arXiv subjects

Li Chen

Publications and source records attributed to Li Chen.

At least 109 records · Page 6Linked to original sources

arXiv2026

$χ_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies

High-reliability long-horizon robotic manipulation has traditionally relied on large-scale data and compute to understand complex real-world dynamics. However, we identify that the primary bottleneck to real-world robustness is not resource scale alone, but the distributional shift among the human demonstration distribution, the inductive bias learned by the policy, and the test-time execution distribution -- a systematic inconsistency that causes compounding errors in multi-stage tasks. To mitigate these inconsistencies, we propose $χ_{0}$, a resource-efficient framework with effective modules designated to achieve production-level robustness in robotic manipulation. Our approach builds off three technical pillars: (i) Model Arithmetic, a weight-space merging strategy that efficiently soaks up diverse distributions of different demonstrations, varying from object appearance to state variations; (ii) Stage Advantage, a stage-aware advantage estimator that provides stable, dense progress signals, overcoming the numerical instability of prior non-stage approaches; and (iii) Train-Deploy Alignment, which bridges the distribution gap via spatio-temporal augmentation, heuristic DAgger corrections, and temporal chunk-wise smoothing. $χ_{0}$ enables two sets of dual-arm robots to collaboratively orchestrate long-horizon garment manipulation, spanning tasks from flattening, folding, to hanging different clothes. Our method exhibits high-reliability autonomy; we are able to run the system from arbitrary initial state for consecutive 24 hours non-stop. Experiments validate that $χ_{0}$ surpasses the state-of-the-art $π_{0.5}$ in success rate by nearly 250%, with only 20-hour data and 8 A100 GPUs. Code, data and models will be released to facilitate the community.

cs.RO↗

arXiv2026

Efimovian Phonon Production for an Analog Coasting Universe in Bose-Einstein Condensates

Efimov effects arise from scale invariance, a fundamental symmetry with universal implications. While spatial Efimov physics has been extensively studied, realizing its temporal counterpart remains challenging, as it requires a dynamical system that breaks time-translation symmetry yet preserves the essential time-scaling symmetry. Analog cosmology offers a powerful platform to address this challenge, bridging the domains of Efimov physics and cosmology. Here, we predict a temporal Efimov effect in an analog linearly expanding universe realized with a quasi-two-dimensional Bose-Einstein condensate. The invariance of phonon mode equations under time rescaling leads to particle production with two distinct dynamics: power-law growth and log-periodic oscillations, with the latter being the hallmark signature of the Efimov effect. Furthermore, these dynamics map directly onto sub- and super-horizon cosmological modes. Our predictions can be directly verified through time-averaged measurements of the density-fluctuation spectrum $S_{k}(t)$ in current experiments.

cond-mat.quant-gas↗

arXiv2026

FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources

Federated Learning (FL) enables collaborative intelligence across decentralized data source devices in a privacy-preserving way. While substantial research attention has been drawn to optimizing the learning process for an individual task, real-world applications increasingly require multiple machine learning tasks simultaneously training their models across a shared pool of devices. Naively applying single-FL optimization techniques in multi-FL systems results in suboptimal system performance, particularly due to device heterogeneity and resource inefficiency. To address such a critical open challenge, we introduce {\em FedACT}, a novel resource heterogeneity-aware device scheduling approach designed to efficiently schedule heterogeneous devices across multiple concurrent FL jobs, with the goal of minimizing their average job completion time (JCT). {\em FedACT} dynamically assigns devices to FL jobs based on an alignment scoring mechanism that evaluates the compatibility between available resources of devices and resource demands of jobs. Additionally, it incorporates participation fairness to ensure balanced contributions from devices across jobs, further enhancing the accuracy levels of learned global models. An optimal scheduling plan is formulated in {\em FedACT} by prioritizing devices with higher alignment scores, while ensuring fair participation across jobs. To evaluate the effectiveness of the proposed scheduling algorithm, we carried out comprehensive experiments using diverse FL jobs and benchmark datasets. Experimental results demonstrate that {\em FedACT} reduces the average JCT by up to 8.3$\times$ and improves model accuracy by up to 44.5\%, compared to the state-of-the-art baselines.

cs.LG↗

arXiv2026

FreeTacMan: Robot-free Visuo-Tactile Data Collection System for Contact-rich Manipulation

Enabling robots with contact-rich manipulation remains a pivotal challenge in robot learning, which is substantially hindered by the data collection gap, including its inefficiency and limited sensor setup. While prior work has explored handheld paradigms, their rod-based mechanical structures remain rigid and unintuitive, providing limited tactile feedback and posing challenges for operators. Motivated by the dexterity and force feedback of human motion, we propose FreeTacMan, a human-centric and robot-free data collection system for accurate and efficient robot manipulation. Concretely, we design a wearable gripper with visuo-tactile sensors for data collection, which can be worn by human fingers for intuitive control. A high-precision optical tracking system is introduced to capture end-effector poses while synchronizing visual and tactile feedback simultaneously. We leverage FreeTacMan to collect a large-scale multimodal dataset, comprising over 3000k paired visuo-tactile images with end-effector poses, 10k demonstration trajectories across 50 diverse contact-rich manipulation tasks. FreeTacMan achieves multiple improvements in data collection performance over prior works and enables effective policy learning from self-collected datasets. By open-sourcing the hardware and the dataset, we aim to facilitate reproducibility and support research in visuo-tactile manipulation.

cs.RO↗

arXiv2026

Agility Meets Stability: Versatile Humanoid Control with Heterogeneous Data

Humanoid robots are envisioned to perform a wide range of tasks in human-centered environments, requiring controllers that combine agility with robust balance. Recent advances in locomotion and whole-body tracking have enabled impressive progress in either agile dynamic skills or stability-critical behaviors, but existing methods remain specialized, focusing on one capability while compromising the other. In this work, we introduce AMS (Agility Meets Stability), the first framework that unifies both dynamic motion tracking and extreme balance maintenance in a single policy. Our key insight is to leverage heterogeneous data sources: human motion capture datasets that provide rich, agile behaviors, and physically constrained synthetic balance motions that capture stability configurations. To reconcile the divergent optimization goals of agility and stability, we design a hybrid reward scheme that applies general tracking objectives across all data while injecting balance-specific priors only into synthetic motions. Further, an adaptive learning strategy with performance-driven sampling and motion-specific reward shaping enables efficient training across diverse motion distributions. We validate AMS extensively in simulation and on a real Unitree G1 humanoid. Experiments demonstrate that a single policy can execute agile skills such as dancing and running, while also performing zero-shot extreme balance motions like Ip Man's Squat, highlighting AMS as a versatile control paradigm for future humanoid applications.

cs.RO↗

arXiv2026

Second-quantized approach to the study of Halperin state in fractional quantum Hall effect

We give a recursion relation for the second-quantized fermionic (bosonic) Halperin state, which avoids exact diagonalization of its two-component first-quantized parent Hamiltonian. We validate this formula by proving that the second-quantized Halperin state, as recursively defined in this formula, is indeed a zero mode of the corresponding second-quantized parent Hamiltonian and that it has the correct filling factor.

cond-mat.str-el↗

arXiv2026

Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization

Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-level planning. Vision-Language Models (VLMs) offer a general perceive-reason-act framework for this goal. However, previous approaches using reflective planning to guide VLMs in correcting actions encounter significant limitations. These methods rely on inefficient and often inaccurate implicit learning of state-values from noisy foresight predictions, evaluate only a single greedy future, and suffer from substantial inference latency. To address these limitations, we propose a novel test-time computation framework that decouples state evaluation from action generation. This provides a more direct and fine-grained supervisory signal for robust decision-making. Our method explicitly models the advantage of an action plan, quantified by its reduction in distance to the goal, and uses a scalable critic to estimate. To address the stochastic nature of single-trajectory evaluation, we employ beam search to explore multiple future paths and aggregate them during decoding to model their expected long-term returns, leading to more robust action generation. Additionally, we introduce a lightweight, confidence-based trigger that allows for early exit when direct predictions are reliable, invoking reflection only when necessary. Extensive experiments on diverse, unseen multi-stage robotic manipulation tasks demonstrate a 24.6% improvement in success rate over state-of-the-art baselines, while significantly reducing inference time by 56.5%.

cs.RO↗

arXiv2026

Rigorous Derivation of the Degenerate Parabolic-Elliptic Keller-Segel System from a Moderately Interacting Stochastic Particle System. Part II Propagation of Chaos

This work is a series of two articles. The main goal is to rigorously derive the degenerate parabolic-elliptic Keller-Segel system in the sub-critical regime from a moderately interacting stochastic particle system. In the first article [7], we establish the classical solution theory of the degenerate parabolic-elliptic Keller-Segel system and its non-local version. In the second article, which is the current one, we derive a propagation of chaos result, where the classical solution theory obtained in the first article is used to derive required estimates for the particle system. Due to the degeneracy of the non-linear diffusion and the singular aggregation effect in the system, we perform an approximation of the stochastic particle system by using a cut-offed interacting potential. An additional linear diffusion on the particle level is used as a parabolic regularization of the system. We present the propagation of chaos result with logarithmic scalings. Consequently, the propagation of chaos follows directly from convergence in the sense of expectation and the vanishing viscosity argument of the Keller-Segel system.

math.PR↗

arXiv2026

Supercharging Packet-level Network Simulation of Large Model Training via Memoization and Fast-Forwarding

Packet-level discrete-event simulation (PLDES) is a prevalent tool for evaluating detailed performance of large model training. Although PLDES offers high fidelity and generality, its slow performance has plagued networking practitioners. Existing optimization techniques either simplify the network model, resulting in large errors; or execute it in parallel using multiple processors, with an upper bound on speedup. This paper explores an alternative optimization direction that reduces the computational loads of PLDES while maintaining high fidelity. Our key insight is that, in distributed LLM training, packet-level traffic behaviors often exhibit repetitive contention patterns and steady-states where flow rates stabilize, ignoring these redundant discrete events speeds up the simulation considerably and the error is negligible. We realize this idea by proposing Wormhole, a user-transparent PLDES kernel capable of automatically memoization for unsteady-states and skipping for steady-states. Wormhole adopts network partitioning, state memoization and reuse, and rate-based steady-state identification to accurately determine the periods of each flow's steady-state, while maintaining simulation consistency after fast-forwarding. Experiments demonstrate that Wormhole can achieve a 744x speedup over the original ns-3 (510x for MoE workload), with a bounded error of <1%. Applying current multithreading parallel techniques and Wormhole together allows a 1012x speedup, reducing the simulation time for one GPT-13B training under 128 GPUs from 9 hours to 5 minutes.

cs.NI↗

arXiv2026

Normalized solutions of quasilinear Schrödinger-Poisson system with critical nonlinear term in bounded domain

This work examines a quasilinear Schrödinger-Poisson system involving a critical nonlinearity, expressed as \[ -Δu + ϕu + λu = |u|^{q-2} u + |u|^4 u, \quad x \in Ω_r, \] \[ -Δϕ- \varepsilon^4 Δ_4 ϕ= u^2, \qquad\qquad\qquad\quad\ x \in Ω_r, \] \[ \enspace u = ϕ= 0, \qquad\qquad\qquad\qquad\qquad\enspace\ \ \,x \in \partial Ω_r \] subject to the normalized condition \[ \int_{Ω_r} |u|^2\, \mathrm d x = b^2. \] Here $\varepsilon > 0$, $q \in (2, 8/3)$, $Ω_r \subset \mathbb R^3$ is a bounded domain. By means of a truncation method combined with genus theory, we establish the existence of multiple families of normalized solutions. Due to the presence of a critical exponent in the nonlinear term, the associated energy functional fails to satisfy the usual compactness properties. To address this issue, we invoke the concentration-compactness principle. Furthermore, we derive the asymptotic result that the aforementioned system reduces to the classical Schrödinger-Poisson system (with $\varepsilon = 0$). Our findings extend several recent results concerning problems of this type.

math.AP↗

arXiv2026

Revisiting the Seasonal Trend Decomposition for Enhanced Time Series Forecasting

Time series forecasting presents significant challenges in real-world applications across various domains. Building upon the decomposition of the time series, we enhance the architecture of machine learning models for better multivariate time series forecasting. To achieve this, we focus on the trend and seasonal components individually and investigate solutions to predict them with less errors. Recognizing that reversible instance normalization is effective only for the trend component, we take a different approach with the seasonal component by directly applying backbone models without any normalization or scaling procedures. Through these strategies, we successfully reduce error values of the existing state-of-the-art models and finally introduce dual-MLP models as more computationally efficient solutions. Furthermore, our approach consistently yields positive results with around 10% MSE average reduction across four state-of-the-art baselines on the benchmark datasets. We also evaluate our approach on a hydrological dataset extracted from the United States Geological Survey (USGS) river stations, where our models achieve significant improvements while maintaining linear time complexity, demonstrating real-world effectiveness. The source code is available at https://github.com/Sanjeev97/Time-Series-Decomposition

cs.LG↗

arXiv2026

Low-complexity Design for Beam Coverage in Near-field and Far-field: A Fourier Transform Approach

In this paper, we study efficient beam coverage design for multi-antenna systems in both far-field and near-field cases. To reduce the computational complexity of existing sampling-based optimization methods, we propose a new low-complexity yet efficient beam coverage design. To this end, we first formulate a general beam coverage optimization problem to maximize the worst-case beamforming gain over a target region. For the far-field case, we show that the beam coverage design can be viewed as a spatial-frequency filtering problem, where angular coverage can be achieved by weight-shaping in the antenna domain via an inverse FT, yielding an infinite-length weighting sequence. Under the constraint of a finite number of antennas, a surrogate scheme is proposed by directly truncating this sequence, which inevitably introduces a roll-off effect at the angular boundaries, yielding degraded worst-case beamforming gain. To address this issue, we characterize the finite-antenna-induced roll-off effect, based on which a roll-off-aware design with a protective zoom is developed to ensure a flat beamforming-gain profile within the target angular region. Next, we extend the proposed method to the near-field case. Specifically, by applying a first-order Taylor approximation to the near-field channel steering vector (CSV), the two-dimensional (2D) beam coverage design (in both angle and inverse-range) can be transformed into a 2D inverse FT, leading to a low-complexity beamforming design. Furthermore, an inherent near-field range defocusing effect is observed, indicating that sufficiently wide angular coverage results in range-insensitive beam steering. Finally, numerical results demonstrate that the proposed FT-based approach achieves a comparable worst-case beamforming performance with that of conventional sampling-based optimization methods while significantly reducing the computational complexity.

cs.IT↗

arXiv2026

Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation

Why must vision-language navigation be bound to detailed and verbose language instructions? While such details ease decision-making, they fundamentally contradict the goal for navigation in the real-world. Ideally, agents should possess the autonomy to navigate in unknown environments guided solely by simple and high-level intents. Realizing this ambition introduces a formidable challenge: Beyond-the-View Navigation (BVN), where agents must locate distant, unseen targets without dense and step-by-step guidance. Existing large language model (LLM)-based methods, though adept at following dense instructions, often suffer from short-sighted behaviors due to their reliance on short-horimzon supervision. Simply extending the supervision horizon, however, destabilizes LLM training. In this work, we identify that video generation models inherently benefit from long-horizon supervision to align with language instructions, rendering them uniquely suitable for BVN tasks. Capitalizing on this insight, we propose introducing the video generation model into this field for the first time. Yet, the prohibitive latency for generating videos spanning tens of seconds makes real-world deployment impractical. To bridge this gap, we propose SparseVideoNav, achieving sub-second trajectory inference guided by a generated sparse future spanning a 20-second horizon. This yields a remarkable 27x speed-up compared to the unoptimized counterpart. Extensive real-world zero-shot experiments demonstrate that SparseVideoNav achieves 2.5x the success rate of state-of-the-art LLM baselines on BVN tasks and marks the first realization of such capability in challenging night scenes.

cs.CV↗

arXiv2026

PALM: PAnoramic Learning Map Integrating Learning Analytics and Curriculum Map for Scalable Insights Across Courses

This study proposes and evaluates the PAnoramic Learning Map (PALM), a learning analytics (LA) dashboard designed to address the scalability challenges of LA by integrating curriculum-level information. Traditional LA research has predominantly focused on individual courses or learners and often lacks a framework that considers the relationships between courses and the long-term trajectory of learning. To bridge this gap, PALM was developed to integrate multilayered educational data into a curriculum map, enabling learners to intuitively understand their learning records and academic progression. We conducted a system evaluation to assess PALM's effectiveness in two key areas: (1) its impact on students' awareness of their learning behaviors, and (2) its comparative performance against existing systems. The results indicate that PALM enhances learners' awareness of study planning and reflection, particularly by improving perceived behavioral control through the visual presentation of individual learning histories and statistical trends, which clarify the links between learning actions and outcomes. Although PALM requires ongoing refinement as a system, it received significantly higher evaluations than existing systems in terms of visual appeal and usability. By serving as an information resource with previously inaccessible insights, PALM enhances self-regulated learning and engagement, representing a significant step beyond conventional LA toward a comprehensive and scalable approach.

cs.HC↗

arXiv2026

Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models suffers from two critical challenges: (1) the inherent noise in preference datasets, which degrades model performance, and (2) the inefficiency of conventional training methods, which ignore the differences in sample difficulty. In this paper, we identify a strong correlation between response entropy and accuracy, indicating that entropy can serve as a reliable and unsupervised proxy for annotation noise and sample difficulty. Based on this insight, we propose a novel Entropy-Guided Training (EGT) approach for multimodal reasoning reward models, which combines two strategies: (1) entropy-guided data curation to mitigate the impact of unreliable samples, and (2) an entropy-guided training strategy that progressively introduces more complex examples. Extensive experiments across three benchmarks show that the EGT-trained model consistently outperforms state-of-the-art multimodal reward models.

cs.AI↗

arXiv2026

Successive Cancellation List Decoding of Extended Reed-Solomon Codes

Reed-Solomon (RS) codes are an important class of non-binary error-correction codes. They are particularly competent in correcting burst errors, being widely applied in modern communications and data storage systems. This also thanks to their distance property of reaching the Singleton bound, being the maximum distance separable (MDS) codes. This paper proposes a new list decoding for extended RS (eRS) codes defined over a finite field of characteristic two, i.e., F_{2^n}. It is developed based on transforming an eRS code into n binary polar codes. Consequently, it can be decoded by the successive cancellation (SC) decoding and further their list decoding, i.e., the SCL decoding. A pre-transformed matrix is required for reinterpretating the eRS codes, which also determines their SC and SCL decoding performances. Its column linear independence property is studied, leading to theoretical characterization of their SC decoding performance. Our proposed decoding and analysis are validated numerically.

cs.IT↗

arXiv2026

The Double-Edged Sword of Knowledge Transfer: Diagnosing and Curing Fairness Pathologies in Cross-Domain Recommendation

Cross-domain recommendation (CDR) offers an effective strategy for improving recommendation quality in a target domain by leveraging auxiliary signals from source domains. Nonetheless, emerging evidence shows that CDR can inadvertently heighten group-level unfairness. In this work, we conduct a comprehensive theoretical and empirical analysis to uncover why these fairness issues arise. Specifically, we identify two key challenges: (i) Cross-Domain Disparity Transfer, wherein existing group-level disparities in the source domain are systematically propagated to the target domain; and (ii) Unfairness from Cross-Domain Information Gain, where the benefits derived from cross-domain knowledge are unevenly allocated among distinct groups. To address these two challenges, we propose a Cross-Domain Fairness Augmentation (CDFA) framework composed of two key components. Firstly, it mitigates cross-domain disparity transfer by adaptively integrating unlabeled data to equilibrate the informativeness of training signals across groups. Secondly, it redistributes cross-domain information gains via an information-theoretic approach to ensure equitable benefit allocation across groups. Extensive experiments on multiple datasets and baselines demonstrate that our framework significantly reduces unfairness in CDR without sacrificing overall recommendation performance, while even enhancing it.

cs.IR↗

arXiv2026

Post-Training Fairness Control: A Single-Train Framework for Dynamic Fairness in Recommendation

Despite growing efforts to mitigate unfairness in recommender systems, existing fairness-aware methods typically fix the fairness requirement at training time and provide limited post-training flexibility. However, in real-world scenarios, diverse stakeholders may demand differing fairness requirements over time, so retraining for different fairness requirements becomes prohibitive. To address this limitation, we propose Cofair, a single-train framework that enables post-training fairness control in recommendation. Specifically, Cofair introduces a shared representation layer with fairness-conditioned adapter modules to produce user embeddings specialized for varied fairness levels, along with a user-level regularization term that guarantees user-wise monotonic fairness improvements across these levels. We theoretically establish that the adversarial objective of Cofair upper bounds demographic parity and the regularization term enforces progressive fairness at user level. Comprehensive experiments on multiple datasets and backbone models demonstrate that our framework provides dynamic fairness at different levels, delivering comparable or better fairness-accuracy curves than state-of-the-art baselines, without the need to retrain for each new fairness requirement. Our code is publicly available at https://github.com/weixinchen98/Cofair.

cs.LG↗