Search arXiv⌕ Search

arXiv subjects

Yuhao Li

Publications and source records attributed to Yuhao Li.

At least 55 records · Page 3Linked to original sources
arXiv2025

Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer

Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic selection. Our architecture led to victory in the 2024 RoboCup SPL Challenge Shield Division. In this work, we fully describe our system's architecture and empirically analyze key design decisions that contributed to its success. Our approach demonstrates how RL-based behaviors can be integrated into complete robot behavior architectures.

cs.RO↗
arXiv2025

C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation

Trajectory-based motion control has emerged as an intuitive and efficient approach for controllable video generation. However, the existing trajectory-based approaches are usually limited to only generating the motion trajectory of the controlled object and ignoring the dynamic interactions between the controlled object and its surroundings. To address this limitation, we propose a Chain-of-Thought-based motion controller for controllable video generation, named C-Drag. Instead of directly generating the motion of some objects, our C-Drag first performs object perception and then reasons the dynamic interactions between different objects according to the given motion control of the objects. Specifically, our method includes an object perception module and a Chain-of-Thought-based motion reasoning module. The object perception module employs visual language models to capture the position and category information of various objects within the image. The Chain-of-Thought-based motion reasoning module takes this information as input and conducts a stage-wise reasoning process to generate motion trajectories for each of the affected objects, which are subsequently fed to the diffusion model for video synthesis. Furthermore, we introduce a new video object interaction (VOI) dataset to evaluate the generation quality of motion controlled video generation methods. Our VOI dataset contains three typical types of interactions and provides the motion trajectories of objects that can be used for accurate performance evaluation. Experimental results show that C-Drag achieves promising performance across multiple metrics, excelling in object motion control. Our benchmark, codes, and models will be available at https://github.com/WesLee88524/C-Drag-Official-Repo.

cs.CV↗
arXiv2025

MiniMax-01: Scaling Foundation Models with Lightning Attention

We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer contexts. The core lies in lightning attention and its efficient scaling. To maximize computational capacity, we integrate it with Mixture of Experts (MoE), creating a model with 32 experts and 456 billion total parameters, of which 45.9 billion are activated for each token. We develop an optimized parallel strategy and highly efficient computation-communication overlap techniques for MoE and lightning attention. This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens. The context window of MiniMax-Text-01 can reach up to 1 million tokens during training and extrapolate to 4 million tokens during inference at an affordable cost. Our vision-language model, MiniMax-VL-01 is built through continued training with 512 billion vision-language tokens. Experiments on both standard and in-house benchmarks show that our models match the performance of state-of-the-art models like GPT-4o and Claude-3.5-Sonnet while offering 20-32 times longer context window. We publicly release MiniMax-01 at https://github.com/MiniMax-AI.

cs.CL↗
arXiv2025

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs

Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse set of challenges with eight different categories ranging from complex visual perception to scientific reasoning with over 4k reasoning steps in total, enabling robust evaluation of LLMs' abilities to perform accurate and interpretable visual reasoning across multiple steps. Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps, emphasizing both correctness and logical coherence. The proposed metric offers deeper insights into reasoning performance compared to traditional end-task accuracy metrics. Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach, where tasks are progressively organized to facilitate incremental skill acquisition and problem-solving. The proposed LlamaV-o1 is designed for multi-step reasoning and learns step-by-step through a structured training paradigm. Extensive experiments show that our LlamaV-o1 outperforms existing open-source models and performs favorably against close-source proprietary models. Compared to the recent Llava-CoT, our LlamaV-o1 achieves an average score of 67.3 with an absolute gain of 3.8\% across six benchmarks while being 5 times faster during inference scaling. Our benchmark, model, and code are publicly available.

cs.CV↗
arXiv2024

Unusual topological polar texture in moiré ferroelectrics

Topological polar textures in ferroelectrics have attracted significant interest for their potential for energy-efficient and high-density data storage and processing. Among these, polar merons and antimerons are predicted in strained and twisted bilayers of inversion symmetry broken systems. However, experimental observation of these polar textures within twisted two-dimensional van der Waals (2D vdW) materials remains challenging. Here, we utilize vector piezoresponse force microscopy (PFM) to reconstruct the polarization fields in R-type marginally twisted hexagonal boron nitride (hBN). We observe alternating out-of-plane (OOP) polarizations at domain regions and in-plane (IP) vortex-like polarization patterns along domain walls (DWs), indicative of a network of polar merons and antimerons. Notably, the OOP polarization exhibits three polarity reversals across a DW. Similar polar textures are identified in marginally twisted MoSe2 and WSe2 homobilayers. Our theoretical simulations attribute these unusual polarization reversals near the DWs to the competition between moiré ferroelectricity and piezoelectricity. These results provide experimental evidence of complex polar textures in moiré ferroelectrics, offering new insights into the electronic band topology in twisted transition metal dichalcogenides (TMDCs).

cond-mat.mtrl-sci↗
arXiv2024

SaliencyI2PLoc: saliency-guided image-point cloud localization using contrastive learning

Image to point cloud global localization is crucial for robot navigation in GNSS-denied environments and has become increasingly important for multi-robot map fusion and urban asset management. The modality gap between images and point clouds poses significant challenges for cross-modality fusion. Current cross-modality global localization solutions either require modality unification, which leads to information loss, or rely on engineered training schemes to encode multi-modality features, which often lack feature alignment and relation consistency. To address these limitations, we propose, SaliencyI2PLoc, a novel contrastive learning based architecture that fuses the saliency map into feature aggregation and maintains the feature relation consistency on multi-manifold spaces. To alleviate the pre-process of data mining, the contrastive learning framework is applied which efficiently achieves cross-modality feature mapping. The context saliency-guided local feature aggregation module is designed, which fully leverages the contribution of the stationary information in the scene generating a more representative global feature. Furthermore, to enhance the cross-modality feature alignment during contrastive learning, the consistency of relative relationships between samples in different manifold spaces is also taken into account. Experiments conducted on urban and highway scenario datasets demonstrate the effectiveness and robustness of our method. Specifically, our method achieves a Recall@1 of 78.92% and a Recall@20 of 97.59% on the urban scenario evaluation dataset, showing an improvement of 37.35% and 18.07%, compared to the baseline method. This demonstrates that our architecture efficiently fuses images and point clouds and represents a significant step forward in cross-modality global localization. The project page and code will be released.

cs.CV↗
arXiv2024

CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration

Image-to-point cloud (I2P) registration is a fundamental task for robots and autonomous vehicles to achieve cross-modality data fusion and localization. Current I2P registration methods primarily focus on estimating correspondences at the point or pixel level, often neglecting global alignment. As a result, I2P matching can easily converge to a local optimum if it lacks high-level guidance from global constraints. To improve the success rate and general robustness, this paper introduces CoFiI2P, a novel I2P registration network that extracts correspondences in a coarse-to-fine manner. First, the image and point cloud data are processed through a two-stream encoder-decoder network for hierarchical feature extraction. Second, a coarse-to-fine matching module is designed to leverage these features and establish robust feature correspondences. Specifically, In the coarse matching phase, a novel I2P transformer module is employed to capture both homogeneous and heterogeneous global information from the image and point cloud data. This enables the estimation of coarse super-point/super-pixel matching pairs with discriminative descriptors. In the fine matching module, point/pixel pairs are established with the guidance of super-point/super-pixel correspondences. Finally, based on matching pairs, the transform matrix is estimated with the EPnP-RANSAC algorithm. Experiments conducted on the KITTI Odometry dataset demonstrate that CoFiI2P achieves impressive results, with a relative rotation error (RRE) of 1.14 degrees and a relative translation error (RTE) of 0.29 meters, while maintaining real-time speed.Additional experiments on the Nuscenes datasets confirm our method's generalizability. The project page is available at \url{https://whu-usi3dv.github.io/CoFiI2P}.

cs.CV↗
arXiv2024

Layer-dependent electromechanical response in twisted graphene moiré superlattices

The coupling of mechanical deformation and electrical stimuli at the nanoscale has been a subject of intense investigation in the realm of materials science. Recently, twisted van der Waals (vdW) materials have emerged as a platform to explore exotic quantum states. These states are intimately tied to the formation of moiré superlattices, which can be visualized directly exploiting the electromechanical response. However, the origin of the response, even in twisted bilayer graphene (tBLG), remains unsettled. Here, employing lateral piezoresponse force microscopy (LPFM), we investigate the electromechanical responses of marginally twisted graphene moiré superlattices with different layer thicknesses. We observe distinct LPFM amplitudes and spatial profiles in tBLG and twisted monolayer-bilayer graphene (tMBG), exhibiting effective in-plane piezoelectric coefficients of 0.05 pm/V and 0.35 pm/V, respectively. Force tuning experiments further underscore a marked divergence in their responses. The contrasting behaviors suggest different electromechanical couplings in tBLG and tMBG. In tBLG, the response near the domain walls is attributed to the flexoelectric effect, while in tMBG, the behaviors can be comprehended within the context of piezoelectric effect. Our results not only provide insights to electromechanical and corporative effects in twisted vdW materials with different stacking symmetries, but may also show their potential for engineering them at the nanoscale.

cond-mat.mes-hall↗
arXiv2023

Testing Intersecting and Union-Closed Families

Inspired by the classic problem of Boolean function monotonicity testing, we investigate the testability of other well-studied properties of combinatorial finite set systems, specifically \emph{intersecting} families and \emph{union-closed} families. A function $f: \{0,1\}^n \to \{0,1\}$ is intersecting (respectively, union-closed) if its set of satisfying assignments corresponds to an intersecting family (respectively, a union-closed family) of subsets of $[n]$. Our main results are that -- in sharp contrast with the property of being a monotone set system -- the property of being an intersecting set system, and the property of being a union-closed set system, both turn out to be information-theoretically difficult to test. We show that: $\bullet$ For $ε\geq Ω(1/\sqrt{n})$, any non-adaptive two-sided $ε$-tester for intersectingness must make $2^{Ω(n^{1/4}/\sqrtε)}$ queries. We also give a $2^{Ω(\sqrt{n \log(1/ε)})}$-query lower bound for non-adaptive one-sided $ε$-testers for intersectingness. $\bullet$ For $ε\geq 1/2^{Ω(n^{0.49})}$, any non-adaptive two-sided $ε$-tester for union-closedness must make $n^{Ω(\log(1/ε))}$ queries. Thus, neither intersectingness nor union-closedness shares the $\mathrm{poly}(n,1/ε)$-query non-adaptive testability that is enjoyed by monotonicity. To complement our lower bounds, we also give a simple $\mathrm{poly}(n^{\sqrt{n\log(1/ε)}},1/ε)$-query, one-sided, non-adaptive algorithm for $ε$-testing each of these properties (intersectingness and union-closedness). We thus achieve nearly tight upper and lower bounds for two-sided testing of intersectingness when $ε= Θ(1/\sqrt{n})$, and for one-sided testing of intersectingness when $ε=Θ(1).$

cs.CC↗
arXiv2023

MEV Makes Everyone Happy under Greedy Sequencing Rule

Trading through decentralized exchanges (DEXs) has become crucial in today's blockchain ecosystem, enabling users to swap tokens efficiently and automatically. However, the capacity of miners to strategically order transactions has led to exploitative practices (e.g., front-running attacks, sandwich attacks) and gain substantial Maximal Extractable Value (MEV) for their own advantage. To mitigate such manipulation, Ferreira and Parkes recently proposed a greedy sequencing rule such that the execution price of transactions in a block moves back and forth around the starting price. Utilizing this sequencing rule makes it impossible for miners to conduct sandwich attacks, consequently mitigating the MEV problem. However, no sequencing rule can prevent miners from obtaining risk-free profits. This paper systemically studies the computation of a miner's optimal strategy for maximizing MEV under the greedy sequencing rule, where the utility of miners is measured by the overall value of their token holdings. Our results unveil a dichotomy between the no trading fee scenario, which can be optimally strategized in polynomial time, and the scenario with a constant fraction of trading fee, where finding the optimal strategy is proven NP-hard. The latter represents a significant challenge for miners seeking optimal MEV. Following the computation results, we further show a remarkable phenomenon: Miner's optimal MEV also benefits users. Precisely, in the scenarios without trading fees, when miners adopt the optimal strategy given by our algorithm, all users' transactions will be executed, and each user will receive equivalent or surpass profits compared to their expectations. This outcome provides further support for the study and design of sequencing rules in decentralized exchanges.

cs.GT↗
arXiv2023

Mildly Exponential Lower Bounds on Tolerant Testers for Monotonicity, Unateness, and Juntas

We give the first super-polynomial (in fact, mildly exponential) lower bounds for tolerant testing (equivalently, distance estimation) of monotonicity, unateness, and juntas with a constant separation between the "yes" and "no" cases. Specifically, we give $\bullet$ A $2^{Ω(n^{1/4}/\sqrt{\varepsilon})}$-query lower bound for non-adaptive, two-sided tolerant monotonicity testers and unateness testers when the "gap" parameter $\varepsilon_2-\varepsilon_1$ is equal to $\varepsilon$, for any $\varepsilon \geq 1/\sqrt{n}$; $\bullet$ A $2^{Ω(k^{1/2})}$-query lower bound for non-adaptive, two-sided tolerant junta testers when the gap parameter is an absolute constant. In the constant-gap regime no non-trivial prior lower bound was known for monotonicity, the best prior lower bound known for unateness was $\tildeΩ(n^{3/2})$ queries, and the best prior lower bound known for juntas was $\mathrm{poly}(k)$ queries.

cs.CC↗
arXiv2023

Symmetry-broken Chern insulators in twisted double bilayer graphene

Twisted double bilayer graphene (tDBG) has emerged as an especially rich platform for studying strongly correlated and topological states of matter. The material features moiré bands that can be continuously deformed by both perpendicular displacement field and twist angle. Here, we construct a phase diagram representing of the correlated and topological states as a function of these parameters, based on measurements on over a dozen tDBG devices encompassing the two distinct stacking configurations in which the constituent Bernal bilayer graphene sheets are rotated either slightly away from 0° or 60°. We find a hierarchy of symmetry-broken states that emerge sequentially as the twist angle approaches an apparent optimal value of $θ\approx$ 1.34°. Among them, we discover a sequence of symmetry-broken Chern insulator (SBCI) states that arise only within a narrow range of twist angles ($\approx$ 1.33° to 1.39°). We observe an associated anomalous Hall effect at zero field in all samples supporting SBCI states, indicating spontaneous time-reversal symmetry breaking and possible moiré unit cell enlargement at zero magnetic field.

cond-mat.mes-hall↗
arXiv2023

On Tightness of Tsaknakis-Spirakis Descent Methods for Approximate Nash Equilibria

This article explores the minimum approximation ratio for Nash equilibrium in bi-matrix games, focusing on the Tsaknakis and Spirakis (TS) methods. The previous SOTA, TS algorithm, achieved an approximation ratio of 0.3393, but efforts to improve the analysis of the TS algorithm have been unsuccessful. This work demonstrates that the bound of 0.3393 is tight for the TS algorithm and presents a theoretical worst-case analysis. A condition for identifying tight instances is provided, along with a generator. While most generated instances are unstable, indicating potential improvements, stable instances exist where perturbations cannot enhance the 0.3393 bound. Other approximate algorithms, such as regret-matching and fictitious play, achieve better ratios on these instances. The generated instances can serve as benchmarks for approximate Nash equilibrium algorithms. The article also mentions progress in the TS algorithm, achieving an approximation ratio of 1/3, which can be further studied using the presented techniques.

cs.GT↗
arXiv2023

Optimal Private Payoff Manipulation against Commitment in Extensive-form Games

To take advantage of strategy commitment, a useful tactic of playing games, a leader must learn enough information about the follower's payoff function. However, this leaves the follower a chance to provide fake information and influence the final game outcome. Through a carefully contrived payoff function misreported to the learning leader, the follower may induce an outcome that benefits him more, compared to the ones when he truthfully behaves. We study the follower's optimal manipulation via such strategic behaviors in extensive-form games. Followers' different attitudes are taken into account. An optimistic follower maximizes his true utility among all game outcomes that can be induced by some payoff function. A pessimistic follower only considers misreporting payoff functions that induce a unique game outcome. For all the settings considered in this paper, we characterize all the possible game outcomes that can be induced successfully. We show that it is polynomial-time tractable for the follower to find the optimal way of misreporting his private payoff information. Our work completely resolves this follower's optimal manipulation problem on an extensive-form game tree.

cs.GT↗
arXiv2023

Learning to Manipulate a Commitment Optimizer

It is shown in recent studies that in a Stackelberg game the follower can manipulate the leader by deviating from their true best-response behavior. Such manipulations are computationally tractable and can be highly beneficial for the follower. Meanwhile, they may result in significant payoff losses for the leader, sometimes completely defeating their first-mover advantage. A warning to commitment optimizers, the risk these findings indicate appears to be alleviated to some extent by a strict information advantage the manipulations rely on. That is, the follower knows the full information about both players' payoffs whereas the leader only knows their own payoffs. In this paper, we study the manipulation problem with this information advantage relaxed. We consider the scenario where the follower is not given any information about the leader's payoffs to begin with but has to learn to manipulate by interacting with the leader. The follower can gather necessary information by querying the leader's optimal commitments against contrived best-response behaviors. Our results indicate that the information advantage is not entirely indispensable to the follower's manipulations: the follower can learn the optimal way to manipulate in polynomial time with polynomially many queries of the leader's optimal commitment.

cs.GT↗
arXiv2022

Nonlinear reconstruction of features in the primordial power spectrum from large-scale structure

Potential features in the primordial power spectrum have been searched for in galaxy surveys in recent years since these features can assist in understanding the nature of inflation. The null detection to date suggests that any such features should be fairly weak, and next-generation galaxy surveys, with their unprecedented sizes and precisions, are in a position to place stronger constraints than before. However, even if such primordial features once existed in the early Universe, they would have been significantly damped in the nonlinear regime at low redshift due to structure formation, which makes them difficult to be directly detected in real observations. A potential way to tackle this challenge for probing the features is to undo the cosmological evolution, i.e., using reconstruction to obtain an approximate linear density field. By employing a set of N-body simulations, here we show that a recently-proposed nonlinear reconstruction algorithm can effectively retrieve damped oscillatory features from halo catalogues and improve the accuracy of the measurement of feature parameters (assuming that such primordial features do exist). We do a Fisher analysis to forecast how nonlinear reconstruction affects the constraining power, and find that it can lead to significantly more robust constraints on the feature amplitude for a DESI-like survey. Comparing nonlinear reconstruction with other ways of improving constraints, such as increasing the survey volume and range of scales, this shows that it is possible to achieve what the latter do, but at a lower cost.

astro-ph.CO↗
arXiv2022

Improved Upper Bounds for Finding Tarski Fixed Points

We study the query complexity of finding a Tarski fixed point over the $k$-dimensional grid $\{1,\ldots,n\}^k$. Improving on the previous best upper bound of $\smash{O(\log^{\lceil 2k/3\rceil} n)}$ [FPS20], we give a new algorithm with query complexity $\smash{O(\log^{\lceil (k+1)/2\rceil} n)}$. This is based on a novel decomposition theorem about a weaker variant of the Tarski fixed point problem, where the input consists of a monotone function $f:[n]^k\rightarrow [n]^k$ and a monotone sign function $b:[n]^k\rightarrow \{-1,0,1\}$ and the goal is to find an $x\in [n]^k$ that satisfies $either$ $f(x)\preceq x$ and $b(x)\le 0$ $or$ $f(x)\succeq x$ and $b(x)\ge 0$.

cs.GT↗
arXiv2022

Symmetry breaking and anomalous conductivity in a double moiré superlattice

A double moiré superlattice can be realized by stacking three layers of atomically thin two-dimensional materials with designer interlayer twisting or lattice mismatches. In this novel structure, atomic reconstruction of constituent layers could introduce significant modifications to the lattice symmetry and electronic structure at small twist angles. Here, we employ conductive atomic force microscopy (cAFM) to investigate symmetry breaking and local electrical properties in twisted trilayer graphene. We observe clear double moiré superlattices with two distinct moire periods all over the sample. At neighboring domains of the large moiré, the current exhibit either two- or six-fold rotational symmetry, indicating delicate symmetry breaking beyond the rigid model. Moreover, an anomalous current appears at the 'A-A' stacking site of the larger moiré, contradictory to previous observations on twisted bilayer graphene. Both behaviors can be understood by atomic reconstruction, and we also show that the cAFM signal of twisted graphene samples is dominated by the tip-graphene contact resistance that maps the local work function of twisted graphene and the metallic tip qualitatively. Our results unveil cAFM is an effective probe for visualizing atomic reconstruction and symmetry breaking in novel moiré superlattices, which could provide new insights for exploring and manipulating more exotic quantum states based on twisted van der Waals heterostructures.

cond-mat.mes-hall↗