arXiv subjects

Boyang Zhou

Publications and source records attributed to Boyang Zhou.

9 recordsLinked to original sources

arXiv2026

AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations

Real-time navigation in cluttered and dynamic environments requires collision-free and dynamically feasible motion under limited perception. However, feasible navigation behaviors are inherently multimodal because multiple paths may exist around obstacles. In this paper, we formulate navigation as learning a transferable goal-conditioned stochastic path prior that models a reusable distribution over goal-aligned geometry-consistent local paths conditioned on local observations. This formulation enables structured sampling of navigation candidates, allowing multiple feasible paths to be explored through sampling without relying on robot-specific motion constraints. To this end, we introduce a goal-aligned canonical state representation that removes in-plane rotational ambiguity and normalizes local geometry with respect to the goal, enabling rotation-invariant path distribution learning. We further develop a structured prior learning framework that parameterizes local paths using a geometry-aware polar action manifold and incorporates risk-sensitive utility shaping with multi-goal distributional rollouts for stable and safety-aware planning. Extensive experiments in dense static environments and dynamic pedestrian scenarios demonstrate that the proposed method achieves consistently high success rates with competitive efficiency while enabling cross-platform transfer of a single path prior learned on differential-drive robots to quadruped platforms without retraining.

cs.RO↗

arXiv2026

Learn to Match: Two-Sided Matching with Temporally Extended Feedback

Two-sided matching markets often involve information that unfolds over time through interviews, repeated interaction, learning, and separation. Existing matching models typically reduce this process to immediate sub-Gaussian feedback about fixed preferences, missing settings where payoff-relevant information is revealed gradually and changes future matching decisions. We introduce a framework with temporally extended feedback, that formulates two-sided matching as a partially observable Markov game with costly pre-match screening, noisy post-match observations, evolving latent profiles, and endogenous continuation or dissolution. We instantiate this framework in Learn2Match, a multi-agent reinforcement-learning benchmark for dynamic matching markets. Learn2Match supports decentralized decision making over whom to interview, whom to match with, and when to dissolve a match, while evaluating policies using regret, social welfare, and an information-friction loss that measures the welfare gap caused by incomplete revelation of latent preferences. We find that independent PPO achieves higher cumulative social welfare and lower cumulative regret than the bandit-style CA-ETC baseline under temporally extended feedback, demonstrating the promise of MARL for dynamic matching markets. However, PPO still incurs higher information-friction loss, revealing that end-to-end MARL does not yet provide the coordinated exploration structure of matching-bandit methods. These results position Learn2Match as a benchmark for developing the next generation of matching-market algorithms: methods that are adaptive like RL agents, statistically disciplined like bandit algorithms, and structurally aware like stable-matching mechanisms. Please refer to https://sites.google.com/view/learn-to-match/home for the official website and the code link.

cs.LG↗

arXiv2026

Addressing Negative Commons Governance with Positive Commons Principles

Computing is accompanied by both positive and negative commons throughout its lifecycle of creation, execution, and disposal. We examine two governance systems situated within this lifecycle -- global e-waste trade and the Linux kernel community -- to evaluate whether Elinor Ostrom's eight design principles for common-pool resource (CPR) governance extend to the management of negative common-pool resources (NCPRs). Unlike traditional CPRs where communities work to preserve a finite resource (i.e. clean water), NCPR governance seeks to collectively reduce a negative shared stock. In our two cases, e-waste governance aims to reduce the volume of mismanaged waste and illicit trade, while the Linux community aims to reduce the number of error-prone or malicious contributions that reach the main branch and, in turn, extend the life of existing hardware. Through qualitative analysis of primary sources from each domain, we find that the same eight principles by Ostrom that aid positive commons governance tend to appear in successful negative commons governance systems. We argue that future NCPR governance design should prioritize Ostrom's principles, particularly clearly defined boundaries and well-functioning nested structures.

cs.HC↗

arXiv2026

HeartbeatCam: Self-Triggered Photo Elicitation of Stress Events Using Wearable Sensing

People often recognize what triggered their stress only after the moment has passed. In therapy, this can become a recurring problem: clients are asked to remember what happened between sessions, but the details that matter (where they were, what they saw and heard, what was happening around them) are easy to lose. We introduce HeartbeatCam, a wearable sensing system that gathers contextual information during moments of elevated stress. It uses a consumer smartwatch stress signal to trigger capture from an open-source AR glasses camera, recording a sparse image-audio clip that can later be reviewed and annotated. The system adopts an actionable sensing approach to mental healthcare, using physiological signals along with contextual capture to support collaborative interpretation of stress-triggering moments with mental health professionals.

cs.HC↗

arXiv2026

E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning

Human-in-the-loop guidance has emerged as an effective approach for accelerating online reinforcement learning (RL) in real-world manipulation. However, existing human-in-the-loop RL (HiL-RL) frameworks often suffer from low sample efficiency, requiring substantial human interventions to achieve convergence and thereby leading to high labor costs. To address this, we propose a sample-efficient real-world human-in-the-loop RL framework named E2HiL, which requires fewer human interventions by actively selecting informative samples. Specifically, stable reduction of policy entropy enables improved trade-off between exploration and exploitation with higher sample efficiency. We first build influence functions of different samples on the policy entropy, which is efficiently estimated by the covariance of action probabilities and soft advantages of policies. Then we select samples with moderate values of influence functions, where shortcut samples that induce sharp entropy drops and noisy samples with negligible effect are pruned. Extensive experiments across 10 real-world manipulation tasks, spanning multiple embodiments and learning frameworks, demonstrate that E2HiL improves success rates by 24.9% while reducing human interventions by 9.3% compared to state-of-the-art HiL-RL baselines. These results validate its effectiveness as a policy- and embodiment-agnostic plug-and-play module for efficient real-world RL. The project page can be found at https://e2hil.github.io/.

cs.RO↗

arXiv2025

Reproducibility Report: Test-Time Training on Nearest Neighbors for Large Language Models

We reproduce the central claims of Test-Time Training on Nearest Neighbors for Large Language Models (Hardt and Sun, 2024), which proposes adapting a language model at inference time by fine-tuning on retrieved nearest-neighbor sequences. Using pretrained RoBERTa embeddings indexed with Faiss, we retrieve 20 neighbors per test input and apply one gradient update per neighbor across GPT-2 (117M, 774M), GPT-Neo (1.3B), and R1-Distilled-Qwen2.5-1.5B. Our experiments confirm that test-time training significantly reduces perplexity and bits-per-byte metrics across diverse domains from The Pile, with the largest improvements in structured or specialized datasets such as GitHub and EuroParl. We further validate that models not pretrained on The Pile benefit more from this adaptation than models already trained on similar data, allowing smaller models to approach the performance of larger ones. Due to infrastructure limitations, we introduce a memory-efficient retrieval implementation that loads only required line offsets rather than entire files, reducing RAM requirements from over 128 GB per server to 32 GB. We also extend the original study by evaluating R1-Distilled-Qwen2.5-1.5B, showing that test-time training yields consistent gains even for modern reasoning-optimized architectures. Overall, our results support the robustness and generality of nearest-neighbor test-time training while highlighting practical considerations for reproducing large-scale retrieval-augmented adaptation.

cs.CL↗

arXiv2025

UniTok-Audio: A Unified Audio Generation Framework via Generative Modeling on Discrete Codec Tokens

Generative modeling has recently achieved remarkable success across text, image, and audio domains, demonstrating powerful capabilities for unified representation learning. However, audio generation models still face challenges in terms of audio quality and generalization ability across tasks. This fragmentation results in redundant development efforts, inconsistent performance, and limited extensibility. To address these issues, we propose \textbf{UniTok-Audio}, a scalable and extensible framework for unified audio generation tasks. Specifically, 1) UniTok-Audio extracts continuous feature of conditions to generates discrete tokens of target audio in an autoregressive manner; 2) a special task identifier token unifies different learning patterns of multiple tasks in a single framework; 3) a dual-stream audio codec involving acoustic and semantic branch is developed for high-fidelity waveform reconstruction. Experimental results demonstrate that UniTok-Audio achieves competitive performance in comparation with state-of-the-art task-specific or multi-task systems across five time-aligned tasks: speech restoration, target speaker extraction, speech separation, voice conversion, and language-queried audio source separation. To foster future research, we will open-source our codebase. The demo page of our work can be found here: https://alibaba.github.io/unified-audio.

cs.SD↗

arXiv2024

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from a single input image) for key frame interpolation, i.e., to produce a video in between two input frames. We accomplish this adaptation through a lightweight fine-tuning technique that produces a version of the model that instead predicts videos moving backwards in time from a single input image. This model (along with the original forward-moving model) is subsequently used in a dual-directional diffusion sampling process that combines the overlapping model estimates starting from each of the two keyframes. Our experiments show that our method outperforms both existing diffusion-based methods and traditional frame interpolation techniques.

cs.CV↗

arXiv2023

F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. At present, adversarial training is one of the most effective defenses against adversarial examples. However, traditional adversarial training makes it difficult to achieve a good trade-off between clean accuracy and robustness since spurious features are still learned by DNNs. The intrinsic reason is that traditional adversarial training makes it difficult to fully learn core features from adversarial examples when adversarial noise and clean examples cannot be disentangled. In this paper, we disentangle the adversarial examples into natural and perturbed patterns by bit-plane slicing. We assume the higher bit-planes represent natural patterns and the lower bit-planes represent perturbed patterns, respectively. We propose a Feature-Focusing Adversarial Training (F$^2$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns. The experimental results demonstrated that F$^2$AT outperforms state-of-the-art methods in clean accuracy and adversarial robustness.

cs.CV↗