arXiv subjects

Yifei Zhou

Publications and source records attributed to Yifei Zhou.

At least 19 recordsLinked to original sources

arXiv2026

Joint angle based learning to refine kinematic human pose estimation

Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human poses. The performance of existing deep learning-based models for HPE refinement is considerably limited by inaccurate training datasets in which the keypoints are manually annotated. This paper proposed a novel method to overcome the difficulty, in which the key techniques include: (i) A robust joint angle-based description of kinematic human poses; (ii) Approximating temporal variation of joint angles using high order Fourier series to get reliable "ground truth"; (iii) A bidirectional recurrent network is designed as a post-processing module to refine the estimation of single image-based HPE models. Trained with the high-quality dataset constructed using our method, the network demonstrates outstanding performance to correct wrongly recognized joints and smooth their spatiotemporal trajectories. Tests show that joint angle-based refinement (JAR) outperforms the state-of-the-art HPE refinement network in challenging cases like figure skating and breaking. JAR also demonstrates great potential to rectify existing datasets.

cs.CV↗

arXiv2026

PEMark: Watermarking API Responses Based on Proxy Gateways and Position Encoding

Data leakage from API responses has drawn wide attention. APIs are often not fully regulated, making them easy to abuse. One common solution is to embed watermarks into API responses for traceability. However, existing watermarking methods often require modifying database content or API response data. This forces changes to business system code, and may even disrupt normal business operations because data values are altered. In this paper, we propose an original pluggable watermarking scheme based on a watermark proxy gateway and PEMark (Position Encoding-based Watermarking). The key novelty of our approach is exploiting the inherent permutation redundancy in the ordering of JSON/XML key-value pairs -- an overlooked dimension that carries no semantic information yet provides abundant encoding capacity. First, we forward server responses to the watermark proxy gateway, a design that requires zero modification to existing business systems. Then, we embed a watermark into each API response using position encoding, which reorders keys without altering any data values. To the best of our knowledge, this is the first work to achieve distortion-free API response watermarking via position encoding over a proxy gateway. Our method does not modify any data values, so normal business operations continue seamlessly after watermark embedding. Experimental results show that our framework maintains business usability while ensuring that returned API data is traceable. Compared with current mainstream schemes, our method is robust against tampering and insertion attacks (100\% similarity), and can withstand certain levels of deletion attacks.

cs.CR↗

arXiv2026

Towards Generalizable Robotic Data Flywheel: High-Dimensional Factorization and Composition

The lack of sufficiently diverse data, coupled with limited data efficiency, remains a major bottleneck for generalist robotic models, yet systematic strategies for collecting and curating such data are not fully explored. Task diversity arises from implicit factors that are sparsely distributed across multiple dimensions and are difficult to define explicitly. To address this challenge, we propose F-ACIL, a heuristic factor-aware compositional iterative learning framework that enables structured data factorization and promotes compositional generalization. F-ACIL decomposes the data distribution into structured factor spaces such as object, action, and environment. Based on the factorized formulation, we develop a factor-wise data collection and an iterative training paradigm that promotes compositional generalization over the high-dimensional factor space, leading to more effective utilization of real-world robotic demonstrations. With extensive real-world experiments, we show that F-ACIL can achieve more than 45% performance gains with 5-10$\times$ fewer demonstrations comparing to that of which without the strategy. The results suggest that structured factorization offers a practical pathway toward efficient compositional generalization in real-world robotic learning. We believe F-ACIL can inspire more systematic research on building generalizable robotic data flywheel strategies. More demonstrations can be found at: https://f-acil.github.io/

cs.RO↗

arXiv2026

GR-Dexter Technical Report

Vision-language-action (VLA) models have enabled language-conditioned, long-horizon robot manipulation, but most existing systems are limited to grippers. Scaling VLA policies to bimanual robots with high degree-of-freedom (DoF) dexterous hands remains challenging due to the expanded action space, frequent hand-object occlusions, and the cost of collecting real-robot data. We present GR-Dexter, a holistic hardware-model-data framework for VLA-based generalist manipulation on a bimanual dexterous-hand robot. Our approach combines the design of a compact 21-DoF robotic hand, an intuitive bimanual teleoperation system for real-robot data collection, and a training recipe that leverages teleoperated robot trajectories together with large-scale vision-language and carefully curated cross-embodiment datasets. Across real-world evaluations spanning long-horizon everyday manipulation and generalizable pick-and-place, GR-Dexter achieves strong in-domain performance and improved robustness to unseen objects and unseen instructions. We hope GR-Dexter serves as a practical step toward generalist dexterous-hand robotic manipulation.

cs.RO↗

arXiv2025

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic Agent Leaderboard (HAL) to address these challenges. We make three main contributions. First, we provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of VMs, reducing evaluation time from weeks to hours while eliminating common implementation bugs. Second, we conduct three-dimensional analysis spanning models, scaffolds, and benchmarks. We validate the harness by conducting 21,730 agent rollouts across 9 models and 9 benchmarks in coding, web navigation, science, and customer service with a total cost of about $40,000. Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs. Third, we use LLM-aided log inspection to uncover previously unreported behaviors, such as searching for the benchmark on HuggingFace instead of solving a task, or misusing credit cards in flight booking tasks. We share all agent logs, comprising 2.5B tokens of language model calls, to incentivize further research into agent behavior. By standardizing how the field evaluates agents and addressing common pitfalls in agent evaluation, we hope to shift the focus from agents that ace benchmarks to agents that work reliably in the real world.

cs.AI↗

arXiv2025

Learning Adaptive Parallel Reasoning with Language Models

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs, leading to increased latency and exhausted context windows, while parallel methods such as self-consistency suffer from insufficient coordination, resulting in redundant computations and limited performance gains. To address these shortcomings, we propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end. APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations. A key innovation is our end-to-end reinforcement learning strategy, optimizing both parent and child inference threads to enhance task success rate without requiring predefined reasoning structures. Experiments on the Countdown reasoning task demonstrate significant benefits of APR: (1) higher performance within the same context window (83.4% vs. 60.0% at 4k context); (2) superior scalability with increased computation (80.1% vs. 66.6% at 20k total tokens); (3) improved accuracy at equivalent latency (75.2% vs. 57.3% at approximately 5,000ms). APR represents a step towards enabling language models to autonomously optimize their reasoning processes through adaptive allocation of computation.

cs.AI↗

arXiv2025

FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorization

Neuro-symbolic artificial intelligence (neuro-symbolic AI) excels in logical analysis and reasoning. Hyperdimensional Computing (HDC), a promising brain-inspired computational model, is integral to neuro-symbolic AI. Various HDC models have been proposed to represent class-instance and class-class relations, but when representing the more complex class-subclass relation, where multiple objects associate different levels of classes and subclasses, they face challenges for factorization, a crucial task for neuro-symbolic AI systems. In this article, we propose FactorHD, a novel HDC model capable of representing and factorizing the complex class-subclass relation efficiently. FactorHD features a symbolic encoding method that embeds an extra memorization clause, preserving more information for multiple objects. In addition, it employs an efficient factorization algorithm that selectively eliminates redundant classes by identifying the memorization clause of the target class. Such model significantly enhances computing efficiency and accuracy in representing and factorizing multiple objects with class-subclass relation, overcoming limitations of existing HDC models such as "superposition catastrophe" and "the problem of 2". Evaluations show that FactorHD achieves approximately 5667x speedup at a representation size of 10^9 compared to existing HDC models. When integrated with the ResNet-18 neural network, FactorHD achieves 92.48% factorization accuracy on the Cifar-10 dataset.

cs.SC↗

arXiv2025

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction

The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this can be done by generating thinking traces before acting in the world. However, this process does not allow agents to acquire new information from the environment or adapt their behavior over time. In this work, we propose to scale test-time interaction, an untapped dimension of test-time scaling that increases the agent's interaction horizon to enable running rich behaviors such as exploration, backtracking, and dynamic re-planning within a single rollout. To demonstrate the promise of this scaling dimension, we study the domain of web agents. We first show that even prompting-based interaction scaling without any training can improve task success on web benchmarks non-trivially. Building on this, we introduce TTI (Test-Time Interaction), a curriculum-based online reinforcement learning (RL) approach that trains agents by adaptively adjusting their rollout lengths. Using a Gemma 3 12B model, TTI produces state-of-the-art open-source, open-data web agents on WebVoyager and WebArena benchmarks. We further show that TTI enables agents to balance exploration and exploitation adaptively. Our results establish interaction scaling as a powerful, complementary axis to scaling per-step compute, offering new avenues for training adaptive agents.

cs.LG↗

arXiv2025

Self-Challenging Language Model Agents

Large language models are quickly becoming the foundation for intelligent agents that are capable of using tools. However, training such agents is challenging because it requires human creation and annotation of a diverse set of tasks, tools, and evaluation criteria. In this paper, we propose the Self-Challenging framework for training an agent on high-quality tasks that are generated by itself. The agent first plays the role of challenger and generates a task after interacting with the given tools. The tasks take the form of a novel general class of problems termed Code-as-Task, which are defined by an instruction, a verification function and solution and failure cases which serve as tests, allowing to filter only for high-quality tasks. The agent then takes an executor role and trains on those tasks with reinforcement learning using the evaluation feedback as a reward. Evaluation on two existing multi-turn tool-use agent benchmarks, M3ToolEval and TauBench, shows the Self-Challenging framework achieves over a two-fold improvement in Llama-3.1-8B-Instruct, despite using only self-generated training data.

cs.AI↗

arXiv2025

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs and it remains unclear how to develop such algorithms. To study this, we first introduce a new benchmark, ColBench, where an LLM agent interacts with a human collaborator over multiple turns to solve realistic tasks in backend programming and frontend design. Building on this benchmark, we propose a novel RL algorithm, SWEET-RL (RL with Step-WisE Evaluation from Training-time information), that uses a carefully designed optimization objective to train a critic model with access to additional training-time information. The critic provides step-level rewards for improving the policy model. Our experiments demonstrate that SWEET-RL achieves a 6% absolute improvement in success and win rates on ColBench compared to other state-of-the-art multi-turn RL algorithms, enabling Llama-3.1-8B to match or exceed the performance of GPT4-o in realistic collaborative content creation.

cs.LG↗

arXiv2025

Digi-Q: Learning Q-Value Functions for Training Device-Control Agents

While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments (e.g., mobile device control). On-policy reinforcement learning (RL) should address these limitations, but collecting actual rollouts in an environment is often undesirable in truly open-ended agentic problems such as mobile device control or interacting with humans, where each unit of interaction is associated with a cost. In such scenarios, a method for policy learning that can utilize off-policy experience by learning a trained action-value function is much more effective. In this paper, we develop an approach, called Digi-Q, to train VLM-based action-value Q-functions which are then used to extract the agent policy. We study our approach in the mobile device control setting. Digi-Q trains the Q-function using offline temporal-difference (TD) learning, on top of frozen, intermediate-layer features of a VLM. Compared to fine-tuning the whole VLM, this approach saves us compute and enhances scalability. To make the VLM features amenable for representing the Q-function, we need to employ an initial phase of fine-tuning to amplify coverage over actionable information needed for value function. Once trained, we use this Q-function via a Best-of-N policy extraction operator that imitates the best action out of multiple candidate actions from the current policy as ranked by the value function, enabling policy improvement without environment interaction. Digi-Q outperforms several prior methods on user-scale device control tasks in Android-in-the-Wild, attaining 21.2% improvement over prior best-performing method. In some cases, our Digi-Q approach already matches state-of-the-art RL methods that require interaction. The project is open-sourced at https://github.com/DigiRL-agent/digiq

cs.LG↗

arXiv2025

TReCiM: Lower Power and Temperature-Resilient Multibit 2FeFET-1T Compute-in-Memory Design

Compute-in-memory (CiM) emerges as a promising solution to solve hardware challenges in artificial intelligence (AI) and the Internet of Things (IoT), particularly addressing the "memory wall" issue. By utilizing nonvolatile memory (NVM) devices in a crossbar structure, CiM efficiently accelerates multiply-accumulate (MAC) computations, the crucial operations in neural networks and other AI models. Among various NVM devices, Ferroelectric FET (FeFET) is particularly appealing for ultra-low-power CiM arrays due to its CMOS compatibility, voltage-driven write/read mechanisms and high ION/IOFF ratio. Moreover, subthreshold-operated FeFETs, which operate at scaling voltages in the subthreshold region, can further minimize the power consumption of CiM array. However, subthreshold-FeFETs are susceptible to temperature drift, resulting in computation accuracy degradation. Existing solutions exhibit weak temperature resilience at larger array size and only support 1-bit. In this paper, we propose TReCiM, an ultra-low-power temperature-resilient multibit 2FeFET-1T CiM design that reliably performs MAC operations in the subthreshold-FeFET region with temperature ranging from 0 to 85 degrees Celcius at scale. We benchmark our design using NeuroSim framework in the context of VGG-8 neural network architecture running the CIFAR-10 dataset. Benchmarking results suggest that when considering temperature drift impact, our proposed TReCiM array achieves 91.31% accuracy, with 1.86% accuracy improvement compared to existing 1-bit 2T-1FeFET CiM array. Furthermore, our proposed design achieves 48.03 TOPS/W energy efficiency at system level, comparable to existing designs with smaller technology feature sizes.

cs.ET↗

arXiv2024

Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation models. Such a generalist agent needs to have a large and diverse skill repertoire, such as finding directions between two travel locations and buying specific items from the Internet. If each skill needs to be specified manually through a fixed set of human-annotated instructions, the agent's skill repertoire will necessarily be limited due to the quantity and diversity of human-annotated instructions. In this work, we address this challenge by proposing Proposer-Agent-Evaluator, an effective learning system that enables foundation model agents to autonomously discover and practice skills in the wild. At the heart of PAE is a context-aware task proposer that autonomously proposes tasks for the agent to practice with context information of the environment such as user demos or even just the name of the website itself for Internet-browsing agents. Then, the agent policy attempts those tasks with thoughts and actual grounded operations in the real world with resulting trajectories evaluated by an autonomous VLM-based success evaluator. The success evaluation serves as the reward signal for the agent to refine its policies through RL. We validate PAE on challenging vision-based web navigation, using both real-world and self-hosted websites from WebVoyager and WebArena.To the best of our knowledge, this work represents the first effective learning system to apply autonomous task proposal with RL for agents that generalizes real-world human-annotated benchmarks with SOTA performances. Our open-source checkpoints and code can be found in https://yanqval.github.io/PAE/

cs.LG↗

arXiv2024

Aligning Large Language Models with Representation Editing: A Control Perspective

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time alignment techniques, such as prompting and guided decoding, do not modify the underlying model, and their performance remains dependent on the original model's capabilities. To address these challenges, we propose aligning LLMs through representation editing. The core of our method is to view a pre-trained autoregressive LLM as a discrete-time stochastic dynamical system. To achieve alignment for specific objectives, we introduce external control signals into the state space of this language dynamical system. We train a value function directly on the hidden states according to the Bellman equation, enabling gradient-based optimization to obtain the optimal control signals at test time. Our experiments demonstrate that our method outperforms existing test-time alignment techniques while requiring significantly fewer resources compared to fine-tuning methods. Our code is available at https://github.com/Lingkai-Kong/RE-Control.

cs.AI↗

arXiv2024

Autonomous Evaluation and Refinement of Digital Agents

We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control. We experiment with multiple evaluation models that trade off between inference cost, modularity of design, and accuracy. We validate the performance of these models in several popular benchmarks for digital agents, finding between 74.4 and 92.9% agreement with oracle evaluation metrics. Finally, we use these evaluators to improve the performance of existing agents via fine-tuning and inference-time guidance. Without any additional supervision, we improve state-of-the-art performance by 29% on the popular benchmark WebArena, and achieve around 75% relative improvement in device control settings.

cs.AI↗

arXiv2024

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to efficiently learn optimal decision-making agents in multi-step goal-directed tasks from interactive environments. To address this challenge, we propose an algorithmic framework that fine-tunes VLMs with reinforcement learning (RL). Specifically, our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning, enabling the VLM to efficiently explore intermediate reasoning steps that lead to the final text-based action. Next, the open-ended text output is parsed into an executable action to interact with the environment to obtain goal-directed task rewards. Finally, our framework uses these task rewards to fine-tune the entire VLM with RL. Empirically, we demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks, enabling 7b models to outperform commercial models such as GPT4-V or Gemini. Furthermore, we find that CoT reasoning is a crucial component for performance improvement, as removing the CoT reasoning results in a significant decrease in the overall performance of our method.

cs.AI↗

arXiv2024

KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data

Building generalist robotic systems involves effectively endowing robots with the capabilities to handle novel objects in an open-world setting. Inspired by the advances of large pre-trained models, we propose Keypoint Affordance Learning from Imagined Environments (KALIE), which adapts pre-trained Vision Language Models (VLMs) for robotic control in a scalable manner. Instead of directly producing motor commands, KALIE controls the robot by predicting point-based affordance representations based on natural language instructions and visual observations of the scene. The VLM is trained on 2D images with affordances labeled by humans, bypassing the need for training data collected on robotic systems. Through an affordance-aware data synthesis pipeline, KALIE automatically creates massive high-quality training data based on limited example data manually collected by humans. We demonstrate that KALIE can learn to robustly solve new manipulation tasks with unseen objects given only 50 example data points. Compared to baselines using pre-trained VLMs, our approach consistently achieves superior performance.

cs.RO↗

arXiv2024

Enhancing Representation Learning of EEG Data with Masked Autoencoders

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal representation. Our MAE includes an encoder and a decoder. A certain proportion of input EEG signals are randomly masked and sent to our MAE. The goal is to recover these masked signals. After this self-supervised pre-training, the encoder is fine-tuned on downstream tasks. We evaluate our MAE on EEGEyeNet gaze estimation task. We find that the MAE is an effective brain signal learner. It also significantly improves learning efficiency. Compared to the model without MAE pre-training, the pre-trained one achieves equal performance with 1/3 the time of training and outperforms it in half the training time. Our study shows that self-supervised learning is a promising research direction for EEG-based applications as other fields (natural language processing, computer vision, robotics, etc.), and thus we expect foundation models to be successful in EEG domain.

cs.HC↗