arXiv subjects

Ran Cheng

Publications and source records attributed to Ran Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2026

The Great March 100: 100 Detail-oriented Tasks for Evaluating Embodied AI Agents

Recently, with the rapid development of robot learning and imitation learning, numerous datasets and methods have emerged. However, these datasets and their task designs often lack systematic consideration and principles. This raises important questions: Do the current datasets and task designs truly advance the capabilities of robotic agents? Do evaluations on a few common tasks accurately reflect the differentiated performance of various methods proposed by different teams and evaluated on different tasks? To address these issues, we introduce the Great March 100 (\textbf{GM-100}) as the first step towards a robot learning Olympics. GM-100 consists of 100 carefully designed tasks that cover a wide range of interactions and long-tail behaviors, aiming to provide a diverse and challenging set of tasks to comprehensively evaluate the capabilities of robotic agents and promote diversity and complexity in robot dataset task designs. These tasks are developed through systematic analysis and expansion of existing task designs, combined with insights from human-object interaction primitives and object affordances. We collect a large amount of trajectory data on different robotic platforms and evaluate several baseline models. Experimental results demonstrate that the GM-100 tasks are 1) feasible to execute and 2) sufficiently challenging to effectively differentiate the performance of current VLA models. Our data and code are available at https://rhos.ai/research/gm-100.

cs.RO↗

arXiv2025

Learning to Evolve for Optimization via Stability-Inducing Neural Unrolling

Evolutionary algorithms serve as a powerful paradigm for tackling optimization challenges, yet their reliance on manually engineered heuristics inherently limits their adaptability across diverse landscapes. However, the transition from the hand-crafted heuristics to data-driven algorithms faces a fundamental dilemma: achieving neural \emph{plasticity} without sacrificing algorithmic stability. Although learned optimizers offer high adaptivity, their unconstrained update rules often result in unstable dynamics and brittle generalization on unseen landscapes. To address this challenge, this paper proposes Learning to Evolve (L2E), a bilevel meta-optimization framework that learns evolutionary search via stability-inducing neural unrolling. First, L2E reformulates population evolution as an unrolled fixed-point iteration via a structured neural operator. In this design, the inner loop imposes a stability-biased update structure, while the outer loop meta-trains the operator to produce effective search trajectories across tasks. Second, to balance global exploration with local refinement, a gradient-derived composite solver adaptively fuses learned evolutionary proposals with proxy numerical guidance in a differentiable manner. Extensive experiments on synthetic benchmarks and real-world control tasks demonstrate that L2E achieves substantial optimization performance, scales to high-dimensional problems, and exhibits robust zero-shot transfer across diverse test distributions.

cs.NE↗

arXiv2025

Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective

In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of Decoupled Knowledge Distillation (DKD), which re-emphasizes the importance of logit knowledge through advanced decoupling and weighting strategies. While DKD marks a significant advancement, its underlying mechanisms merit deeper exploration. As a response, we rethink DKD from a predictive distribution perspective. First, we introduce an enhanced version, the Generalized Decoupled Knowledge Distillation (GDKD) loss, which offers a more versatile method for decoupling logits. Then we pay particular attention to the teacher model's predictive distribution and its impact on the gradients of GDKD loss, uncovering two critical insights often overlooked: (1) the partitioning by the top logit considerably improves the interrelationship of non-top logits, and (2) amplifying the focus on the distillation loss of non-top logits enhances the knowledge extraction among them. Utilizing these insights, we further propose a streamlined GDKD algorithm with an efficient partition strategy to handle the multimodality of teacher models' predictive distribution. Our comprehensive experiments conducted on a variety of benchmarks, including CIFAR-100, ImageNet, Tiny-ImageNet, CUB-200-2011, and Cityscapes, demonstrate GDKD's superior performance over both the original DKD and other leading knowledge distillation methods. The code is available at https://github.com/ZaberKo/GDKD.

cs.LG↗

arXiv2025

High-speed antiferromagnetic domain walls driven by coherent spin waves

The ability to rapidly manipulate domain walls (DWs) in magnetic materials is key to developing novel high-speed spintronic memory and computing devices. Antiferromagnetic (AFM) materials present a particularly promising platform due to their robustness against stray fields and their potential for exceptional DW velocities. Among various proposed driving mechanisms, coherent spin waves could potentially propel AFM DWs to the magnon group velocity while minimizing dissipation from Joule heating. However, experimental realization has remained elusive due to the dual challenges of generating coherent AFM spin waves near isolated mobile AFM DWs and simultaneously measuring high-speed DW dynamics. Here we experimentally realize an approach where ultrafast laser pulses generate coherent spin waves that drive AFM DWs and develop a technique to directly map the spatiotemporal DW dynamics. Using the room-temperature AFM insulator Sr$_2$Cu$_3$O$_4$Cl$_2$, we observe AFM DW motion with record-high velocities up to ~50 km/s. Remarkably, the direction of DW propagation is controllable through both the pump laser helicity and the sign of the DW winding number. This bidirectional control can be theoretically explained, and numerically reproduced, by the DW dynamics induced by coherent spin waves of the in-plane magnon mode - a phenomenon unique to magnets with an easy-plane anisotropy. Our work uncovers a novel DW propulsion mechanism that is generalizable to a wide range of AFM materials, unlocking new opportunities for ultrafast coherent AFM spintronics.

cond-mat.mes-hall↗

arXiv2025

Temporal-Guided Visual Foundation Models for Event-Based Vision

Event cameras offer unique advantages for vision tasks in challenging environments, yet processing asynchronous event streams remains an open challenge. While existing methods rely on specialized architectures or resource-intensive training, the potential of leveraging modern Visual Foundation Models (VFMs) pretrained on image data remains under-explored for event-based vision. To address this, we propose Temporal-Guided VFM (TGVFM), a novel framework that integrates VFMs with our temporal context fusion block seamlessly to bridge this gap. Our temporal block introduces three key components: (1) Long-Range Temporal Attention to model global temporal dependencies, (2) Dual Spatiotemporal Attention for multi-scale frame correlation, and (3) Deep Feature Guidance Mechanism to fuse semantic-temporal features. By retraining event-to-video models on real-world data and leveraging transformer-based VFMs, TGVFM preserves spatiotemporal dynamics while harnessing pretrained representations. Experiments demonstrate SoTA performance across semantic segmentation, depth estimation, and object detection, with improvements of 16%, 21%, and 16% over existing methods, respectively. Overall, this work unlocks the cross-modality potential of image-based VFMs for event-based vision with temporal reasoning. Code is available at https://github.com/XiaRho/TGVFM.

cs.CV↗

arXiv2025

Proper Theory of Magnon Orbital Angular Momentum at Equilibrium

The orbital motion of chargeless bosons, unlike that of electrons, does not generate a magnetic moment and thus cannot directly interact with magnetic fields. To formulate the orbital angular momentum (OAM) of magnons, we first identify its proper conjugate variable by considering the Aharonov-Casher effect, which gives rise to a virtual perturbation to the equilibrium state, allowing us to calculate the magnon OAM as a virtual response to an infinitesimal electric field divergence. At finite temperatures, both self-rotation and topological contributions to the magnon OAM are explicitly derived, analogous to their electronic counterpart but with the correct bosonic statistics. In a two-dimensional honeycomb lattice, we show that the Dzyaloshinskii-Moriya interaction induces a large magnon OAM in both the ferromagnetic and antiferromagnetic phases. Our formalism can be generalized to other chargeless bosons with intrinsic spin.

cond-mat.mes-hall↗

arXiv2025

IntSR: An Integrated Generative Framework for Search and Recommendation

Generative recommendation has emerged as a promising paradigm, demonstrating remarkable results in both academic benchmarks and industrial applications. However, existing systems predominantly focus on unifying retrieval and ranking while neglecting the integration of search and recommendation (S&R) tasks. What makes search and recommendation different is how queries are formed: search uses explicit user requests, while recommendation relies on implicit user interests. As for retrieval versus ranking, the distinction comes down to whether the queries are the target items themselves. Recognizing the query as central element, we propose IntSR, an integrated generative framework for S&R. IntSR integrates these disparate tasks using distinct query modalities. It also addresses the increased computational complexity associated with integrated S&R behaviors and the erroneous pattern learning introduced by a dynamically changing corpus. IntSR has been successfully deployed across various scenarios in Amap, leading to substantial improvements in digital asset's GMV(+9.34%), POI recommendation's CTR(+2.76%), and travel mode suggestion's ACC(+7.04%).

cs.IR↗

arXiv2025

A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving

Large language models (LLMs) are increasingly integrated with evolutionary computation to support optimization tasks. This survey primarily focuses on evolutionary optimization, i.e., optimization based on evolutionary computation. For brevity, we use the term optimization throughout to denote this scope. However, existing surveys typically examine isolated roles of LLMs and do not provide a unified view that connects optimization modeling with optimization solving. To address this gap, we systematically review recent developments through a workflow-oriented framework. First, we organize the literature into two primary stages: LLMs for optimization modeling and LLMs for optimization solving (in this survey, the terms optimization modeling and optimization solving are used as concise forms of optimization problem modeling and optimization problem solving, respectively). Second, we divide the solving stage into three paradigms according to the role of the LLM: stand-alone optimizers, low-level components embedded in optimization algorithms, and high-level managers for algorithm selection and generation. Third, we analyze representative methods, identify their technical limitations, and clarify their relationships with traditional optimization approaches. We further substantiate this taxonomy through benchmark systematization, baseline comparisons, and practitioner-oriented guidance, and we review interdisciplinary applications across the natural sciences, engineering, and machine learning. Based on the resulting analysis, we identify research directions toward dynamic, self-evolving, and agentic optimization ecosystems. An up-to-date collection of related literature is maintained at https://github.com/ishmael233/LLM4OPT.

cs.NE↗

arXiv2025

Evolutionary Generative Optimization: Towards Fully Data-Driven Evolutionary Optimization via Generative Learning

Recent advances in data-driven evolutionary algorithms (EAs) have demonstrated the potential of leveraging historical data to improve optimization accuracy and adaptability. Despite these advancements, existing methods remain reliant on handcrafted process-level operators. In contrast, Evolutionary Generative Optimization (EvoGO) is a fully data-driven framework designed from the objective level, enabling autonomous learning of the entire search process. EvoGO streamlines the evolutionary optimization process into three stages: data preparation, model training, and population generation. The data preparation stage constructs a pairwise dataset to enrich training diversity without incurring additional evaluation costs. During model training, a tailored generative model learns to transform inferior solutions into superior ones. In the population generation stage, EvoGO replaces traditional reproduction operators with a scalable and parallelizable generative mechanism. Extensive experiments on numerical benchmarks, classical control problems, and high-dimensional robotic tasks demonstrate that EvoGO consistently converges within merely 10 generations and substantially outperforms a wide spectrum of optimization approaches, including traditional EAs, Bayesian optimization, and reinforcement learning based methods. Code is available at: https://github.com/EMI-Group/evogo

cs.NE↗

arXiv2025

VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks

Recent advances in reinforcement learning (RL) have led to substantial improvements in the mathematical reasoning abilities of LLMs, as measured by standard benchmarks. Yet these gains often persist even when models are trained with flawed signals, such as random or inverted rewards. This raises a fundamental question: do such improvements reflect genuine reasoning, or are they merely artifacts of overfitting to benchmark-specific patterns? To answer this question, we adopt an evaluation-centric perspective and highlight two critical shortcomings in existing protocols. First, benchmark contamination arises because test problems are publicly available, thereby increasing the risk of data leakage. Second, evaluation fragility results from reliance on single-instance assessments, which are sensitive to stochastic outputs and fail to capture reasoning consistency. These limitations suggest the need for a new evaluation paradigm that can probe reasoning ability beyond memorization and one-off success. As response, we propose VAR-MATH, a symbolic evaluation framework that converts fixed numerical problems into parameterized templates and requires models to solve multiple instantiations of each. This design enforces consistency across structurally equivalent variants, mitigates contamination, and enhances robustness through bootstrapped metrics. We apply VAR-MATH to transform three popular benchmarks, AMC23, AIME24, and AIME25, into their symbolic counterparts, VAR-AMC23, VAR-AIME24, and VAR-AIME25. Experimental results show substantial performance drops for RL-trained models on these variabilized benchmarks, especially for smaller models, with average declines of 47.9\% on AMC23, 58.8\% on AIME24, and 72.9\% on AIME25. These findings indicate that some existing RL methods rely on superficial heuristics and fail to generalize beyond specific numerical forms.

cs.AI↗

arXiv2025

Giant Response and Harmonic Generation in N\'eel-Torque Antiferromagnetic Resonance

We theoretically investigate the resonant and higher order magnetic responses of a collinear antiferromagnet induced by N\'eel spin-orbit torques (NSOTs). By deriving the dynamical susceptibilities up to the third harmonic, we find remarkable NSOT-induced amplifications of the linear and nonlinear magnetic dynamics by orders of magnitude compared to conventional spin-orbit torques, enabling highly-efficient frequency conversion in the terahertz frequency range. From the effective dynamics, we uncover the strong coupling between the N\'eel vector and the driving field of NSOTs, providing a physical explanation of the gigantic responses at all orders. We then propose a multilayer antiferromagnetic nano-device leveraging the gigantic harmonic generation to achieve unprecedented frequency amplifiers and converters. Our work uncovers a previously overlooked role of the NSOTs in nonlinear dynamics.

cond-mat.mes-hall↗

arXiv2025

Characterizing Spin-Orbit Torques by Tensorial Spin Hall Magnetoresistance

Magnetoresistance (MR) provides a crucial tool for experimentally studying spin torques. While MR is well established in the device geometry of the spin Hall effect (SHE), as exemplified by the magnet/heavy-metal heterostructures, its role and manifestation beyond the SHE paradigm remain elusive. We propose a hitherto unknown form of MR where the underlying charge-to-spin conversion and its inverse process violate the simple geometry of the SHE, calling for tensorial descriptions. This MR can generate a series of unique harmonic responses essential for the experimental characterization of unconventional spin-orbit torques in non-SHE materials. We demonstrate these harmonic signals with semimetal WTe$_2$ in mind but the results are not restricted to specific materials.

cond-mat.mes-hall↗

arXiv2025

EvoGit: Decentralized Code Evolution via Git-Based Multi-Agent Collaboration

We introduce EvoGit, a decentralized multi-agent framework for collaborative software development driven by autonomous code evolution. EvoGit deploys a population of independent coding agents, each proposing edits to a shared codebase without centralized coordination, explicit message passing, or shared memory. Instead, all coordination emerges through a Git-based phylogenetic graph that tracks the full version lineage and enables agents to asynchronously read from and write to the evolving code repository. This graph-based structure supports fine-grained branching, implicit concurrency, and scalable agent interaction while preserving a consistent historical record. Human involvement is minimal but strategic: users define high-level goals, periodically review the graph, and provide lightweight feedback to promote promising directions or prune unproductive ones. Experiments demonstrate EvoGit's ability to autonomously produce functional and modular software artifacts across two real-world tasks: (1) building a web application from scratch using modern frameworks, and (2) constructing a meta-level system that evolves its own language-model-guided solver for the bin-packing optimization problem. Our results underscore EvoGit's potential to establish a new paradigm for decentralized, automated, and continual software development. EvoGit is open-sourced at https://github.com/BillHuang2001/evogit.

cs.DC↗

arXiv2025

Diversity-Aware Policy Optimization for Large Language Model Reasoning

The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek R1, which has inspired a surge of research into data quality and reinforcement learning (RL) algorithms. Despite the pivotal role diversity plays in RL, its influence on LLM reasoning remains largely underexplored. To bridge this gap, this work presents a systematic investigation into the impact of diversity in RL-based training for LLM reasoning, and proposes a novel diversity-aware policy optimization method. Across evaluations on 12 LLMs, we observe a strong positive correlation between the solution diversity and Potential at k (a novel metric quantifying an LLM's reasoning potential) in high-performing models. This finding motivates our method to explicitly promote diversity during RL training. Specifically, we design a token-level diversity and reformulate it into a practical objective, then we selectively apply it to positive samples. Integrated into the R1-zero training framework, our method achieves a 3.5 percent average improvement across four mathematical reasoning benchmarks, while generating more diverse and robust solutions.

cs.LG↗

arXiv2025

Disorder-Induced Suppression of Antiferromagnetic Magnon Transport in Cr2O3

We explore the impact of spin disorder associated with structural defects on antiferromagnetic magnon transport by probing the spin-flop transition of Cr2O3 using spin Seebeck effect measurements. By fabricating homoepitaxial Cr2O3 films grown on smooth Cr2O3 crystals, we systematically vary the thickness of the films in which the presence of point defects modulates the spin-flop transition field. We find that magnon propagation through the film is entirely suppressed for film thickness greater than 3 nm, revealing the pivotal role of disorder in governing antiferromagnetic magnon transport.

cond-mat.mtrl-sci↗

arXiv2025

MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization

Meta-Black-Box Optimization (MetaBBO) streamlines the automation of optimization algorithm design through meta-learning. It typically employs a bi-level structure: the meta-level policy undergoes meta-training to reduce the manual effort required in developing algorithms for low-level optimization tasks. The original MetaBox (2023) provided the first open-source framework for reinforcement learning-based single-objective MetaBBO. However, its relatively narrow scope no longer keep pace with the swift advancement in this field. In this paper, we introduce MetaBox-v2 (https://github.com/MetaEvo/MetaBox) as a milestone upgrade with four novel features: 1) a unified architecture supporting RL, evolutionary, and gradient-based approaches, by which we reproduce $23$ up-to-date baselines; 2) efficient parallelization schemes, which reduce the training/testing time by $10-40$x; 3) a comprehensive benchmark suite of $18$ synthetic/realistic tasks ($1900$+ instances) spanning single-objective, multi-objective, multi-model, and multi-task optimization scenarios; 4) plentiful and extensible interfaces for custom analysis/visualization and integrating to external optimization tools/benchmarks. To show the utility of MetaBox-v2, we carry out a systematic case study that evaluates the built-in baselines in terms of the optimization performance, generalization ability and learning efficiency. Valuable insights are concluded from thorough and detailed analysis for practitioners and those new to the field.

cs.LG↗

arXiv2025

Emerging (2+1)D electrodynamics and topological instanton in pseudo-Hermitian two-level systems

We reveal a hidden electrodynamical structure emerging from a general $2\times2$ pseudo-Hermitian system that exhibits real spectra. Even when the Hamiltonian does not explicitly depend on time, the Berry curvature can be mapped onto a $2+1$ dimensional electromagnetic field arising from an artificial spacetime instanton, in sharp contrast to the Hermitian systems where the Berry curvature is equivalent to the static magnetic field of a magnetic monopole in three spatial dimensions. The instanton appearing as a spacetime singularity carries a topological charge that quantizes the jump of magnetic flux of the Berry curvature at the time origin. Our findings are demonstrated in a simple example related to antiferromagnetic magnons.

cond-mat.mes-hall↗

arXiv2025

TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies

The NeuroEvolution of Augmenting Topologies (NEAT) algorithm has received considerable recognition in the field of neuroevolution. Its effectiveness is derived from initiating with simple networks and incrementally evolving both their topologies and weights. Although its capability across various challenges is evident, the algorithm's computational efficiency remains an impediment, limiting its scalability potential. To address these limitations, this paper introduces TensorNEAT, a GPU-accelerated library that applies tensorization to the NEAT algorithm. Tensorization reformulates NEAT's diverse network topologies and operations into uniformly shaped tensors, enabling efficient parallel execution across entire populations. TensorNEAT is built upon JAX, leveraging automatic function vectorization and hardware acceleration to significantly enhance computational efficiency. In addition to NEAT, the library supports variants such as CPPN and HyperNEAT, and integrates with benchmark environments like Gym, Brax, and gymnax. Experimental evaluations across various robotic control environments in Brax demonstrate that TensorNEAT delivers up to 500x speedups compared to existing implementations, such as NEAT-Python. The source code for TensorNEAT is publicly available at: https://github.com/EMI-Group/tensorneat.

cs.NE↗