arXiv subjects

Hang Yu

Publications and source records attributed to Hang Yu.

At least 73 records · Page 4Linked to original sources

arXiv2026

A Problem-Oriented Perspective and Anchor Verification for Code Optimization

Large Language Models (LLMs) have shown remarkable capabilities in solving various programming tasks, such as code generation. However, their potential for code optimization, particularly in performance enhancement, remains largely unexplored. This paper investigates the capabilities of LLMs in optimizing code for minimal execution time, addressing a critical gap in current research. The recently proposed code optimization methods construct program optimization pairs based on iterative submissions from the same programmer for the same problem. However, this approach confines LLMs to local performance improvements, neglecting global algorithmic innovation. To overcome this limitation, we adopt a completely different perspective by reconstructing the optimization pairs into a problem-oriented approach. This allows for the integration of various ideas from multiple programmers tackling the same problem. Furthermore, we observe that code optimization presents greater challenges compared to code generation, often accompanied by "optimization tax". Recognizing the inherent trade-offs in correctness and efficiency, we introduce a novel anchor verification framework to mitigate this "optimization tax". Ultimately, the problem oriented perspective combined with the anchor verification framework significantly enhances both the correct optimization ratio and speedup to new levels.

cs.PL↗

arXiv2026

Impact on Inferred Neutron Star Equation of State due to Nonlinear Hydrodynamics, Background Spin, and Relativity

Tidal interaction is a unique, detectable signature in gravitational wave signals from inspiraling binary neutron stars (BNSs), which can be used to constrain the neutron star (NS) equation of state (EoS). The tidal interaction is resonantly amplified as the orbital frequency approaches the NS fundamental mode (f-mode) frequency. It has been shown that the exclusion of tidal resonance in parameter estimation leads to a significant bias in the inferred NS tidal deformability and hence the NS EoS [Pratten et al. PRL 129, 081102 (2022)]. The strength and location of tidal resonance depend sensitively on the f-mode frequency, which is typically modeled using its universal relation with the tidal deformability that is derived for an isolated, non-spinning NS assuming only linear fluid perturbations. In a BNS inspiral, the f-mode frequency can be corrected by at least three known effects: nonlinear hydrodynamics, background spin, and relativity. We use Hamiltonian Monte Carlo simulations to estimate the systematic bias on tidal deformability when each frequency correction is ignored. Our study considers both loud, individual events and the stacking of a population of detections. Both scenarios are expected when the next-generation detectors are available with a sensitivity level increased by about an order of magnitude.

gr-qc↗

arXiv2026

Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation

Real-world robotic manipulation demands visuomotor policies capable of robust spatial scene understanding and strong generalization across diverse camera viewpoints. While recent advances in 3D-aware visual representations have shown promise, they still suffer from several key limitations, including reliance on multi-view observations during inference which is impractical in single-view restricted scenarios, incomplete scene modeling that fails to capture holistic and fine-grained geometric structures essential for precise manipulation, and lack of effective policy training strategies to retain and exploit the acquired 3D knowledge. To address these challenges, we present MethodName, a unified representation-policy learning framework for view-generalizable robotic manipulation. MethodName introduces a single-view 3D pretraining paradigm that leverages point cloud reconstruction and feed-forward gaussian splatting under multi-view supervision to learn holistic geometric representations. During policy learning, MethodName performs multi-step distillation to preserve the pretrained geometric understanding and effectively transfer it to manipulation skills. We conduct experiments on 12 RLBench tasks, where our approach outperforms the previous state-of-the-art method by 12.7% in average success rate. Further evaluation on six representative tasks demonstrates strong zero-shot view generalization, with success rate drops of only 22.0% and 29.7% under moderate and large viewpoint shifts respectively, whereas the state-of-the-art method suffers larger decreases of 41.6% and 51.5%.

cs.RO↗

arXiv2026

Dynamical tide modified Roche limit in eccentric, asynchronous binaries

The Roche limit, or the threshold separation within which a celestial object (the donor) M cannot remain in a stable configuration due to a companion's tidal field, has been well established when M is in hydrostatic equilibrium and has synchronous rotation in a circular orbit. However, limited analyses exist considering corrections to the Roche limit due to hydrodynamical effects. We fill in the gap by providing a general theoretical framework involving nonlinear hydrodynamics. We consider both exact nonlinear equations derived from an affine model describing incompressible ellipsoids and series-expanded ones that can be calculated for realistic stars and planets. Our formulation addresses the Roche problem in generic orbits and synchronization levels of M, and fully accounts for the history-dependent hydrodynamical effects. We show that as the orbital eccentricity increases, fluid instability is more likely to develop at the pericenter due to the increased dynamical tide that accumulates over multiple orbits. When M moves in a highly eccentric orbit (with eccentricity around 0.9) and the damping of the fluid is small, the threshold pericenter separation at which mass loss from M can occur can be at least 30% higher than the value predicted for a circular orbit with hydrostatic equilibrium. If only a single passage is considered, however, the threshold separation is 20% smaller than the static limit. The nonlinear interaction at each pericenter passage can also trigger a chaotic fluid evolution inside M even with moderate eccentricities, complementing previous studies of chaotic tides caused by random propagation phases. Our work has broad implications for interacting binaries in eccentric orbits, including migrating gaseous exoplanets, repeated partial tidal disruption events, and more.

astro-ph.EP↗

arXiv2025

How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots

Enhancing the expressiveness of human teaching is vital for both improving robots' learning from humans and the human-teaching-robot experience. In this work, we characterize and test a little-used teaching signal: \textit{progress}, designed to represent the completion percentage of a task. We conducted two online studies with 76 crowd-sourced participants and one public space study with 40 non-expert participants to validate the capability of this progress signal. We find that progress indicates whether the task is successfully performed, reflects the degree of task completion, identifies unproductive but harmless behaviors, and is likely to be more consistent across participants. Furthermore, our results show that giving progress does not require extra workload and time. An additional contribution of our work is a dataset of 40 non-expert demonstrations from the public space study through an ice cream topping-adding task, which we observe to be multi-policy and sub-optimal, with sub-optimality not only from teleoperation errors but also from exploratory actions and attempts. The dataset is available at https://github.com/TeachingwithProgress/Non-Expert\_Demonstrations.

cs.RO↗

arXiv2025

CHARM: Considering Human Attributes for Reinforcement Modeling

Reinforcement Learning from Human Feedback has recently achieved significant success in various fields, and its performance is highly related to feedback quality. While much prior work acknowledged that human teachers' characteristics would affect human feedback patterns, there is little work that has closely investigated the actual effects. In this work, we designed an exploratory study investigating how human feedback patterns are associated with human characteristics. We conducted a public space study with two long horizon tasks and 46 participants. We found that feedback patterns are not only correlated with task statistics, such as rewards, but also correlated with participants' characteristics, especially robot experience and educational background. Additionally, we demonstrated that human feedback value can be more accurately predicted with human characteristics compared to only using task statistics. All human feedback and characteristics we collected, and codes for our data collection and predicting more accurate human feedback are available at https://github.com/AABL-Lab/CHARM

cs.RO↗

arXiv2025

C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling

We present C2LLM - Contrastive Code Large Language Models, a family of code embedding models in both 0.5B and 7B sizes. Building upon Qwen-2.5-Coder backbones, C2LLM adopts a Pooling by Multihead Attention (PMA) module for generating sequence embedding from token embeddings, effectively 1) utilizing the LLM's causal representations acquired during pretraining, while also 2) being able to aggregate information from all tokens in the sequence, breaking the information bottleneck in EOS-based sequence embeddings, and 3) supporting flexible adaptation of embedding dimension, serving as an alternative to MRL. Trained on three million publicly available data, C2LLM models set new records on MTEB-Code among models of similar sizes, with C2LLM-7B ranking 1st on the overall leaderboard.

cs.CL↗

arXiv2025

Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations

Learning from Demonstration (LfD) is a popular approach for robots to acquire new skills, but most LfD methods suffer from imperfections in human demonstrations. Prior work typically treats these suboptimalities as random noise. In this paper we study non-optimal behaviors in non-expert demonstrations and show that they are systematic, forming what we call demonstration sidetracks. Using a public space study with 40 participants performing a long-horizon robot task, we recreated the setup in simulation and annotated all demonstrations. We identify four types of sidetracks (Exploration, Mistake, Alignment, Pause) and one control pattern (one-dimension control). Sidetracks appear frequently across participants, and their temporal and spatial distribution is tied to task context. We also find that users' control patterns depend on the control interface. These insights point to the need for better models of suboptimal demonstrations to improve LfD algorithms and bridge the gap between lab training and real-world deployment. All demonstrations, infrastructure, and annotations are available at https://github.com/AABL-Lab/Human-Demonstration-Sidetracks.

cs.RO↗

arXiv2025

Aligning Academia with Industry: An Empirical Study of Industrial Needs and Academic Capabilities in AI-Driven Software Engineering

The rapid advancement of large language models (LLMs) is fundamentally reshaping software engineering (SE), driving a paradigm shift in both academic research and industrial practice. While top-tier SE venues continue to show sustained or emerging focus on areas like automated testing and program repair, with researchers worldwide reporting continuous performance gains, the alignment of these academic advances with real industrial needs remains unclear. To bridge this gap, we first conduct a systematic analysis of 1,367 papers published in FSE, ASE, and ICSE between 2022 and 2025, identifying key research topics, commonly used benchmarks, industrial relevance, and open-source availability. We then carry out an empirical survey across 17 organizations, collecting 282 responses on six prominent topics, i.e., program analysis, automated testing, code generation/completion, issue resolution, pre-trained code models, and dependency management, through structured questionnaires. By contrasting academic capabilities with industrial feedback, we derive seven critical implications, highlighting under-addressed challenges in software requirements and architecture, the reliability and explainability of intelligent SE approaches, input assumptions in academic research, practical evaluation tensions, and ethical considerations. This study aims to refocus academic attention on these important yet under-explored problems and to guide future SE research toward greater industrial impact.

cs.SE↗

arXiv2025

ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts

Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories present challenges for reward propagation, resulting in inaccurate value estimation and degraded policy performance. While trajectory stitching via generative models offers a promising solution, existing augmentation methods frequently produce trajectories that are either confined to the support of the behavior policy or violate the underlying dynamics, thereby limiting their effectiveness for policy improvement. We propose ASTRO, a data augmentation framework that generates distributionally novel and dynamics-consistent trajectories for offline RL. ASTRO first learns a temporal-distance representation to identify distinct and reachable stitch targets. We then employ a dynamics-guided stitch planner that adaptively generates connecting action sequences via Rollout Deviation Feedback, defined as the gap between target state sequence and the actual arrived state sequence by executing predicted actions, to improve trajectory stitching's feasibility and reachability. This approach facilitates effective augmentation through stitching and ultimately enhances policy learning. ASTRO outperforms prior offline RL augmentation methods across various algorithms, achieving notable performance gain on the challenging OGBench suite and demonstrating consistent improvements on standard offline RL benchmarks such as D4RL.

cs.LG↗

arXiv2025

Local Well-Posedness of the Motion of Inviscid Liquid Crystals with a Free Surface Boundary

In this article, we prove the local well-posedness of the free-boundary Lin-Liu equations describing the motion of inviscid nematic liquid crystals in the presence of surface tension in Lagrangian coordinates. It is well known that a priori energy estimates alone are insufficient for establishing local existence in free-boundary problems involving inviscid fluid equations, primarily due to the loss of symmetry in the linearized equations. The main challenge is to develop an effective approximate system of equations that is asymptotically consistent with the free-boundary Lin-Liu model expressed in the Lagrangian coordinates. This system must accurately capture the coupling between the fluid motion and the harmonic heat flows within the interior, as well as the regularity of the moving boundary.

math.AP↗

arXiv2025

From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement Learning

Learning from human feedback is an effective way to improve robotic learning in exploration-heavy tasks. Compared to the wide application of binary human feedback, scalar human feedback has been used less because it is believed to be noisy and unstable. In this paper, we compare scalar and binary feedback, and demonstrate that scalar feedback benefits learning when properly handled. We collected binary or scalar feedback respectively from two groups of crowdworkers on a robot task. We found that when considering how consistently a participant labeled the same data, scalar feedback led to less consistency than binary feedback; however, the difference vanishes if small mismatches are allowed. Additionally, scalar and binary feedback show no significant differences in their correlations with key Reinforcement Learning targets. We then introduce Stabilizing TEacher Assessment DYnamics (STEADY) to improve learning from scalar feedback. Based on the idea that scalar feedback is muti-distributional, STEADY re-constructs underlying positive and negative feedback distributions and re-scales scalar feedback based on feedback statistics. We show that models trained with \textit{scalar feedback + STEADY } outperform baselines, including binary feedback and raw scalar feedback, in a robot reaching task with non-expert human feedback. Our results show that both binary feedback and scalar feedback are dynamic, and scalar feedback is a promising signal for use in interactive Reinforcement Learning.

cs.RO↗

arXiv2025

See What I Mean? Expressiveness and Clarity in Robot Display Design

Nonverbal visual symbols and displays play an important role in communication when humans and robots work collaboratively. However, few studies have investigated how different types of non-verbal cues affect objective task performance, especially in a dynamic environment that requires real time decision-making. In this work, we designed a collaborative navigation task where the user and the robot only had partial information about the map on each end and thus the users were forced to communicate with a robot to complete the task. We conducted our study in a public space and recruited 37 participants who randomly passed by our setup. Each participant collaborated with a robot utilizing either animated anthropomorphic eyes and animated icons, or static anthropomorphic eyes and static icons. We found that participants that interacted with a robot with animated displays reported the greatest level of trust and satisfaction; that participants interpreted static icons the best; and that participants with a robot with static eyes had the highest completion success. These results suggest that while animation can foster trust with robots, human-robot communication can be optimized by the addition of familiar static icons that may be easier for users to interpret. We published our code, designed symbols, and collected results online at: https://github.com/mattufts/huamn_Cozmo_interaction.

cs.RO↗

arXiv2025

WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization

Visual geo-localization for drones faces critical degradation under weather perturbations, \eg, rain and fog, where existing methods struggle with two inherent limitations: 1) Heavy reliance on limited weather categories that constrain generalization, and 2) Suboptimal disentanglement of entangled scene-weather features through pseudo weather categories. We present WeatherPrompt, a multi-modality learning paradigm that establishes weather-invariant representations through fusing the image embedding with the text context. Our framework introduces two key contributions: First, a Training-free Weather Reasoning mechanism that employs off-the-shelf large multi-modality models to synthesize multi-weather textual descriptions through human-like reasoning. It improves the scalability to unseen or complex weather, and could reflect different weather strength. Second, to better disentangle the scene and weather feature, we propose a multi-modality framework with the dynamic gating mechanism driven by the text embedding to adaptively reweight and fuse visual features across modalities. The framework is further optimized by the cross-modal objectives, including image-text contrastive learning and image-text matching, which maps the same scene with different weather conditions closer in the respresentation space. Extensive experiments validate that, under diverse weather conditions, our method achieves competitive recall rates compared to state-of-the-art drone geo-localization methods. Notably, it improves Recall@1 by +13.37\% under night conditions and by 18.69\% under fog and snow conditions.

cs.CV↗

arXiv2025

Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation

Generating realistic hand-object interactions (HOI) videos is a significant challenge due to the difficulty of modeling physical constraints (e.g., contact and occlusion between hands and manipulated objects). Current methods utilize HOI representation as an auxiliary generative objective to guide video synthesis. However, there is a dilemma between 2D and 3D representations that cannot simultaneously guarantee scalability and interaction fidelity. To address this limitation, we propose a structure and contact-aware representation that captures hand-object contact, hand-object occlusion, and holistic structure context without 3D annotations. This interaction-oriented and scalable supervision signal enables the model to learn fine-grained interaction physics and generalize to open-world scenarios. To fully exploit the proposed representation, we introduce a joint-generation paradigm with a share-and-specialization strategy that generates interaction-oriented representations and videos. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on two real-world datasets in generating physics-realistic and temporally coherent HOI videos. Furthermore, our approach exhibits strong generalization to challenging open-world scenarios, highlighting the benefit of our scalable design. Our project page is https://hgzn258.github.io/SCAR/.

cs.CV↗

arXiv2025

Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization

Universal online learning aims to achieve optimal regret guarantees without requiring prior knowledge of the curvature of online functions. Existing methods have established minimax-optimal regret bounds for universal online learning, where a single algorithm can simultaneously attain $\mathcal{O}(\sqrt{T})$ regret for convex functions, $\mathcal{O}(d \log T)$ for exp-concave functions, and $\mathcal{O}(\log T)$ for strongly convex functions, where $T$ is the number of rounds and $d$ is the dimension of the feasible domain. However, these methods still lack problem-dependent adaptivity. In particular, no universal method provides regret bounds that scale with the gradient variation $V_T$, a key quantity that plays a crucial role in applications such as stochastic optimization and fast-rate convergence in games. In this work, we introduce UniGrad, a novel approach that achieves both universality and adaptivity, with two distinct realizations: UniGrad.Correct and UniGrad.Bregman. Both methods achieve universal regret guarantees that adapt to gradient variation, simultaneously attaining $\mathcal{O}(\log V_T)$ regret for strongly convex functions and $\mathcal{O}(d \log V_T)$ regret for exp-concave functions. For convex functions, the regret bounds differ: UniGrad.Correct achieves an $\mathcal{O}(\sqrt{V_T \log V_T})$ bound while preserving the RVU property that is crucial for fast convergence in online games, whereas UniGrad.Bregman achieves the optimal $\mathcal{O}(\sqrt{V_T})$ regret bound through a novel design. Both methods employ a meta algorithm with $\mathcal{O}(\log T)$ base learners, which naturally requires $\mathcal{O}(\log T)$ gradient queries per round. To enhance computational efficiency, we introduce UniGrad++, which retains the regret while reducing the gradient query to just $1$ per round via surrogate optimization. We further provide various implications.

cs.LG↗

arXiv2025

InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection

Sarcasm in social media, frequently conveyed through the interplay of text and images, presents significant challenges for sentiment analysis and intention mining. Existing multi-modal sarcasm detection approaches have been shown to excessively depend on superficial cues within the textual modality, exhibiting limited capability to accurately discern sarcasm through subtle text-image interactions. To address this limitation, a novel framework, InterCLIP-MEP, is proposed. This framework integrates Interactive CLIP (InterCLIP), which employs an efficient training strategy to derive enriched cross-modal representations by embedding inter-modal information directly into each encoder, while using approximately 20.6$\times$ fewer trainable parameters compared with existing state-of-the-art (SOTA) methods. Furthermore, a Memory-Enhanced Predictor (MEP) is introduced, featuring a dynamic dual-channel memory mechanism that captures and retains valuable knowledge from test samples during inference, serving as a non-parametric classifier to enhance sarcasm detection robustness. Extensive experiments on MMSD, MMSD2.0, and DocMSU show that InterCLIP-MEP achieves SOTA performance, specifically improving accuracy by 1.08% and F1 score by 1.51% on MMSD2.0. Under distributional shift evaluation, it attains 73.96% accuracy, exceeding its memory-free variant by nearly 10% and the previous SOTA by over 15%, demonstrating superior stability and adaptability. The implementation of InterCLIP-MEP is publicly available at https://github.com/CoderChen01/InterCLIP-MEP.

cs.CL↗

arXiv2025

CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

Automated code review (CR) is a key application for Large Language Models (LLMs), but progress is hampered by a "reality gap": existing benchmarks evaluate models on isolated sub-tasks using simplified, context-poor data. This fails to reflect the holistic context-rich nature of real-world CR. To bridge this gap, we introduce CodeFuse-CR-Bench, the first comprehensiveness-aware benchmark for repository-level CR evaluation. CodeFuse-CR-Bench comprises 601 high-quality instances from 70 Python projects covering nine Pull-Request (PR) problem domains, where each instance provides rich, multi-faceted context including the associated issue, PR details, and repository state, enabling end-to-end evaluation. Beyond superficial metrics, we also propose a novel evaluation framework that combines rule-based checks for location and syntax with model-based judgments of review quality. We present the first large-scale assessment of state-of-the-art LLMs on this comprehensive CR task. Our results establish crucial baselines and reveal that (1) no single LLM dominates all aspects of CR; (2) Gemini 2.5 Pro achieves the highest comprehensive performance; and (3) different LLMs exhibit varying robustness to redundant context. These findings highlight the necessity of holistic, multi-dimensional evaluation and provide actionable insights for advancing truly intelligent yet practical CR assistants.

cs.SE↗