arXiv subjects

Haoran Lu

Publications and source records attributed to Haoran Lu.

At least 37 records · Page 2Linked to original sources

arXiv2026

PROGRESSLM: Towards Progress Reasoning in Vision-Language Models

Estimating task progress requires reasoning over long-horizon dynamics rather than recognizing static visual content. While modern Vision-Language Models (VLMs) excel at describing what is visible, it remains unclear whether they can infer how far a task has progressed from partial observations. To this end, we introduce Progress-Bench, a benchmark for systematically evaluating progress reasoning in VLMs. Beyond benchmarking, we further explore a human-inspired two-stage progress reasoning paradigm through both training-free prompting and training-based approach based on curated dataset ProgressLM-45K. Experiments on 14 VLMs show that most models are not yet ready for task progress estimation, exhibiting sensitivity to demonstration modality and viewpoint changes, as well as poor handling of unanswerable cases. While training-free prompting that enforces structured progress reasoning yields limited and model-dependent gains, the training-based ProgressLM-3B achieves consistent improvements even at a small model scale, despite being trained on a task set fully disjoint from the evaluation tasks. Further analyses reveal characteristic error patterns and clarify when and why progress reasoning succeeds or fails. Website: https://progresslm.github.io/ProgressLM/

cs.CV↗

arXiv2026

NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning

Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agents as nodes and intermediate textual signals as edges. In NeuroMAS, agent nodes are role-free but structure-aware: the topology only determines how information can flow in general, while reinforcement learning training determines how nodes communicate, specialize, and coordinate. This formulation shifts multi-agent design from workflow engineering toward architecture design, where depth, width, connectivity, and growth protocol become scalable sources of capability. Further, we provide a theoretical perspective showing why such modular textual computation is more parameter-efficient when tasks admit hierarchical decompositions. Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems. These results suggest that learned neural multi-agent systems are a promising scaling axis for LLMs.

cs.AI↗

arXiv2026

3D Printing of Passively Actuated Self-Folding Robots with Integrated Functional Modules

We introduce an elastic-driven self-folding approach that fabricates robots directly from flat 3D-printed conductive PLA nets. Elastic bands routed through printed hooks store energy that folds the sheet into programmed 3D geometries, while the flat state allows accurate placement of electronics and magnets before deployment. The same substrate doubles as electrodes for capacitive touch and supports a reusable platform I/O palette with Hall sensors and eccentric rotating mass (ERM) motors for docking detection and vibration actuation. We also derive a closed-form folding model that balances hinge stiffness with elastic band moment to predict equilibrium fold angles; experiments validate the model and yield a design map linking hinge thickness, band size, and hook spacing to target angles. Using this workflow we realize multiple polyhedral modules and demonstrate three applications: a cube that highlights the potential of self-folding for scalable modular robot collectives, a deployable gripper, and a tendon-driven finger. The method is low cost, stimulus-free, and integrates actuation and sensing.

cs.RO↗

arXiv2026

GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning

Garment manipulation has attracted increasing attention due to its critical role in home-assistant robotics. However, the majority of existing garment manipulation works assume an initial state consisting of only one garment, while piled garments are far more common in real-world settings. To bridge this gap, we propose a novel garment retrieval pipeline that can not only follow language instruction to execute safe and clean retrieval but also guarantee exactly one garment is retrieved per attempt, establishing a robust foundation for the execution of downstream tasks (e.g., folding, hanging, wearing). Our pipeline seamlessly integrates vision-language reasoning with visual affordance perception, fully leveraging the high-level reasoning and planning capabilities of VLMs alongside the generalization power of visual affordance for low-level actions. To enhance the VLM's comprehensive awareness of each garment's state within a garment pile, we employ visual segmentation model (SAM2) to execute object segmentation on the garment pile for aiding VLM-based reasoning with sufficient visual cues. A mask fine-tuning mechanism is further integrated to address scenarios where the initial segmentation results are suboptimal. In addition, a dual-arm cooperation framework is deployed to address cases involving large or long garments, as well as excessive garment sagging caused by incorrect grasping point determination, both of which are strenuous for a single arm to handle. The effectiveness of our pipeline are consistently demonstrated across diverse tasks and varying scenarios in both real-world and simulation environments. Project page: https://garmentpile2.github.io/.

cs.RO↗

arXiv2026

Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulation

Articulated object manipulation is essential for various real-world robotic tasks, yet generalizing across diverse objects remains a major challenge. A key to generalization lies in understanding functional parts (e.g., door handles and knobs), which indicate where and how to manipulate across diverse object categories and shapes. Previous works attempted to achieve generalization by introducing foundation features, while these features are mostly 2D-based and do not specifically consider functional parts. When lifting these 2D features to geometry-profound 3D space, challenges arise, such as long runtimes, multi-view inconsistencies, and low spatial resolution with insufficient geometric information. To address these issues, we propose Part-Aware 3D Feature Field (PA3FF), a novel dense 3D feature with part awareness for generalizable articulated object manipulation. PA3FF is trained by 3D part proposals from a large-scale labeled dataset, via a contrastive learning formulation. Given point clouds as input, PA3FF predicts a continuous 3D feature field in a feedforward manner, where the distance between point features reflects the proximity of functional parts: points with similar features are more likely to belong to the same part. Building on this feature, we introduce the Part-Aware Diffusion Policy (PADP), an imitation learning framework aimed at enhancing sample efficiency and generalization for robotic manipulation. We evaluate PADP on several simulated and real-world tasks, demonstrating that PA3FF consistently outperforms a range of 2D and 3D representations in manipulation scenarios, including CLIP, DINOv2, and Grounded-SAM. Beyond imitation learning, PA3FF enables diverse downstream methods, including correspondence learning and segmentation tasks, making it a versatile foundation for robotic manipulation. Project page: https://pa3ff.github.io

cs.RO↗

arXiv2026

Krypton-sputtered tantalum films for scalable high-performance quantum devices

Superconducting qubits based on tantalum (Ta) thin films have demonstrated the highest-performing microwave resonators and qubits. This makes Ta an attractive material for superconducting quantum computing applications, but, so far, direct deposition has largely relied on high substrate temperatures exceeding \SI{400}{\celsius} to achieve the body-centered cubic phase, BCC (\textalpha-Ta). This leads to compatibility issues for scalable fabrication leveraging standard semiconductor fabrication lines. Here, we show that changing the sputter gas from argon (Ar) to krypton (Kr) promotes BCC Ta synthesis on silicon (Si) at temperatures as low as \SI{200}{\celsius}, providing a wide process window compatible with back-end-of-the-line fabrication standards. Furthermore, we find these films to have substantially higher electronic conductivity, consistent with clean-limit superconductivity. We validated the microwave performance through coplanar waveguide resonator measurements, finding that films deposited at \SI{250}{\celsius} and \SI{350}{\celsius} exhibit a tight performance distribution at the state of the art. Higher temperature-grown films exhibit higher losses, in correlation with the degree of Ta/Si intermixing revealed by cross-sectional transmission electron microscopy. Finally, with these films, we demonstrate transmon qubits with a relatively compact, \SI{20}{\micro\meter} capacitor gap, achieving a median quality factor up to 14 million.

quant-ph↗

arXiv2026

Low-loss Nb on Si superconducting resonators from a dual-use spintronics deposition chamber and with acid-free post-processing

Magnetic impurities are known to degrade superconductivity. For this reason, physical vapor deposition chambers that have previously been used for magnetic materials have generally been avoided for making high-quality superconducting resonator devices. In this article, we show by example that such chambers can be used for this purpose; with Nb films sputtered in a chamber that continues to be used for magnetic materials, we demonstrate compact (\SI{3}{\micro\meter} gap) coplanar waveguide resonators with low-power internal quality factors near one million. We achieve this using a resist strip bath with no post-fabrication acid treatment, which results in performance comparable to previous strip baths with acid treatments. We also find evidence that this improved resist strip bath provides a better surface chemical template for post-fabrication hydrogen fluoride processing. These results are consistent across three Si substrate preparation methods, including a \SI{700}{\celsius} anneal. These results will inform nanofabrication for other superconducting materials and the integration of magnetic materials for hybrid systems.

quant-ph↗

arXiv2026

Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions

The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary paradigms: Knowledge Distillation (KD) and Dataset Distillation (DD), both aimed at compressing LLMs while preserving their advanced reasoning capabilities and linguistic diversity. We first examine key methodologies in KD, such as task-specific alignment, rationale-based training, and multi-teacher frameworks, alongside DD techniques that synthesize compact, high-impact datasets through optimization-based gradient matching, latent space regularization, and generative synthesis. Building on these foundations, we explore how integrating KD and DD can produce more effective and scalable compression strategies. Together, these approaches address persistent challenges in model scalability, architectural heterogeneity, and the preservation of emergent LLM abilities. We further highlight applications across domains such as healthcare and education, where distillation enables efficient deployment without sacrificing performance. Despite substantial progress, open challenges remain in preserving emergent reasoning and linguistic diversity, enabling efficient adaptation to continually evolving teacher models and datasets, and establishing comprehensive evaluation protocols. By synthesizing methodological innovations, theoretical foundations, and practical insights, our survey charts a path toward sustainable, resource-efficient LLMs through the tighter integration of KD and DD principles.

cs.CL↗

arXiv2025

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and adversarial collaboration. Existing defenses fall into two lines: (i) self-verification that asks each agent to pre-filter unsafe instructions before execution, and (ii) external guard modules that police behaviors. The former often underperforms because a standalone agent lacks sufficient capacity to detect cross-agent unsafe chains and delegation-induced risks; the latter increases system overhead and creates a single-point-of-failure-once compromised, system-wide safety collapses, and adding more guards worsens cost and complexity. To solve these challenges, we propose AdvEvo-MARL, a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents. Rather than relying on external guards, AdvEvo-MARL jointly optimizes attackers (which synthesize evolving jailbreak prompts) and defenders (task agents trained to both accomplish their duties and resist attacks) in adversarial learning environments. To stabilize learning and foster cooperation, we introduce a public baseline for advantage estimation: agents within the same functional group share a group-level mean-return baseline, enabling lower-variance updates and stronger intra-group coordination. Across representative attack scenarios, AdvEvo-MARL consistently keeps attack-success rate (ASR) below 20%, whereas baselines reach up to 38.33%, while preserving-and sometimes improving-task accuracy (up to +3.67% on reasoning tasks). These results show that safety and utility can be jointly improved without relying on extra guard agents or added system overhead.

cs.AI↗

arXiv2025

FairReason: Balancing Reasoning and Social Bias in MLLMs

Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studies explore advanced prompting schemes and post-training fine-tuning. Although these techniques improve logical accuracy, they frequently leave the models' outputs burdened with pronounced social biases. Clarifying how reasoning gains interact with bias mitigation-and whether the two objectives inherently trade off-therefore remains an open and pressing research problem. Our study begins by benchmarking three bias-mitigation strategies-supervised fine-uning (SFT), knowledge distillation (KD), and rule-based reinforcement learning (RL)-under identical conditions, establishing their baseline strengths and weaknesses. Building on these results, we vary the proportion of debias-focused and reasoning-centric samples within each paradigm to chart the reasoning-versus-bias trade-off. Our sweeps reveal a consistent sweet spot: a roughly 1:4 mix trained with reinforcement learning cuts stereotype scores by 10% while retaining 88% of the model's original reasoning accuracy, offering concrete guidance for balancing fairness and capability in MLLMs.

cs.AI↗

arXiv2025

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical challenge. This survey provides a comprehensive overview of practical alignment techniques, training protocols, and empirical findings in LLM alignment. We analyze the development of alignment methods across diverse paradigms, characterizing the fundamental trade-offs between core alignment objectives. Our analysis shows that while supervised fine-tuning enables basic instruction-following, preference-based methods offer more flexibility for aligning with nuanced human intent. We discuss state-of-the-art techniques, including Direct Preference Optimization (DPO), Constitutional AI, brain-inspired methods, and alignment uncertainty quantification (AUQ), highlighting their approaches to balancing quality and efficiency. We review existing evaluation frameworks and benchmarking datasets, emphasizing limitations such as reward misspecification, distributional robustness, and scalable oversight. We summarize strategies adopted by leading AI labs to illustrate the current state of practice. We conclude by outlining open problems in oversight, value pluralism, robustness, and continuous alignment. This survey aims to inform both researchers and practitioners navigating the evolving landscape of LLM alignment.

cs.AI↗

arXiv2025

BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly

Shape assembly, the process of combining parts into a complete whole, is a crucial robotic skill with broad real-world applications. Among various assembly tasks, geometric assembly--where broken parts are reassembled into their original form (e.g., reconstructing a shattered bowl)--is particularly challenging. This requires the robot to recognize geometric cues for grasping, assembly, and subsequent bimanual collaborative manipulation on varied fragments. In this paper, we exploit the geometric generalization of point-level affordance, learning affordance aware of bimanual collaboration in geometric assembly with long-horizon action sequences. To address the evaluation ambiguity caused by geometry diversity of broken parts, we introduce a real-world benchmark featuring geometric variety and global reproducibility. Extensive experiments demonstrate the superiority of our approach over both previous affordance-based and imitation-based methods. Project page: https://sites.google.com/view/biassembly/.

cs.RO↗

arXiv2025

A Systematic Approach for Multi-objective Double-side Clock Tree Synthesis

As the scaling of semiconductor devices nears its limits, utilizing the back-side space of silicon has emerged as a new trend for future integrated circuits. With intense interest, several works have hacked existing backend tools to explore the potential of synthesizing double-side clock trees via nano Through-Silicon-Vias (nTSVs). However, these works lack a systematic perspective on design resource allocation and multi-objective optimization. We propose a systematic approach to design clock trees with double-side metal layers, including hierarchical clock routing, concurrent buffers and nTSVs insertion, and skew refinement. Compared with the state-of-the-art (SOTA) methods, the widely-used open-source tool, our algorithm outperforms them in latency, skew, wirelength, and the number of buffers and nTSVs.

cs.AR↗

arXiv2025

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Data scaling and standardized evaluation benchmarks have driven significant advances in natural language processing and computer vision. However, robotics faces unique challenges in scaling data and establishing evaluation protocols. Collecting real-world data is resource-intensive and inefficient, while benchmarking in real-world scenarios remains highly complex. Synthetic data and simulation offer promising alternatives, yet existing efforts often fall short in data quality, diversity, and benchmark standardization. To address these challenges, we introduce RoboVerse, a comprehensive framework comprising a simulation platform, a synthetic dataset, and unified benchmarks. Our simulation platform supports multiple simulators and robotic embodiments, enabling seamless transitions between different environments. The synthetic dataset, featuring high-fidelity physics and photorealistic rendering, is constructed through multiple approaches. Additionally, we propose unified benchmarks for imitation learning and reinforcement learning, enabling evaluation across different levels of generalization. At the core of the simulation platform is MetaSim, an infrastructure that abstracts diverse simulation environments into a universal interface. It restructures existing simulation environments into a simulator-agnostic configuration system, as well as an API aligning different simulator functionalities, such as launching simulation environments, loading assets with initial states, stepping the physics engine, etc. This abstraction ensures interoperability and extensibility. Comprehensive experiments demonstrate that RoboVerse enhances the performance of imitation learning, reinforcement learning, world model learning, and sim-to-real transfer. These results validate the reliability of our dataset and benchmarks, establishing RoboVerse as a robust solution for advancing robot learning.

cs.RO↗

arXiv2025

Design Optimization of Flip FET Standard Cells with Dual-sided Pins for Ultimate Scaling

Recently, we proposed a novel transistor architecture for 3D stacked FETs called Flip FET (FFET), featuring N/P transistors back-to-back stacked and dual-sided interconnects. With dual-sided power rails and signal tracks, FFET can achieve an aggressive 2.5T cell height. As a tradeoff, the complex structure and limited numbers of M0 tracks could limit the standard cell design. As a solution, multiple innovations were introduced and examined in this work. Based on an advanced node design rule, several unique building blocks in FFET such as drain merge (DM), gate merge (GM), field drain merge (FDM) and buried signal track (BST) were investigated. Other key design concepts of multi-row, split gate and dummy gate insertion (DG) were also carefully studied, delivering around 35.6% area reduction compared with 3T CFET. Furthermore, the symmetric design of FFET has unique superiority over CFET thanks to the separate N/P logic on two sides of the wafer and their connections using DM and GM. New routing scheme with dual-sided output pins on both wafer frontside (FS) and backside (BS) was proposed for the first time. Finally, we conducted a comprehensive evaluation on complex cell design, taking AOI22 as an example. New strategies were proposed and examined. The FDM design is identified as the best, outperforming the BST and dummy gate design by 1.93% and 5.13% for the transition delay.

cond-mat.mes-hall↗

arXiv2025

Efficient Multi-Task Inferencing: Model Merging with Gromov-Wasserstein Feature Alignment

Automatic scoring of student responses enhances efficiency in education, but deploying a separate neural network for each task increases storage demands, maintenance efforts, and redundant computations. To address these challenges, this paper introduces the Gromov-Wasserstein Scoring Model Merging (GW-SMM) method, which merges models based on feature distribution similarities measured via the Gromov-Wasserstein distance. Our approach begins by extracting features from student responses using individual models, capturing both item-specific context and unique learned representations. The Gromov-Wasserstein distance then quantifies the similarity between these feature distributions, identifying the most compatible models for merging. Models exhibiting the smallest pairwise distances, typically in pairs or trios, are merged by combining only the shared layers preceding the classification head. This strategy results in a unified feature extractor while preserving separate classification heads for item-specific scoring. We validated our approach against human expert knowledge and a GPT-o1-based merging method. GW-SMM consistently outperformed both, achieving a higher micro F1 score, macro F1 score, exact match accuracy, and per-label accuracy. The improvements in micro F1 and per-label accuracy were statistically significant compared to GPT-o1-based merging (p=0.04, p=0.01). Additionally, GW-SMM reduced storage requirements by half without compromising much accuracy, demonstrating its computational efficiency alongside reliable scoring performance.

cs.CL↗

arXiv2025

Kramers-protected hardware-efficient error correction with Andreev spin qubits

We propose an architecture for bit-flip error correction of Andreev spins that is protected by Kramers' degeneracy. Specifically, we show that a coupling network of linear inductors and Andreev spin qubits results in a static Hamiltonian composed of the stabilizers of a bit-flip code. The electrodynamics of the many-body spin states also respect these stabilizers, and we show how reflectometry off a single coupled resonator can thereby accomplish their projective measurement. We further show how circuit-mediated spin couplings enable error correction operations and a complete set of single- and two-module logical quantum gates. The concept, which we dub the Ising molecule qubit (or Isene), is experimentally feasible and provides a path for compact noise-biased qubits.

quant-ph↗

arXiv2025

Overlay-aware Variation Study of Flip FET and Benchmark with CFET

In this work, we carried out an overlay-aware variation study on Flip FET (FFET) considering the impact on RC parasitics induced by the lithography misalignment in backside processes, and benchmarked it with CFET in terms of the power-performance (PP) and variation sources. The iso-leakage frequency degrades up to 2.20% with layout misalignment of 4 nm. It's found that the Drain Merge resistance degrades significantly with misalignment increasing and is identified as the major variation source. Through careful DTCO with design rule optimization, the variation can be greatly suppressed, while the resistance fluctuation of the DM also drops substantially. Monte Carlo random experiments were also conducted, validating the variation reduction. Comparing with the CFET featuring self-aligned gate and much less overlay induced misalignment, fortunately, FFET's PP is still better except when misalignment reaches 8 nm, which is out of spec and nearly impossible. Considering the variabilities induced by the high aspect ratio processes, CFET still faces big challenges compared with FFET.

cond-mat.mes-hall↗