arXiv subjects

Amy Zhao

Publications and source records attributed to Amy Zhao.

17 recordsLinked to original sources

arXiv2026

HumanCLAW: Can Vision-Language Models Act Through a Body?

Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous full-body motion with real physical consequences, including gravity and collisions. The body can therefore act freely in the physical world, while execution-side disturbances, balance and motor errors, are factored out. What remains measurable is the model's action intelligence: its moment-to-moment choice of what the body should execute next. Based on this framework, we build HumanCLAW-Bench: 1,218 long-horizon, egocentric find-navigate-interact episodes across 41 indoor scenes. We test nine state-of-the-art VLMs and find that none solves the benchmark; the best model reaches only a 16.8% success rate. Recognizing the target is not the bottleneck. What current VLMs lack is embodied self-awareness: they lose track of their own body, failing to tell where it is, whether it has reached the goal, or whether it has hit an obstacle.

cs.CV↗

arXiv2026

Paper Agents, Paper Gains: An Empirical Analysis of DeFi Investment Agents

DeFi investment agents, systems that use AI for autonomous on-chain trading, have attained over USD 3 billion in combined token valuations since late 2024. We survey over 1,900 AI-tagged crypto projects, filter to investment-focused agents, and curate 10 representative projects spanning strategy and observability dimensions. We then conduct a deep-dive architectural analysis of two prominent agent frameworks, ElizaOS and Virtuals Protocol, and a quantitative on-chain performance analysis of 11 Solana-based agent treasuries with publicly attributable trading activity, covering 925,323 token holders. We find that current deployments remain early and heterogeneous: (1) in our sample, many projects do not yet provide clear evidence of autonomous trade execution, and developer interviews suggest that many visible deployments remain basic API integrations; (2) agent treasuries retain over USD 30M in paper gains while token holders collectively lost USD 191.7M, with the top 1% of wallets capturing 81.4% of all gains (USD 1.81B); (3) token valuations are weakly connected to treasury fundamentals, with market-cap-to-AUM ratios exceeding 10,000x versus below 1x for established DeFi protocols; and (4) aggregate user gains peaked at USD 2.4B before declining to net losses, with median returns negative on every platform and tokens declining 93% on average from all-time highs. We interpret these outcomes as characteristic of a permissionless, first-generation market in which open infrastructure enables rapid experimentation but also allows naive or speculative agents to launch before robust standards for autonomy, performance, and stakeholder alignment emerge. We therefore propose a maturity framework along three dimensions: autonomous execution, risk-adjusted profitability, and stakeholder alignment, to characterize the gap between current deployments and future investment-grade agent systems.

cs.AI↗

arXiv2026

EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR

Egocentric human motion estimation is essential for AR/VR experiences, yet remains challenging due to limited body coverage from the egocentric viewpoint, frequent occlusions, and scarce labeled data. We present EgoPoseFormer v2, a method that addresses these challenges through two key contributions: (1) a transformer-based model for temporally consistent and spatially grounded body pose estimation, and (2) an auto-labeling system that enables the use of large unlabeled datasets for training. Our model is fully differentiable, introduces identity-conditioned queries, multi-view spatial refinement, causal temporal attention, and supports both keypoints and parametric body representations under a constant compute budget. The auto-labeling system scales learning to tens of millions of unlabeled frames via uncertainty-aware semi-supervised training. The system follows a teacher-student schema to generate pseudo-labels and guide training with uncertainty distillation, enabling the model to generalize to different environments. On the EgoBody3M benchmark, with a 0.8 ms latency on GPU, our model outperforms two state-of-the-art methods by 12.2% and 19.4% in accuracy, and reduces temporal jitter by 22.2% and 51.7%. Furthermore, our auto-labeling system further improves the wrist MPJPE by 13.1%.

cs.CV↗

arXiv2026

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilities due to the limited scale of available text-motion pairs. Furthermore, prior methods typically convert motion into discrete representations via quantization to integrate with language models, introducing substantial jitter artifacts from discrete tokenization. To address these challenges, we propose LLaMo, a unified framework that extends pretrained LLMs through a modality-specific Mixture-of-Transformers (MoT) architecture. This design inherently preserves the language understanding of the base model while enabling scalable multimodal adaptation. We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone through a lightweight flow-matching head, allowing for streaming motion generation in real-time (>30 FPS). Leveraging the comprehensive language understanding of pretrained LLMs and large-scale motion-text pretraining, our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings, especially zero-shot motion generation, marking a significant step towards a general unified motion-language large model.

cs.CV↗

arXiv2026

The CoinAlg Bind: Profitability-Fairness Tradeoffs in Collective Investment Algorithms

Collective Investment Algorithms (CoinAlgs) are increasingly popular systems that deploy shared trading strategies for investor communities. Their goal is to democratize sophisticated -- often AI-based -- investing tools. We identify and demonstrate a fundamental profitability-fairness tradeoff in CoinAlgs that we call the CoinAlg Bind: CoinAlgs cannot ensure economic fairness without losing profit to arbitrage. We present a formal model of CoinAlgs, with definitions of privacy (incomplete algorithm disclosure) and economic fairness (value extraction by an adversarial insider). We prove two complementary results that together demonstrate the CoinAlg Bind. First, privacy in a CoinAlg is a precondition for insider attacks on economic fairness. Conversely, in a game-theoretic model, lack of privacy, i.e., transparency, enables arbitrageurs to erode the profitability of a CoinAlg. Using data from Uniswap, a decentralized exchange, we empirically study both sides of the CoinAlg Bind. We quantify the impact of arbitrage against transparent CoinAlgs. We show the risks posed by a private CoinAlg: Even low-bandwidth covert-channel information leakage enables unfair value extraction.

cs.GT↗

arXiv2025

BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models

Early children's developmental trajectories set up a natural goal for sample-efficient pretraining of vision foundation models. We introduce BabyVLM-V2, a developmentally grounded framework for infant-inspired vision-language modeling that extensively improves upon BabyVLM-V1 through a longitudinal, multifaceted pretraining set, a versatile model, and, most importantly, DevCV Toolbox for cognitive evaluation. The pretraining set maximizes coverage while minimizing curation of a longitudinal, infant-centric audiovisual corpus, yielding video-utterance, image-utterance, and multi-turn conversational data that mirror infant experiences. DevCV Toolbox adapts all vision-related measures of the recently released NIH Baby Toolbox into a benchmark suite of ten multimodal tasks, covering spatial reasoning, memory, and vocabulary understanding aligned with early children's capabilities. Experimental results show that a compact model pretrained from scratch can achieve competitive performance on DevCV Toolbox, outperforming GPT-4o on some tasks. We hope the principled, unified BabyVLM-V2 framework will accelerate research in developmentally plausible pretraining of vision foundation models.

cs.CV↗

arXiv2025

Voting-Bloc Entropy: A New Metric for DAO Decentralization

Decentralized Autonomous Organizations (DAOs) use smart contracts to foster communities working toward common goals. Existing definitions of decentralization, however -- the 'D' in DAO -- fall short of capturing the key properties characteristic of diverse and equitable participation. This work proposes a new framework for measuring DAO decentralization called Voting-Bloc Entropy (VBE, pronounced ''vibe''). VBE is based on the idea that voters with closely aligned interests act as a centralizing force and should be modeled as such. VBE formalizes this notion by measuring the similarity of participants' utility functions across a set of voting rounds. Unlike prior, ad hoc definitions of decentralization, VBE derives from first principles: We introduce a simple (yet powerful) reinforcement learning-based conceptual model for voting, that in turn implies VBE. We first show VBE's utility as a theoretical tool. We prove a number of results about the (de)centralizing effects of vote delegation, proposal bundling, bribery, etc. that are overlooked in previous notions of DAO decentralization. Our results lead to practical suggestions for enhancing DAO decentralization. We also show how VBE can be used empirically by presenting measurement studies and VBE-based governance experiments. We make the tools we developed for these results available to the community in the form of open-source artifacts in order to facilitate future study of DAO decentralization.

cs.MA↗

arXiv2025

B-Privacy: Defining and Enforcing Privacy in Weighted Voting

In traditional, one-vote-per-person voting systems, privacy equates with ballot secrecy: voting tallies are published, but individual voters' choices are concealed. Voting systems that weight votes in proportion to token holdings, though, are now prevalent in cryptocurrency and web3 systems. We show that these weighted-voting systems overturn existing notions of voter privacy. Our experiments demonstrate that even with secret ballots, publishing raw tallies often reveals voters' choices. Weighted voting thus requires a new framework for privacy. We introduce a notion called B-privacy whose basis is bribery, a key problem in voting systems today. B-privacy captures the economic cost to an adversary of bribing voters based on revealed voting tallies. We propose a mechanism to boost B-privacy by noising voting tallies. We prove bounds on its tradeoff between B-privacy and transparency, meaning reported-tally accuracy. Analyzing 3,582 proposals across 30 Decentralized Autonomous Organizations (DAOs), we find that the prevalence of large voters ("whales") limits the effectiveness of any B-Privacy-enhancing technique. However, our mechanism proves to be effective in cases without extreme voting weight concentration: among proposals requiring coalitions of $\geq5$ voters to flip outcomes, our mechanism raises B-privacy by a geometric mean factor of $4.1\times$. Our work offers the first principled guidance on transparency-privacy tradeoffs in weighted-voting systems, complementing existing approaches that focus on ballot secrecy and revealing fundamental constraints that voting weight concentration imposes on privacy mechanisms.

cs.CR↗

arXiv2025

Geometric Neural Distance Fields for Learning Human Motion Priors

We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery. Unlike existing VAE or diffusion-based methods, our higher-order motion prior explicitly models the human motion in the zero level set of a collection of neural distance fields (NDFs) corresponding to pose, transition (velocity), and acceleration dynamics. Our framework is rigorous in the sense that our NDFs are constructed on the product space of joint rotations, their angular velocities, and angular accelerations, respecting the geometry of the underlying articulations. We further introduce: (i) a novel adaptive-step hybrid algorithm for projecting onto the set of plausible motions, and (ii) a novel geometric integrator to "roll out" realistic motion trajectories during test-time-optimization and generation. Our experiments show significant and consistent gains: trained on the AMASS dataset, NRMF remarkably generalizes across multiple input modalities and to diverse tasks ranging from denoising to motion in-betweening and fitting to partial 2D / 3D observations.

cs.CV↗

arXiv2020

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings

We introduce a new video synthesis task: synthesizing time lapse videos depicting how a given painting might have been created. Artists paint using unique combinations of brushes, strokes, and colors. There are often many possible ways to create a given painting. Our goal is to learn to capture this rich range of possibilities. Creating distributions of long-term videos is a challenge for learning-based video synthesis methods. We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process. We implement this model as a convolutional neural network, and introduce a novel training scheme to enable learning from a limited dataset of painting time lapses. We demonstrate that this model can be used to sample many time steps, enabling long-term stochastic video synthesis. We evaluate our method on digital and watercolor paintings collected from video websites, and show that human raters find our synthetic videos to be similar to time lapse videos produced by real artists. Our code is available at https://xamyzhao.github.io/timecraft.

cs.GR↗

arXiv2019

Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions

We introduce visual deprojection: the task of recovering an image or video that has been collapsed along a dimension. Projections arise in various contexts, such as long-exposure photography, where a dynamic scene is collapsed in time to produce a motion-blurred image, and corner cameras, where reflected light from a scene is collapsed along a spatial dimension because of an edge occluder to yield a 1D video. Deprojection is ill-posed-- often there are many plausible solutions for a given input. We first propose a probabilistic model capturing the ambiguity of the task. We then present a variational inference strategy using convolutional neural networks as functional approximators. Sampling from the inference network at test time yields plausible candidates from the distribution of original signals that are consistent with a given input projection. We evaluate the method on several datasets for both spatial and temporal deprojection tasks. We first demonstrate the method can recover human gait videos and face images from spatial projections, and then show that it can recover videos of moving digits from dramatically motion-blurred images obtained via temporal projection.

cs.CV↗

arXiv2019

WiFi Motion Detection: A Study into Efficacy and Classification

WiFi and security pose both an issue and act as a growing presence in everyday life. Today's motions detection implementations are severely lacking in the areas of secrecy, scope, and cost. To combat this problem, we aim to develop a motion detection system that utilizes WiFi Channel State Information (CSI), which describes how a wireless signal propagates from the transmitter to the receiver. The goal of this study is to develop a real-time motion detection and classification system that is discreet, cost-effective, and easily implementable. The system would only require an Ubuntu laptop with an Intel Ultimate N WiFi Link 5300 and a standard router. The system will be developed in two parts: (1) a robust system to track CSI variations in real-time, and (2) an algorithm to classify the motion. The system used to track CSI variance in real-time was completed in August 2018. Initial results show that introduction of motion to a previously motionless area is detected with high confidence. We present the development of (1) anomaly detection, utilizing the moving average filter implemented in the initial program and/or unsupervised machine learning, and (2) supervised machine learning algorithms to classify a set of simple motions using a proposed feature extraction methods. Lastly, classification methods such as Decision Tree, Naive Bayes, and Long Short-Term Memory can be used to classify basic actions regardless of speed, location, or orientation.

eess.SP↗

arXiv2019

Data augmentation using learned transformations for one-shot medical image segmentation

Image segmentation is an important task in many medical applications. Methods based on convolutional neural networks attain state-of-the-art accuracy; however, they typically rely on supervised training with large labeled datasets. Labeling medical images requires significant expertise and time, and typical hand-tuned approaches for data augmentation fail to capture the complex variations in such images. We present an automated data augmentation method for synthesizing labeled medical images. We demonstrate our method on the task of segmenting magnetic resonance imaging (MRI) brain scans. Our method requires only a single segmented scan, and leverages other unlabeled scans in a semi-supervised approach. We learn a model of transformations from the images, and use the model along with the labeled example to synthesize additional labeled examples. Each transformation is comprised of a spatial deformation field and an intensity change, enabling the synthesis of complex effects such as variations in anatomy and image acquisition procedures. We show that training a supervised segmenter with these new examples provides significant improvements over state-of-the-art methods for one-shot biomedical image segmentation. Our code is available at https://github.com/xamyzhao/brainstorm.

cs.CV↗

arXiv2018

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets or rich deformation models. In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images. We parameterize the function via a convolutional neural network (CNN), and optimize the parameters of the neural network on a set of images. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. In this work, we explore two different training strategies. In the first (unsupervised) setting, we train the model to maximize standard image matching objective functions that are based on the image intensities. In the second setting, we leverage auxiliary segmentations available in the training data. We demonstrate that the unsupervised model's accuracy is comparable to state-of-the-art methods, while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data improves registration accuracy at test time, and evaluate the effect of training set size on registration. Our method promises to speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is freely available at voxelmorph.csail.mit.edu.

cs.CV↗

arXiv2018

Synthesizing Images of Humans in Unseen Poses

We address the computational problem of novel human pose synthesis. Given an image of a person and a desired pose, we produce a depiction of that person in that pose, retaining the appearance of both the person and background. We present a modular generative neural network that synthesizes unseen poses using training pairs of images and poses taken from human action videos. Our network separates a scene into different body part and background layers, moves body parts to new locations and refines their appearances, and composites the new foreground with a hole-filled background. These subtasks, implemented with separate modules, are trained jointly using only a single target image as a supervised label. We use an adversarial discriminator to force our network to synthesize realistic details conditioned on pose. We demonstrate image synthesis results on three action classes: golf, yoga/workouts and tennis, and show that our method produces accurate results within action classes as well as across action classes. Given a sequence of desired poses, we also produce coherent videos of actions.

cs.CV↗

arXiv2018

An Unsupervised Learning Model for Deformable Medical Image Registration

We present a fast learning-based algorithm for deformable, pairwise 3D medical image registration. Current registration methods optimize an objective function independently for each pair of images, which can be time-consuming for large data. We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest. Given a new pair of scans, we can quickly compute a registration field by directly evaluating the function using the learned parameters. We model this function using a convolutional neural network (CNN), and use a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field. The proposed method does not require supervised information such as ground truth registration fields or anatomical landmarks. We demonstrate registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Our method promises to significantly speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is available at https://github.com/balakg/voxelmorph .

cs.CV↗

arXiv2017

A Video-Based Method for Objectively Rating Ataxia

For many movement disorders, such as Parkinson's disease and ataxia, disease progression is visually assessed by a clinician using a numerical disease rating scale. These tests are subjective, time-consuming, and must be administered by a professional. This can be problematic where specialists are not available, or when a patient is not consistently evaluated by the same clinician. We present an automated method for quantifying the severity of motion impairment in patients with ataxia, using only video recordings. We consider videos of the finger-to-nose test, a common movement task used as part of the assessment of ataxia progression during the course of routine clinical checkups. Our method uses neural network-based pose estimation and optical flow techniques to track the motion of the patient's hand in a video recording. We extract features that describe qualities of the motion such as speed and variation in performance. Using labels provided by an expert clinician, we train a supervised learning model that predicts severity according to the Brief Ataxia Rating Scale (BARS). The performance of our system is comparable to that of a group of ataxia specialists in terms of mean error and correlation, and our system's predictions were consistently within the range of inter-rater variability. This work demonstrates the feasibility of using computer vision and machine learning to produce consistent and clinically useful measures of motor impairment.

cs.CV↗