arXiv subjects

Jingyao Wang

Publications and source records attributed to Jingyao Wang.

At least 19 recordsLinked to original sources

arXiv2026

Mind the Couch! Eliciting MLLM Reasoning in Interior Design via Weak-to-Strong Task Vector Injection

Multimodal Large Language Models (MLLMs) have demonstrated great performance, yet they often suffer from severe modality misalignment when confronted with densely constrained spaces for interior design. Due to the loss of high-frequency local topological details and fine-grained aesthetic shifts during visual encoding, existing MLLMs frequently hallucinate, yielding physical spatial collisions and visual aesthetic dissonance. To address this, we propose Dual-prior Activation Residual Task-vectors Injection mechanism (DART-I) for MLLMs. It shifts the paradigm from lossy text-prompting to direct latent intervention, utilizing weak-to-strong deterministic rules to anchor the causal reasoning of MLLMs for interior design. Specifically, DART-I operates in three steps: it first explicitly extracts continuous spatial distance and color typography features from images using extremely lightweight weak experts; subsequently, it transforms these deterministic priors into directional task vectors via a linear projection network; these vectors are dynamically injected as residual terms into the latent space of the frozen MLLMs, steering MLLMs towards precise reasoning for interior design. Stepping outside the conventional paradigms, our method achieves precise reasoning without fine-tuning the MLLMs, effectively bypassing expensive computational costs and catastrophic forgetting. Extensive experiments on various benchmarks demonstrate the effectiveness and advantages of DART-I.

cs.MM↗

arXiv2026

Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting

Time series forecasting often suffers from over-smoothing, especially when future dynamics are multi-modal. Forecasts may follow the coarse trend of the observed future, but fail to preserve sharp changes, oscillations, turning points, and regime transitions that define plausible dynamic evolution. In this work, we revisit over-smoothing from the perspective of latent dynamical mode compression: under partial observation and single-realization supervision, multiple plausible future modes can be weakened, merged, or averaged during forecasting. Based on this view, we propose Dirichlet-Guided Group Forecasting (DGF), a mode-preserving forecasting framework that explicitly models multiple mode-conditioned predictive distributions and uncertainty over their selection probabilities. DGF uses a Dirichlet-guided hierarchical sampling mechanism and reward-based optimization to encourage forecasts that are accurate, dynamically consistent, and mode-distinct. Extensive experiments on real-world forecasting benchmarks show that DGF reduces over-smoothing while improving forecasting accuracy, diversity, and dynamical consistency.

cs.LG↗

arXiv2026

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models

Vision-Language-Action (VLA) models show promising ability in language-guided robotic tasks. However, making VLA policies reliable remains challenging, because a manipulation task is completed through closed-loop interaction, where each action affects subsequent execution. To analyze this problem, we revisit VLA policy during execution and argue that a VLA policy acts both as a planner, which makes task-oriented decisions that change the direction of execution, and as an executor, which realizes these decisions through dense continuous actions. This view suggests that improving VLA reliability requires particular attention to planning actions. Existing optimization methods can imitate actions or improve complete trajectories, but they usually do not explicitly identify planning actions or measure their importance for task success. To address this issue, we propose Planning-Aware Policy Optimization for VLA models (PAPO-VLA). PAPO-VLA first identifies planning actions by jointly considering action variation and trajectory outcome, then estimates their importance through causal sufficiency and causal necessity, and finally incorporates this importance into GRPO advantage estimation. In this way, more important planning actions receive stronger optimization emphasis, while the whole trajectory is still optimized by trajectory-level feedback. Experiments on multiple benchmarks demonstrate the effectiveness of PAPO-VLA.

cs.RO↗

arXiv2026

CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models

Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that existing decoding methods may waste compute on easy cases while underserving hard ones, affecting both model effectiveness and efficiency. To address this issue, we first develop a theoretical framework that links sampling coverage, instance difficulty, and residual risk. Our analysis reveals that multimodal reasoning exhibits a heavy-tailed difficulty distribution; a small subset of hard or ambiguous samples dominates the residual failure probability. Based on this insight, we propose Coverage-Aware Multimodal Decoding (CAMD), an adaptive inference mechanism that dynamically allocates computation according to estimated uncertainty. CAMD integrates evidence-weighted scoring, posterior coverage estimation, and sequential Bayesian updating to balance efficiency and reliability under a limited token budget. Experiments on various benchmark datasets and baselines demonstrate the effectiveness and advantages of our approach.

cs.LG↗

arXiv2026

Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design

Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences. While recent multimodal large language models (MLLMs) offer a unified foundation for interpreting user intent and producing design rationales, our empirical analysis reveals a persistent contradiction in real-world deployment: MLLMs often produce layouts that are unbuildable and aesthetically inconsistent. These findings indicate that simply adding in-domain text is insufficient; effective interior design requires an alignment mechanism that separates hard constraints from soft preferences and coordinates them during optimization. To address this, we propose Design-MLLM, a reinforcement alignment framework that optimizes a feasibility-first preference objective via a dual-branch, aesthetic-oriented reward. Specifically, Design-MLLM (i) explicitly evaluates spatial feasibility using programmatic constraint checks, (ii) assesses aesthetic preference only among feasible candidates to avoid visually appealing but unexecutable shortcuts, and (iii) performs group-relative optimization to obtain stable preference signals. Through this process, Design-MLLM learns a controllable policy that consistently selects and generates solutions that are both executable and aesthetically coherent, rather than occasionally producing visually appealing but infeasible designs. Extensive experiments on various benchmark datasets demonstrate the advantages of Design-MLLM.

cs.MM↗

arXiv2026

Magnetic fluctuations near the Van Hove singularity in the kagome-lattice Hubbard model at finite doping

The kagome-lattice Hubbard model attracts widespread interest due to its flat-band and Van Hove singularity features, which can give rise to unconventional magnetism. We employ determinant quantum Monte Carlo simulations to systematically investigate the uniform magnetic susceptibility across a range of on-site interactions and electron fillings on a two-dimensional kagome lattice. Beyond the Van Hove singularity, dominant ferromagnetic fluctuations emerge. Magnetic susceptibility grows markedly with increasing interaction strength and decreasing temperature, indicating that the Van Hove singularity acts as a critical point for the crossover of dominant magnetic fluctuations. Finite-size analysis further suggests the potential stabilization of a finite-temperature ferromagnetic phase. We also examine the sign problem to identify numerically reliable parameter regimes. These results provide valuable insights into controlling magnetic fluctuations in kagome systems and establish a computational framework for exploring flat-band physics in regimes characterized by novel quantum phases and competing orders.

cond-mat.str-el↗

arXiv2026

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs

Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. Existing approaches typically employ an autoregressive generation strategy to adapt LLMs for TSF. However, we identify a theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, recursively consuming its own generated outputs. This leads to error accumulation, where minor early deviations cascade into significant rollout drift over long horizons. In this paper, we reformulate autoregressive forecasting through the lens of control theory, proposing Feedback-driven LLM (F-LLM), a novel closed-loop framework. Unlike standard methods that passively propagate errors, F-LLM actively stabilizes the trajectory via a learnable residual estimator functioning as a system observer. Furthermore, we provide a mathematical proof that, under explicit contraction assumptions, this closed-loop mechanism guarantees a uniformly bounded step-wise error sequence within the local surrogate dynamics. Extensive experiments demonstrate that F-LLM significantly mitigates error propagation, achieving good performance on time series benchmarks. Our code is publicly available at https://github.com/Zh-XY22/F-LLM.

cs.LG↗

arXiv2026

On the Plasticity and Stability for Post-Training Large Language Models

Training stability remains a critical bottleneck for Group Relative Policy Optimization (GRPO), often manifesting as a trade-off between reasoning plasticity and general capability retention. We identify a root cause as the geometric conflict between plasticity and stability gradients, which leads to destructive interference. Crucially, we argue that deterministic projection methods are suboptimal for GRPO as they overlook the intrinsic stochasticity of group-based gradient estimates. To address this, we propose Probabilistic Conflict Resolution (PCR), a Bayesian framework that models gradients as random variables. PCR dynamically arbitrates conflicts via an uncertainty-aware ``soft projection'' mechanism, optimizing the signal-to-noise ratio. Extensive experiments demonstrate that PCR significantly smooths the training trajectory and achieves superior performance in various reasoning tasks.

cs.LG↗

arXiv2026

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning

Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coupled to final correctness and pay little attention to the underlying reasoning process: trajectories with sound reasoning but wrong answers receive low credit, while lucky guesses with flawed logic may be highly rewarded, affecting reasoning generalization. From a causal perspective, we interpret multi-candidate reasoning for a fixed question as a family of counterfactual experiments with theoretical supports. Building on this, we propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns. It proposes an episodic causal counterfactual reward that jointly captures (i) robustness, encouraging the answer distribution induced by a reasoning step to remain stable under counterfactual perturbations; and (ii) effectiveness, enforcing sufficient variability so that the learned reasoning strategy can transfer across questions. We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust. Extensive experiments on diverse benchmarks demonstrate its advantages.

cs.LG↗

arXiv2026

Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning

The World Wide Web needs reliable predictive capabilities to respond to changes in user behavior and usage patterns. Time series forecasting (TSF) is a key means to achieve this goal. In recent years, the large language models (LLMs) for TSF (LLM4TSF) have achieved good performance. However, there is a significant difference between pretraining corpora and time series data, making it hard to guarantee forecasting quality when directly applying LLMs to TSF; fine-tuning LLMs can mitigate this issue, but often incurs substantial computational overhead. Thus, LLM4TSF faces a dual challenge of prediction performance and compute overhead. To address this, we aim to explore a method for improving the forecasting performance of LLM4TSF while freezing all LLM parameters to reduce computational overhead. Inspired by in-context learning (ICL), we propose LVICL. LVICL uses our vector-injected ICL to inject example information into a frozen LLM, eliciting its in-context learning ability and thereby enhancing its performance on the example-related task (i.e., TSF). Specifically, we first use the LLM together with a learnable context vector adapter to extract a context vector from multiple examples adaptively. This vector contains compressed, example-related information. Subsequently, during the forward pass, we inject this vector into every layer of the LLM to improve forecasting performance. Compared with conventional ICL that adds examples into the prompt, our vector-injected ICL does not increase prompt length; moreover, adaptively deriving a context vector from examples suppresses components harmful to forecasting, thereby improving model performance. Extensive experiments demonstrate the effectiveness of our approach.

cs.LG↗

arXiv2025

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration

In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as the ability of a representation learned from one task to support the objective of another. Inspired by the meta-learning paradigm, we construct multiple SSL tasks within each training batch to support explicitly modeling transferability. Based on empirical evidence and causal analysis, we find that although introducing task-level information improves transferability, it is still hindered by task conflict. To address this issue, we propose a Task Conflict Calibration (TC$^2$) method to alleviate the impact of task conflict. Specifically, it first splits batches to create multiple SSL tasks, infusing task-level information. Next, it uses a factor extraction network to produce causal generative factors for all tasks and a weight extraction network to assign dedicated weights to each sample, employing data reconstruction, orthogonality, and sparsity to ensure effectiveness. Finally, TC$^2$ calibrates sample representations during SSL training and integrates into the pipeline via a two-stage bi-level optimization framework to boost the transferability of learned representations. Experimental results on multiple downstream tasks demonstrate that our method consistently improves the transferability of SSL models.

cs.LG↗

arXiv2025

Interplay of magnetic and thermodynamic responses in the kagome-triangular system

Inspired by the recent experimental progress in pyrochlore derivative RE$_3$Sb$_3$A$_2$O$_{14}$ (A = Mg, Zn), we investigate the Hubbard model on the kagome lattice with an additional hopping $t'/t$, which enables continuous interpolation between the kagome and triangular lattices by using determinant quantum Monte Carlo simulations. We find that increasing $t'/t$ suppresses the nearest-neighbor antiferromagnetic correlations. Concurrently, the next-nearest-neighbor antiferromagnetic correlations are enhanced and closely associated with the emergence of a pronounced low-temperature peak in the specific heat. Increasing on-site interaction $U$ enhances magnetic correlations and shifts the associated $t'/t$ crossover points to larger values. We also discuss the sign problem to clarify which parameter region of our numerical simulations is accessible and reliable. Our results uncover the competition between frustration and correlations and the interplay of magnetic and thermodynamic responses in the kagome lattice, providing insights into correlated states in frustrated materials.

cond-mat.str-el↗

arXiv2025

A $^{3}$He-$^{21}$Ne Ramsey Comagnetometer with sub-nHz frequency resolution

Nuclear spin comagnetometers offer exceptional precision in measurements of spin energy levels and exhibit long-term stability, making them powerful tools for probing spin-dependent physics beyond the Standard Model as well as for inertial rotation sensing. We describe a new $^{3}$He-$^{21}$Ne Ramsey comagnetometer operating with an in-situ $^{87}$Rb magnetometer for initialization and sensing of nuclear spins. During free precession of nuclear spins we turn off all lasers and introduce a microwave field to suppress back-action from Rb atoms. We demonstrate that scalar and dipolar interactions between nuclear spins can be eliminated via control of the polarized sample geometry. These improvements result in a bias-free measurement with a frequency sensitivity of 0.6 nHz after 6 hours of integration.

physics.atom-ph↗

arXiv2025

A Generalized Learning Framework for Self-Supervised Contrastive Learning

Self-supervised contrastive learning (SSCL) has recently demonstrated superiority in multiple downstream tasks. In this paper, we generalize the standard SSCL methods to a Generalized Learning Framework (GLF) consisting of two parts: the aligning part and the constraining part. We analyze three existing SSCL methods: BYOL, Barlow Twins, and SwAV, and show that they can be unified under GLF with different choices of the constraining part. We further propose empirical and theoretical analyses providing two insights into designing the constraining part of GLF: intra-class compactness and inter-class separability, which measure how well the feature space preserves the class information of the inputs. However, since SSCL can not use labels, it is challenging to design a constraining part that satisfies these properties. To address this issue, we consider inducing intra-class compactness and inter-class separability by iteratively capturing the dynamic relationship between anchor and other samples and propose a plug-and-play method called Adaptive Distribution Calibration (ADC) to ensure that samples that are near or far from the anchor point in the original input space are closer or further away from the anchor point in the feature space. Both the theoretical analysis and the empirical evaluation demonstrate the superiority of ADC.

cs.LG↗

arXiv2025

Group Causal Policy Optimization for Post-Training Large Language Models

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands out for its efficiency, leveraging groupwise relative rewards while avoiding costly value function learning. However, GRPO treats candidate responses as independent, overlooking semantic interactions such as complementarity and contradiction. To address this challenge, we first introduce a Structural Causal Model (SCM) that reveals hidden dependencies among candidate responses induced by conditioning on a final integrated output forming a collider structure. Then, our causal analysis leads to two insights: (1) projecting responses onto a causally informed subspace improves prediction quality, and (2) this projection yields a better baseline than query only conditioning. Building on these insights, we propose Group Causal Policy Optimization (GCPO), which integrates causal structure into optimization through two key components: a causally informed reward adjustment and a novel KL regularization term that aligns the policy with a causally projected reference distribution. Comprehensive experimental evaluations demonstrate that GCPO consistently surpasses existing methods, including GRPO across multiple reasoning benchmarks.

cs.LG↗

arXiv2025

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionately to task-irrelevant background regions compared with text-only LLMs, implying spurious background-answer correlations. We claim and analyze that (i) outcome-based rewards can be an important factor leading to spurious correlations, and (ii) spurious correlations can be an important factor leading to hallucinations. Based on these results, we propose Causal-Oriented Policy Optimization (COPO) to mitigate these spurious correlations, thus addressing the issue of hallucinations. It imposes token-level sufficiency and necessity constraints to measure each inference token's causal contribution, thus ensuring correct and evidence-grounded output. Specifically, we first evaluate each token's causal contribution via a newly proposed causal completeness reward. This reward is then used to construct a causally informed advantage function within the GRPO optimization framework, encouraging the model to focus on tokens that are causally sufficient and necessary for accurate generation. Experimental results across various benchmarks demonstrate the advantages of COPO.

cs.CL↗

arXiv2025

Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection

Scene understanding is one of the core tasks in computer vision, aiming to extract semantic information from images to identify objects, scene categories, and their interrelationships. Although advancements in Vision-Language Models (VLMs) have driven progress in this field, existing VLMs still face challenges in adaptation to unseen complex wide-area scenes. To address the challenges, this paper proposes a Hierarchical Coresets Selection (HCS) mechanism to advance the adaptation of VLMs in complex wide-area scene understanding. It progressively refines the selected regions based on the proposed theoretically guaranteed importance function, which considers utility, representativeness, robustness, and synergy. Without requiring additional fine-tuning, HCS enables VLMs to achieve rapid understandings of unseen scenes at any scale using minimal interpretable regions while mitigating insufficient feature density. HCS is a plug-and-play method that is compatible with any VLM. Experiments demonstrate that HCS achieves superior performance and universality in various tasks.

cs.CV↗

arXiv2025

Rethinking Multi-Modal Learning from Gradient Uncertainty

Multi-Modal Learning (MML) integrates information from diverse modalities to improve predictive accuracy. While existing optimization strategies have made significant strides by mitigating gradient direction conflicts, we revisit MML from a gradient-based perspective to explore further improvements. Empirically, we observe an interesting phenomenon: performance fluctuations can persist in both conflict and non-conflict settings. Based on this, we argue that: beyond gradient direction, the intrinsic reliability of gradients acts as a decisive factor in optimization, necessitating the explicit modeling of gradient uncertainty. Guided by this insight, we propose Bayesian-Oriented Gradient Calibration for MML (BOGC-MML). Our approach explicitly models gradients as probability distributions to capture uncertainty, interpreting their precision as evidence within the framework of subjective logic and evidence theory. By subsequently aggregating these signals using a reduced Dempster's combination rule, BOGC-MML adaptively weights gradients based on their reliability to generate a calibrated update. Extensive experiments demonstrate the effectiveness and advantages of the proposed method.

cs.LG↗