, we evaluate on the ALFWorld benchmark, surpassing state-of-the-art methods with scores of 85.07% (textual) and 46.27% (multi-modal), outperforming prior models including GPT-4o. SEEA-R1 also achieves scores of 80.3% (textual) and 44.03% (multi-modal) without ground truth reward, surpassing all open-source baselines and highlighting its scalability as a self-evolving embodied agent. Additional experiments and qualitative analysis further support the potential of SEEA-R1 for future research in scalable embodied intelligence.

Yann Collet, Nick Terrell, W. Felix Handte et al.

In the last few decades, research techniques have improved lossless compression ratios by significantly increasing processing time. However, these techniques have not gained popularity in industry because production systems require high throughput and low resource utilization. Instead, real world improvements in compression are increasingly realized by building application-specific compressors which can exploit knowledge about the structure and semantics of the data being compressed. Application-specific compressor systems outperform even the best generic compressors, but these techniques have severe drawbacks -- they are inherently limited in applicability, are hard to develop, and are difficult to maintain and deploy. In this work, we show that these challenges can be overcome with a new compression strategy. We propose the "graph model" of compression, a new theoretical framework for representing compression as a directed acyclic graph of modular codecs. OpenZL implements this framework and compresses data into a self-describing wire format, any configuration of which can be decompressed by a universal decoder. OpenZL's design enables rapid development of application-specific compressors with minimal code. Experimental results demonstrate that OpenZL achieves superior compression ratios and speeds compared to state-of-the-art general-purpose compressors on a variety of real-world datasets. Compared to ratio-focused deep-learning compressors, OpenZL is competitive on ratio while being many orders of magnitude faster. Internal deployments at Meta have also shown consistent improvements in size and/or speed, with development timelines reduced from months to days. OpenZL thus represents a significant advance in practical, scalable, and maintainable data compression for modern data-intensive applications.

Kevin Zhang, Sakshum Kulshrestha, Christopher Metzler

Despite recent advances, developing general-purpose universal denoising and artifact-removal networks remains largely an open problem: Given fixed network weights, one inherently trades-off specialization at one task (e.g.,~removing Poisson noise) for performance at another (e.g.,~removing speckle noise). In addition, training such a network is challenging due to the curse of dimensionality: As one increases the dimensions of the specification-space (i.e.,~the number of parameters needed to describe the noise distribution) the number of unique specifications one needs to train for grows exponentially. Uniformly sampling this space will result in a network that does well at very challenging problem specifications but poorly at easy problem specifications, where even large errors will have a small effect on the overall mean squared error. In this work we propose training denoising networks using an adaptive-sampling/active-learning strategy. Our work improves upon a recently proposed universal denoiser training strategy by extending these results to higher dimensions and by incorporating a polynomial approximation of the true specification-loss landscape. This approximation allows us to reduce training times by almost two orders of magnitude. We test our method on simulated joint Poisson-Gaussian-Speckle noise and demonstrate that with our proposed training strategy, a single blind, generalist denoiser network can achieve peak signal-to-noise ratios within a uniform bound of specialized denoiser networks across a large range of operating conditions. We also capture a small dataset of images with varying amounts of joint Poisson-Gaussian-Speckle noise and demonstrate that a universal denoiser trained using our adaptive-sampling strategy outperforms uniformly trained baselines.

Kevin Zhang, Kuangzhi Ge, Xiaowei Chi et al.

Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question: with the advent of strong video foundational models, might they supplant conventional vision encoder paradigms for general-purpose multimodal understanding? While recent studies have begun to explore the potential of world models on common vision tasks, these explorations typically lack a systematic investigation of generic, multimodal tasks. In this work, we strive to investigate the capabilities when world model priors are transferred into Vision-Language Models: we re-purpose a video diffusion model as a generative encoder to perform a single denoising step and treat the resulting latents as a set of visual embedding. We empirically investigate this class of models, which we refer to as World-Language Models (WorldLMs), and we find that generative encoders can capture latents useful for downstream understanding that show distinctions from conventional encoders. Naming our best-performing variant Dynamic Vision Aligner (DyVA), we further discover that this method significantly enhances spatial reasoning abilities and enables single-image models to perform multi-frame reasoning. Through the curation of a suite of visual reasoning tasks, we find DyVA to surpass both open-source and proprietary baselines, achieving state-of-the-art or comparable performance. We attribute these gains to WorldLM's inherited motion-consistency internalization from video pre-training. Finally, we systematically explore extensive model designs to highlight promising directions for future work. We hope our study can pave the way for a new family of VLMs that leverage priors from world models and are on a promising path towards generalist vision learners.

Jonathan Rosenthal, Shanchao Liang, Kevin Zhang et al.

Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, and interpretation of model results, but also makes it harder for white-hat researchers to identify vulnerabilities in the MLaaS systems. Model extraction is a promising technique to address these challenges by reverse-engineering black-box models. Since training data is typically unavailable for MLaaS models, this paper focuses on the realistic version of it: data-free model extraction. We propose a data-free model extraction approach, CaBaGe, to achieve higher model extraction accuracy with a small number of queries. Our innovations include (1) a novel experience replay for focusing on difficult training samples; (2) an ensemble of generators for steadily producing diverse synthetic data; and (3) a selective filtering process for querying the victim model with harder, more balanced samples. In addition, we create a more realistic setting, for the first time, where the attacker has no knowledge of the number of classes in the victim training data, and create a solution to learn the number of classes on the fly. Our evaluation shows that CaBaGe outperforms existing techniques on seven datasets -- MNIST, FMNIST, SVHN, CIFAR-10, CIFAR-100, ImageNet-subset, and Tiny ImageNet -- with an accuracy improvement of the extracted models by up to 43.13%. Furthermore, the number of queries required to extract a clone model matching the final accuracy of prior work is reduced by up to 75.7%.

Mohamad Qadri, Kevin Zhang, Akshay Hinduja et al.

Underwater perception and 3D surface reconstruction are challenging problems with broad applications in construction, security, marine archaeology, and environmental monitoring. Treacherous operating conditions, fragile surroundings, and limited navigation control often dictate that submersibles restrict their range of motion and, thus, the baseline over which they can capture measurements. In the context of 3D scene reconstruction, it is well-known that smaller baselines make reconstruction more challenging. Our work develops a physics-based multimodal acoustic-optical neural surface reconstruction framework (AONeuS) capable of effectively integrating high-resolution RGB measurements with low-resolution depth-resolved imaging sonar measurements. By fusing these complementary modalities, our framework can reconstruct accurate high-resolution 3D surfaces from measurements captured over heavily-restricted baselines. Through extensive simulations and in-lab experiments, we demonstrate that AONeuS dramatically outperforms recent RGB-only and sonar-only inverse-differentiable-rendering--based surface reconstruction methods. A website visualizing the results of our paper is located at this address: https://aoneus.github.io/

Shijie Zhang, Kevin Zhang, Zheyuan Gu et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative Policy Optimization (GRPO) stands as the dominant algorithm in this domain due to its stable training and critic-free efficiency. However, we argue that GRPO suffers from a structural limitation: it imposes a uniform, static trust region constraint across all samples. This design implicitly assumes signal homogeneity, a premise misaligned with the heterogeneous nature of outcome-driven learning, where advantage magnitudes and variances fluctuate significantly. Consequently, static constraints fail to fully exploit high-quality signals while insufficiently suppressing noise, often precipitating rapid entropy collapse. To address this, we propose \textbf{E}lastic \textbf{T}rust \textbf{R}egions (\textbf{ETR}), a dynamic mechanism that aligns optimization constraints with signal quality. ETR constructs a signal-aware landscape through dual-level elasticity: at the micro level, it scales clipping boundaries based on advantage magnitude to accelerate learning from high-confidence paths; at the macro level, it leverages group variance to implicitly allocate larger update budgets to tasks in the optimal learning zone. Extensive experiments on AIME and MATH benchmarks demonstrate that ETR consistently outperforms GRPO, achieving superior accuracy while effectively mitigating policy entropy degradation to ensure sustained exploration.

Shijie Zhang, Xiang Guo, Rujun Guo et al.

Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the interpretable reasoning traces of Large Language Models (LLMs), we propose a novel \textbf{Answer-First, Reason Later (AFRL)} paradigm. This paradigm requires the model to output the definitive relevance score in the very first token, followed by a structured logical explanation. Inspired by the success of reasoning models, we adopt a "Supervised Fine-Tuning (SFT) + Reinforcement Learning (RL)" pipeline to achieve AFRL. However, directly applying existing RL training often leads to \textbf{mode collapse} in the search relevance task, where the model forgets complex long-tail rules in pursuit of high rewards. From an information theory perspective: RL inherently minimizes the \textbf{Reverse KL divergence}, which tends to seek probability peaks (mode-seeking) and is prone to "reward hacking." On the other hand, SFT minimizes the \textbf{Forward KL divergence}, forcing the model to cover the data distribution (mode-covering) and effectively anchoring expert rules. Based on this insight, we propose a \textbf{Mode-Balanced Optimization} strategy, incorporating an SFT auxiliary loss into Stepwise-GRPO training to balance these two properties. Furthermore, we construct an automated instruction evolution system and a multi-stage curriculum to ensure expert-level data quality. Extensive experiments demonstrate that our 32B teacher model achieves state-of-the-art performance. Moreover, the AFRL architecture enables efficient knowledge distillation, successfully transferring expert-level logic to a 0.6B model, thereby reconciling reasoning depth with deployment latency.

Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri et al.

Differentiable 3D-Gaussian splatting (GS) is emerging as a prominent technique in computer vision and graphics for reconstructing 3D scenes. GS represents a scene as a set of 3D Gaussians with varying opacities and employs a computationally efficient splatting operation along with analytical derivatives to compute the 3D Gaussian parameters given scene images captured from various viewpoints. Unfortunately, capturing surround view ($360^{\circ}$ viewpoint) images is impossible or impractical in many real-world imaging scenarios, including underwater imaging, rooms inside a building, and autonomous navigation. In these restricted baseline imaging scenarios, the GS algorithm suffers from a well-known 'missing cone' problem, which results in poor reconstruction along the depth axis. In this manuscript, we demonstrate that using transient data (from sonars) allows us to address the missing cone problem by sampling high-frequency data along the depth axis. We extend the Gaussian splatting algorithms for two commonly used sonars and propose fusion algorithms that simultaneously utilize RGB camera data and sonar data. Through simulations, emulations, and hardware experiments across various imaging scenarios, we show that the proposed fusion algorithms lead to significantly better novel view synthesis (5 dB improvement in PSNR) and 3D geometry reconstruction (60% lower Chamfer distance).

Guanqun Wang, Jiaming Liu, Chenxuan Li et al.

The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning, commonsense reasoning, and visual scene understanding. However, the deployment of these large-scale MLLMs on client devices is hindered by their extensive model parameters, leading to a notable decline in generalization capabilities when these models are compressed for device deployment. Addressing this challenge, we introduce a Cloud-Device Collaborative Continual Adaptation framework, designed to enhance the performance of compressed, device-deployed MLLMs by leveraging the robust capabilities of cloud-based, larger-scale MLLMs. Our framework is structured into three key components: a device-to-cloud uplink for efficient data transmission, cloud-based knowledge adaptation, and an optimized cloud-to-device downlink for model deployment. In the uplink phase, we employ an Uncertainty-guided Token Sampling (UTS) strategy to effectively filter out-of-distribution tokens, thereby reducing transmission costs and improving training efficiency. On the cloud side, we propose Adapter-based Knowledge Distillation (AKD) method to transfer refined knowledge from large-scale to compressed, pocket-size MLLMs. Furthermore, we propose a Dynamic Weight update Compression (DWC) strategy for the downlink, which adaptively selects and quantizes updated weight parameters, enhancing transmission efficiency and reducing the representational disparity between cloud and device models. Extensive experiments on several multimodal benchmarks demonstrate the superiority of our proposed framework over prior Knowledge Distillation and device-cloud collaboration methods. Notably, we also validate the feasibility of our approach to real-world experiments.

Kevin Zhang, Luka Chkhetiani, Francis McCann Ramirez et al. · deepmind

This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we perform Noisy Student Training after generating pseudo-labels for the unlabeled public data using a strong Conformer RNN-T baseline model. The addition of these pseudo-labeled data results in remarkable improvements in relative Word Error Rate (WER) by 11.5% and 24.3% for our asynchronous and realtime models, respectively. Additionally, the model is more robust to background noise owing to the addition of these data. The results obtained in this study demonstrate that the incorporation of pseudo-labeled publicly available data is a highly effective strategy for improving ASR accuracy and noise robustness.

Kuangzhi Ge, Lingjun Chen, Kevin Zhang et al.

Recently, significant advances have been made in Video Large Language Models (Video LLMs) in both academia and industry. However, methods to evaluate and benchmark the performance of different Video LLMs, especially their fine-grained, temporal visual capabilities, remain very limited. On one hand, current benchmarks use relatively simple videos (e.g., subtitled movie clips) where the model can understand the entire video by processing just a few frames. On the other hand, their datasets lack diversity in task format, comprising only QA or multi-choice QA, which overlooks the models' capacity for generating in-depth and precise texts. Sports videos, which feature intricate visual information, sequential events, and emotionally charged commentary, present a critical challenge for Video LLMs, making sports commentary an ideal benchmarking task. Inspired by these challenges, we propose a novel task: sports video commentary generation, developed $\textbf{SCBench}$ for Video LLMs. To construct such a benchmark, we introduce (1) $\textbf{SCORES}$, a six-dimensional metric specifically designed for our task, upon which we propose a GPT-based evaluation method, and (2) $\textbf{CommentarySet}$, a dataset consisting of 5,775 annotated video clips and ground-truth labels tailored to our metric. Based on SCBench, we conduct comprehensive evaluations on multiple Video LLMs (e.g. VILA, Video-LLaVA, etc.) and chain-of-thought baseline methods. Our results found that InternVL-Chat-2 achieves the best performance with 5.44, surpassing the second-best by 1.04. Our work provides a fresh perspective for future research, aiming to enhance models' overall capabilities in complex visual understanding tasks. Our dataset will be released soon.

Wisdom O. Ikezogwo, Kevin Zhang, Mehmet Saygin Seyfioglu et al.

We propose MedicalNarratives, a dataset curated from medical pedagogical videos similar in nature to data collected in Think-Aloud studies and inspired by Localized Narratives, which collects grounded image-text data by curating instructors' speech and mouse cursor movements synchronized in time. MedicalNarratives enables pretraining of both semantic and dense objectives, alleviating the need to train medical semantic and dense tasks disparately due to the lack of reasonably sized datasets. Our dataset contains 4.7M image-text pairs from videos and articles, with 1M samples containing dense annotations in the form of traces and bounding boxes. To evaluate the utility of MedicalNarratives, we train GenMedClip based on the CLIP architecture using our dataset spanning 12 medical domains and demonstrate that it outperforms previous state-of-the-art models on a newly constructed medical imaging benchmark that comprehensively evaluates performance across all modalities. Data, demo, code and models available at https://medical-narratives.github.io

Kevin Zhang, Yixin Wang

While probabilistic graphical models can discover latent structure in data, their effectiveness hinges on choosing well-specified models. Identifying such models is challenging in practice, often requiring iterative checking and revision through trial and error. To this end, we propose meta-probabilistic modeling (MPM), a meta-learning algorithm that learns generative model structure directly from multiple related datasets. MPM uses a hierarchical architecture where global model specifications are shared across datasets while local parameters remain dataset-specific. For learning and inference, we propose a tractable VAE-inspired surrogate objective, and optimize it through bi-level optimization: local variables are updated analytically via coordinate ascent, while global parameters are trained with gradient-based methods. We evaluate MPM on object-centric image modeling and sequential text modeling, demonstrating that it adapts generative models to data while recovering meaningful latent representations.

Shijie Zhang, Guohao Sun, Kevin Zhang et al.

Recently, online Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically treat all training samples uniformly, overlooking the vast differences in problem difficulty relative to the model's current capabilities. This uniform training strategy leads to inefficient exploration of problems the model has already mastered, while concurrently lacking effective guidance on problems that are challenging its abilities the most, limiting both learning efficiency and upper-bound performance. To address this, we propose CLPO (Curriculum-guided Learning for Policy Optimization), a novel algorithm that creates a dynamic pedagogical feedback loop within the policy optimization process. The core of CLPO leverages the model's own rollout performance to conduct real-time difficulty assessment, thereby constructing an Online Curriculum. This curriculum then guides an Adaptive Problem Restructuring mechanism, where the model acts as its own teacher: it diversifies medium-difficulty problems to promote generalization and simplifies challenging problems to make them more attainable. Our approach transforms the static training procedure into a dynamic process that co-evolves with the model's capabilities. Experiments show that CLPO achieves state-of-the-art performance across eight challenging mathematical and general reasoning benchmarks, with an average pass@1 improvement of 6.96% over other methods, demonstrating its potential for more efficiently training more capable reasoning models.

Mahtab Bigverdi, Wisdom Ikezogwo, Kevin Zhang et al.

Multimodal language models (MLMs) show promise for clinical decision support and diagnostic reasoning, raising the prospect of end-to-end automated medical image interpretation. However, clinicians are highly selective in adopting AI tools; a model that makes errors on seemingly simple perception tasks such as determining image orientation or identifying whether a CT scan is contrast-enhance are unlikely to be adopted for clinical tasks. We introduce Medblink, a benchmark designed to probe these models for such perceptual abilities. Medblink spans eight clinically meaningful tasks across multiple imaging modalities and anatomical regions, totaling 1,429 multiple-choice questions over 1,605 images. We evaluate 19 state-of-the-art MLMs, including general purpose (GPT4o, Claude 3.5 Sonnet) and domain specific (Med Flamingo, LLaVA Med, RadFM) models. While human annotators achieve 96.4% accuracy, the best-performing model reaches only 65%. These results show that current MLMs frequently fail at routine perceptual checks, suggesting the need to strengthen their visual grounding to support clinical adoption. Data is available on our project page.

Kevin Zhang, Yonghan Jung, Divyat Mahajan et al.

Identifying and measuring biases associated with sensitive attributes is a crucial consideration in healthcare to prevent treatment disparities. One prominent issue is inaccurate pulse oximeter readings, which tend to overestimate oxygen saturation for dark-skinned patients and misrepresent supplemental oxygen needs. Most existing research has revealed statistical disparities linking device measurement errors to patient outcomes in intensive care units (ICUs) without causal formalization. This study causally investigates how racial discrepancies in oximetry measurements affect invasive ventilation in ICU settings. We employ a causal inference-based approach using path-specific effects to isolate the impact of bias by race on clinical decision-making. To estimate these effects, we leverage a doubly robust estimator, propose its self-normalized variant for improved sample efficiency, and provide novel finite-sample guarantees. Our methodology is validated on semi-synthetic data and applied to two large real-world health datasets: MIMIC-IV and eICU. Contrary to prior work, our analysis reveals minimal impact of racial discrepancies on invasive ventilation rates. However, path-specific effects mediated by oxygen saturation disparity are more pronounced on ventilation duration, and the severity differs by dataset. Our work provides a novel pipeline for investigating potential disparities in clinical decision-making and, more importantly, highlights the necessity of causal methods to robustly assess fairness in healthcare.

Tianxiang Lin, Mohamad Qadri, Kevin Zhang et al.

We consider the problem of optimizing neural implicit surfaces for 3D reconstruction using acoustic images collected with drifting sensor poses. The accuracy of current state-of-the-art 3D acoustic modeling algorithms is highly dependent on accurate pose estimation; small errors in sensor pose can lead to severe reconstruction artifacts. In this paper, we propose an algorithm that jointly optimizes the neural scene representation and sonar poses. Our algorithm does so by parameterizing the 6DoF poses as learnable parameters and backpropagating gradients through the neural renderer and implicit representation. We validated our algorithm on both real and simulated datasets. It produces high-fidelity 3D reconstructions even under significant pose drift.

Guanqun Wang, Xinyu Wei, Jiaming Liu et al.

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception tasks, such as detection and segmentation. However, MLLMs mainly focus on high-level image-text interpretations and struggle with fine-grained visual understanding, and vision perception models usually suffer from open-world distribution shifts due to their limited model capacity. To overcome these challenges, we propose the Mutually Reinforced Multimodal Large Language Model (MR-MLLM), a novel framework that synergistically enhances visual perception and multimodal comprehension. First, a shared query fusion mechanism is proposed to harmonize detailed visual inputs from vision models with the linguistic depth of language models, enhancing multimodal comprehension and vision perception synergistically. Second, we propose the perception-enhanced cross-modal integration method, incorporating novel modalities from vision perception outputs, like object detection bounding boxes, to capture subtle visual elements, thus enriching the understanding of both visual and textual data. In addition, an innovative perception-embedded prompt generation mechanism is proposed to embed perceptual information into the language model's prompts, aligning the responses contextually and perceptually for a more accurate multimodal interpretation. Extensive experiments demonstrate MR-MLLM's superior performance in various multimodal comprehension and vision perception tasks, particularly those requiring corner case vision perception and fine-grained language comprehension.

Haoming Cai, Jingxi Chen, Brandon Y. Feng et al.

tmospheric turbulence presents a significant challenge in long-range imaging. Current restoration algorithms often struggle with temporal inconsistency, as well as limited generalization ability across varying turbulence levels and scene content different than the training data. To tackle these issues, we introduce a self-supervised method, Consistent Video Restoration through Turbulence (ConVRT) a test-time optimization method featuring a neural video representation designed to enhance temporal consistency in restoration. A key innovation of ConVRT is the integration of a pretrained vision-language model (CLIP) for semantic-oriented supervision, which steers the restoration towards sharp, photorealistic images in the CLIP latent space. We further develop a principled selection strategy of text prompts, based on their statistical correlation with a perceptual metric. ConVRT's test-time optimization allows it to adapt to a wide range of real-world turbulence conditions, effectively leveraging the insights gained from pre-trained models on simulated data. ConVRT offers a comprehensive and effective solution for mitigating real-world turbulence in dynamic videos.

Kevin Zhang, Vipul Mann, Venkat Venkatasubramanian

Various template-based and template-free approaches have been proposed for single-step retrosynthesis prediction in recent years. While these approaches demonstrate strong performance from a data-driven metrics standpoint, many model architectures do not incorporate underlying chemistry principles. Here, we propose a novel chemistry-aware retrosynthesis prediction framework that combines powerful data-driven models with prior domain knowledge. We present a tree-to-sequence transformer architecture that utilizes hierarchical SMILES grammar-based trees, incorporating crucial chemistry information that is often overlooked by SMILES text-based representations, such as local structures and functional groups. The proposed framework, grammar-based molecular attention tree transformer (G-MATT), achieves significant performance improvements compared to baseline retrosynthesis models. G-MATT achieves a promising top-1 accuracy of 51% (top-10 accuracy of 79.1%), invalid rate of 1.5%, and bioactive similarity rate of 74.8% on the USPTO- 50K dataset. Additional analyses of G-MATT attention maps demonstrate the ability to retain chemistry knowledge without relying on excessively complex model architectures.

Anish Bhattacharya, Akshit Gandhi, Lukas Merkle et al.

For robotic systems to succeed in high risk, real-world situations, they have to be quickly deployable and robust to environmental changes, under-performing hardware, and mission subtask failures. These robots are often designed to consider a single sequence of mission events, with complex algorithms lowering individual subtask failure rates under some critical constraints. Our approach utilizes common techniques in vision and control, and encodes robustness into mission structure through outcome monitoring and recovery strategies. In addition, our system infrastructure enables rapid deployment and requires no central communication. This report also includes lessons in rapid field robotic development and testing. We developed and evaluated our systems through real-robot experiments at an outdoor test site in Pittsburgh, Pennsylvania, USA, as well as in the 2020 Mohamed Bin Zayed International Robotics Challenge. All competition trials were completed in fully autonomous mode without RTK-GPS. Our system placed fourth in Challenge 2 and seventh in the Grand Challenge, with notable achievements such as popping five balloons (Challenge 1), successfully picking and placing a block (Challenge 2), and dispensing the most water onto an outdoor, real fire with an autonomous UAV (Challenge 3).

Ke Wang, Michael Kellman, Christopher M. Sandino et al.

Deep learning (DL) based unrolled reconstructions have shown state-of-the-art performance for under-sampled magnetic resonance imaging (MRI). Similar to compressed sensing, DL can leverage high-dimensional data (e.g. 3D, 2D+time, 3D+time) to further improve performance. However, network size and depth are currently limited by the GPU memory required for backpropagation. Here we use a memory-efficient learning (MEL) framework which favorably trades off storage with a manageable increase in computation during training. Using MEL with multi-dimensional data, we demonstrate improved image reconstruction performance for in-vivo 3D MRI and 2D+time cardiac cine MRI. MEL uses far less GPU memory while marginally increasing the training time, which enables new applications of DL to high-dimensional MRI.

Amrita Sawhney, Steven Lee, Kevin Zhang et al.

A key challenge in robotic food manipulation is modeling the material properties of diverse and deformable food items. We propose using a multimodal sensory approach to interact and play with food that facilitates the ability to distinguish these properties across food items. First, we use a robotic arm and an array of sensors, which are synchronized using ROS, to collect a diverse dataset consisting of 21 unique food items with varying slices and properties. Afterwards, we learn visual embedding networks that utilize a combination of proprioceptive, audio, and visual data to encode similarities among food items using a triplet loss formulation. Our evaluations show that embeddings learned through interactions can successfully increase performance in a wide range of material and shape classification tasks. We envision that these learned embeddings can be utilized as a basis for planning and selecting optimal parameters for more material-aware robotic food manipulation skills. Furthermore, we hope to stimulate further innovations in the field of food robotics by sharing this food playing dataset with the research community.

Kevin Zhang, Mohit Sharma, Jacky Liang et al.

We designed a modular robotic control stack that provides a customizable and accessible interface to the Franka Emika Panda Research robot. This framework abstracts high-level robot control commands as skills, which are decomposed into combinations of trajectory generators, feedback controllers, and termination handlers. Low-level control is implemented in C++ and runs at $1$kHz, and high-level commands are exposed in Python. In addition, external sensor feedback, like estimated object poses, can be streamed to the low-level controllers in real time. This modular approach allows us to quickly prototype new control methods, which is essential for research applications. We have applied this framework across a variety of real-world robot tasks in more than $5$ published research papers. The framework is currently shared internally with other robotics labs at Carnegie Mellon University, and we plan for a public release in the near future.

Michael Kellman, Kevin Zhang, Jon Tamir et al.

Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical model-based reconstructions (termed physics-based networks). However, for real-world large-scale inverse problems, computing gradients via backpropagation is infeasible due to memory limitations of graphics processing units. In this work, we propose a memory-efficient learning procedure that exploits the reversibility of the network's layers to enable data-driven design for large-scale computational imaging systems. We demonstrate our method on a small-scale compressed sensing example, as well as two large-scale real-world systems: multi-channel magnetic resonance imaging and super-resolution optical microscopy.

Kevin Zhang, Mohit Sharma, Manuela Veloso et al.

Cutting is a common form of manipulation when working with divisible objects such as food, rope, or clay. Cooking in particular relies heavily on cutting to divide food items into desired shapes. However, cutting food is a challenging task due to the wide range of material properties exhibited by food items. Due to this variability, the same cutting motions cannot be used for all food items. Sensations from contact events, e.g., when placing the knife on the food item, will also vary depending on the material properties, and the robot will need to adapt accordingly. In this paper, we propose using vibrations and force-torque feedback from the interactions to adapt the slicing motions and monitor for contact events. The robot learns neural networks for performing each of these tasks and generalizing across different material properties. By adapting and monitoring the skill executions, the robot is able to reliably cut through more than 20 different types of food items and even detect whether certain food items are fresh or old.

Kevin Zhang, Feng Xiong, Peize Sun et al.

Detecting human in a crowd is a challenging problem due to the uncertainties of occlusion patterns. In this paper, we propose to handle the crowd occlusion problem in human detection by leveraging the head part. Double Anchor RPN is developed to capture body and head parts in pairs. A proposal crossover strategy is introduced to generate high-quality proposals for both parts as a training augmentation. Features of coupled proposals are then aggregated efficiently to exploit the inherent relationship. Finally, a Joint NMS module is developed for robust post-processing. The proposed framework, called Double Anchor R-CNN, is able to detect the body and head for each person simultaneously in crowded scenarios. State-of-the-art results are reported on challenging human detection datasets. Our model yields log-average miss rates (MR) of 51.79pp on CrowdHuman, 55.01pp on COCOPersons~(crowded sub-dataset) and 40.02pp on CrowdPose~(crowded sub-dataset), which outperforms previous baseline detectors by 3.57pp, 3.82pp, and 4.24pp, respectively. We hope our simple and effective approach will serve as a solid baseline and help ease future research in crowded human detection.

Mohit Sharma, Kevin Zhang, Oliver Kroemer

In this work, we present an interaction-based approach to learn semantically rich representations for the task of slicing vegetables. Unlike previous approaches, we focus on object-centric representations and use auxiliary tasks to learn rich representations using a two-step process. First, we use simple auxiliary tasks, such as predicting the thickness of a cut slice, to learn an embedding space which captures object properties that are important for the task of slicing vegetables. In the second step, we use these learned latent embeddings to learn a forward model. Learning a forward model affords us to plan online in the latent embedding space and forces our model to improve its representations while performing the slicing task. To show the efficacy of our approach we perform experiments on two different vegetables: cucumbers and tomatoes. Our experimental evaluation shows that our method is able to capture important semantic properties for the slicing task, such as the thickness of the vegetable being cut. We further show that by using our learned forward model, we can plan for the task of vegetable slicing.