arXiv subjects

Bin Yu

Publications and source records attributed to Bin Yu.

At least 55 records · Page 3Linked to original sources

arXiv2026

ASafePlace: User-Led Personalization of VR Relaxation via an Art Therapy Activity

To overcome the lack of deep personalization in standard biofeedback methods, we introduce ASafePlace, a system utilizing an AI-powered, art-therapy-inspired exercise called The Safe Place, to create a personalized VR biofeedback experience. In our system, users sketch a personal sanctuary from memory, which is then transformed into a customized 360 virtual environment with personalized audio guidance for relaxation training. A study with 52 participants showed this approach effectively reduced anxiety and increased user presence, while the integration of art-therapy-inspired activity and biofeedback produced strong improvements in physiological relaxation, measured by heart rate variability and respiration rate. Qualitative results showed how participants' sense of familiarity and presence was enhanced by the symbolic elements and natural sanctuaries created from their autobiographical memories. Our findings demonstrate that art-therapy-inspired activity is a powerful tool for creating highly effective and individualized relaxation experiences, naturally connecting the virtual environment to a user's core memories and emotions.

cs.HC↗

arXiv2026

TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers

The fundamental premise of Vision-Language-Action (VLA) models is to harness the extensive general capabilities of pre-trained Vision-Language Models (VLMs) for generalized embodied intelligence. However, standard robotic fine-tuning inevitably disrupts the pre-trained feature space, leading to "catastrophic forgetting" that compromises the general visual understanding we aim to leverage. To effectively utilize the uncorrupted general capabilities of VLMs for robotic tasks, we propose TwinBrainVLA, which coordinates two isomorphic VLM pathways: a frozen generalist (also called "Left Brain") and a trainable specialist (also called "Right Brain"). Our architecture utilizes a Asymmetric Mixture-of-Transformers (AsyMoT) mechanism, enabling the Right Brain to dynamically query and fuse intact semantic knowledge from the Left Brain with proprioceptive states. This fused representation conditions a flow-matching action expert for precise continuous control. Empirical results on SimplerEnv and RoboCasa benchmarks demonstrate that by explicitly retaining general capabilities, TwinBrainVLA achieves substantial performance gains over baseline models in complex manipulation tasks.

cs.RO↗

arXiv2026

MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models

Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-answer hit gap, where the model identifies the correct facts during reasoning but fails to incorporate them into the final response, thereby reducing factual fidelity. To address this issue, we propose MR-ALIGN, a Meta-Reasoning informed alignment framework that enhances factuality without relying on external verifiers. MR-ALIGN quantifies state transition probabilities along the model's thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. This re-weighting reshapes token-level signals into probability-aware segment scores, encouraging coherent reasoning trajectories that are more conducive to factual correctness. Empirical evaluations across four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. These results highlight that aligning the reasoning process itself, rather than merely the outputs, is pivotal for advancing factuality in LRMs.

cs.CL↗

arXiv2025

LLMBoost: Make Large Language Models Stronger with Boosting

Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal representations and interactions across models.In this work, we introduce LLMBoost, a novel ensemble fine-tuning framework that breaks this barrier by explicitly leveraging intermediate states of LLMs. Inspired by the boosting paradigm, LLMBoost incorporates three key innovations. First, a cross-model attention mechanism enables successor models to access and fuse hidden states from predecessors, facilitating hierarchical error correction and knowledge transfer. Second, a chain training paradigm progressively fine-tunes connected models with an error-suppression objective, ensuring that each model rectifies the mispredictions of its predecessor with minimal additional computation. Third, a near-parallel inference paradigm design pipelines hidden states across models layer by layer, achieving inference efficiency approaching single-model decoding. We further establish the theoretical foundations of LLMBoost, proving that sequential integration guarantees monotonic improvements under bounded correction assumptions. Extensive experiments on commonsense reasoning and arithmetic reasoning tasks demonstrate that LLMBoost consistently boosts accuracy while reducing inference latency.

cs.LG↗

arXiv2025

PCS Workflow for Veridical Data Science in the Age of AI

Data science is a pillar of artificial intelligence (AI), which is transforming nearly every domain of human activity, from the social and physical sciences to engineering and medicine. While data-driven findings in AI offer unprecedented power to extract insights and guide decision-making, many are difficult or impossible to replicate. A key reason for this challenge is the uncertainty introduced by the many choices made throughout the data science life cycle (DSLC). Traditional statistical frameworks often fail to account for this uncertainty. The Predictability-Computability-Stability (PCS) framework for veridical (truthful) data science offers a principled approach to addressing this challenge throughout the DSLC. This paper presents an updated and streamlined PCS workflow, tailored for practitioners and enhanced with guided use of generative AI. We include a running example to display the PCS framework in action, and conduct a related case study which showcases the uncertainty in downstream predictions caused by judgment calls in the data cleaning stage.

cs.LG↗

arXiv2025

CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents

Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3\% (synthetic) and 8.7\% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection. Moreover, CDR-Agent significantly reduces computational overhead. Using these datasets, we demonstrated that CDR-Agent not only selects relevant CDRs efficiently, but makes cautious yet effective imaging decisions by minimizing unnecessary interventions while successfully identifying most positively diagnosed cases, outperforming traditional LLM prompting approaches. Code for our work can be found at: https://github.com/zhenxianglance/medagent-cdr-agent

cs.LG↗

arXiv2025

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks

Spatial intelligence spans a rich suite of abilities, including visualising and transforming shapes, mentally rotating objects, judging relational positions and containment, and estimating numerosity. However, it still remains a critical unresolved challenge for Multimodal Large Language Models (MLLMs). To fill this gap, we propose to treat Euclidean geometry problem-solving as a surrogate task. Specifically, we meticulously constructed a curated multimodal dataset, called Euclid30K, comprising approximately 30K plane and solid geometry problems. Furthermore, to enable the model to learn and apply Euclidean principles from these geometry problems, we fine-tuned seven model variants (spanning 3--72B parameters) from the Qwen2.5VL, Qwen3VL, and RoboBrain2.0 families using Group Relative Policy Optimization (GRPO), inspiring the models to identify shapes, count, and relate entities, and perform multi-step deductive reasoning using Euclidean principles. Our experiments demonstrate that the resulting models achieve substantial zero-shot gains across four spatial reasoning benchmarks (Super-CLEVR, Omni3DBench, VSI-Bench, and MindCube) without any task-specific adaptations. Notably, after training on the Euclid30K, the mean VSI-Bench accuracy rose from 36.6\% to 41.8\% (+5.2\%), and the mean MindCube accuracy rose from 31.4\% to 38.1\% (+6.7\%). To our knowledge, this is the first systematic study showing that geometry-centric fine-tuning can confer vision-language models with broadly transferable spatial skills. Code and Euclid30K dataset can be found in \href{https://zgca-ai4edu.github.io/Euclids_Gift}{this}.

cs.CV↗

arXiv2025

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs

Large Language Models (LLMs) have achieved remarkable performance by capturing complex interactions between input features. To identify these interactions, most existing approaches require enumerating all possible combinations of features up to a given order, causing them to scale poorly with the number of inputs $n$. Recently, Kang et al. (2025) proposed SPEX, an information-theoretic approach that uses interaction sparsity to scale to $n \approx 10^3$ features. SPEX greatly improves upon prior methods but requires tens of thousands of model inferences, which can be prohibitive for large models. In this paper, we observe that LLM feature interactions are often hierarchical -- higher-order interactions are accompanied by their lower-order subsets -- which enables more efficient discovery. To exploit this hierarchy, we propose ProxySPEX, an interaction attribution algorithm that first fits gradient boosted trees to masked LLM outputs and then extracts the important interactions. Experiments across four challenging high-dimensional datasets show that ProxySPEX more faithfully reconstructs LLM outputs by 20% over marginal attribution approaches while using $10\times$ fewer inferences than SPEX. By accounting for interactions, ProxySPEX efficiently identifies the most influential features, providing a scalable approximation of their Shapley values. Further, we apply ProxySPEX to two interpretability tasks. Data attribution, where we identify interactions among CIFAR-10 training samples that influence test predictions, and mechanistic interpretability, where we uncover interactions between attention heads, both within and across layers, on a question-answering task.

cs.LG↗

arXiv2025

TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model

Large language models (LLMs) have shown remarkable progress in complex reasoning tasks, largely enabled by test-time scaling (TTS) paradigms that allocate additional compute during inference. Among these, external TTS (particularly the Best-of-N selection paradigm) yields scalable performance improvements by selecting from multiple independently generated reasoning trajectories. However, this approach faces key limitations: (i) the high computational overhead of deploying process reward models, (ii) the underutilization of the LLM's intrinsic latent representations. We introduce TrajSelector, an efficient and effective Best-of-N framework that exploit the hidden states in the sampler LLM for process-level scoring. A lightweight verifier (with only 0.6B parameters) evaluates the quality of step-wise trajectory, and then aggregates these scores to identify the optimal reasoning trajectory. Our framework employs a fully data-driven, end-to-end training recipe that eliminates reliance on massive step-level annotations. Experiential results across five benchmarks demonstrate that TrajSelector delivers consistent performance gains. In Best-of-32 settings, it surpasses majority voting by 4.61% accuracy and outperforms existing process reward models by 4.31% to 12.21%, all while maintaining lower inference costs.

cs.CL↗

arXiv2025

Deep learning the sources of MJO predictability: a spectral view of learned features

The Madden-Julian oscillation (MJO) is a planetary-scale, intraseasonal tropical rainfall phenomenon crucial for global weather and climate; however, its dynamics and predictability remain poorly understood. Here, we leverage deep learning (DL) to investigate the sources of MJO predictability, motivated by a central difference in MJO theories: which spatial scales are essential for driving the MJO? We first develop a deep convolutional neural network (DCNN) to forecast the MJO indices (RMM and ROMI). Our model predicts RMM and ROMI up to 21 and 33 days, respectively, achieving skills comparable to leading subseasonal-to-seasonal models such as NCEP. To identify the spatial scales most relevant for MJO forecasting, we conduct spectral analysis of the latent feature space and find that large-scale patterns dominate the learned signals. Additional experiments show that models using only large-scale signals as the input have the same skills as those using all the scales, supporting the large-scale view of the MJO. Meanwhile, we find that small-scale signals remain informative: surprisingly, models using only small-scale input can still produce skillful forecasts up to 1-2 weeks ahead. We show that this is achieved by reconstructing the large-scale envelope of the small-scale activities, which aligns with the multi-scale view of the MJO. Altogether, our findings support that large-scale patterns--whether directly included or reconstructed--may be the primary source of MJO predictability.

physics.ao-ph↗

arXiv2025

Nonsingular structural stable chaotic 3-flows of attractor-repeller type

We show that any orientable closed 3-manifold $M$ admits structurally stable non-singular flow $f^t$ whose non-wandering set $NW(f^t)$ consists of a 2-dimensional expanding attractor and finitely many repelling periodic trajectories. For $M=\mathbb{S}^3$, we prove that the set of repelling periodic trajectories can be an arbitrary link provided that this link contains the figure eight knot. When a link consists of a unique repelling periodic trajectory (not necessarily a figure eight knot), we prove that this trajectory cannot be a torus knot. For any closed 3-manifold $M$, we show that there does not admit any structurally stable non-singular flow $f^t$ whose non-wandering set $NW(f^t)$ consists of a 2-dimensional expanding attractor and a repelling periodic trajectory so that the repelling periodic trajectory is a trivial knot (i.e., it bounds a disk in $M$).

math.DS↗

arXiv2025

On the algebraic stretching dynamics of variable-density mixing in shock-bubble interaction

The mixing mechanism within a single-vortex has been a theoretical focus for decades, while remains unclear especially under variable-density (VD) scenario. This study investigates canonical single-vortex VD mixing in shock-bubble interactions (SBI) through high-resolution numerical simulations. Special attention is paid to examine the stretching dynamics and its impact on VD mixing within a single-vortex, and this problem is investigated by quantitatively characterizing the scalar dissipation rate (SDR), namely mixing rate, and its time integral, referred to as mixedness. We first examine single-vortex passive-scalar (PS) mixing with the absence of density difference. Under several assumptions, the single-vortex stretching rate illustrates an algebraic growth of the length of scalar strips. By incorporating diffusion process through the solution of the advection-diffusion equation along these stretched strips, a PS mixing model for SDR is proposed. Within this framework, density-gradient effects from two perspectives of stretching dynamics and diffusion process are discovered to challenge the extension of PS mixing model to VD mixing. First, the secondary baroclinic effect increases the VD stretching rate by the additional secondary baroclinic principal strain. Second, the density source effect suppresses the diffusion process. By accounting for both the secondary baroclinic effect on stretching and the density source effect on diffusion, a VD mixing model for SBI is further modified. This model establishes a quantitative relationship between the stretching dynamics and the evolution of the mixing rate and mixedness for single-vortex VD mixing over a broad range of Mach numbers. Furthermore, the essential role of stretching dynamics on the mixing rate is demonstrated by the derived dependence of the time-averaged mixing rate on the Peclet number Pe.

physics.flu-dyn↗

arXiv2025

Inference performance evaluation for LLMs on edge devices with a novel benchmarking framework and metric

With the significant success achieved by large language models (LLMs) like LLaMA, edge computing-based LLM inference services for mobile and PC are in high demand for data privacy. However, different edge platforms have different hardware characteristics and the large demand for memory capacity and bandwidth makes it very challenging to deploy and benchmark LLMs on edge devices. In this paper, we introduce a benchmarking tool named ELIB (edge LLM inference benchmarking) to evaluate LLM inference performance of different edge platforms, and propose a novel metric named MBU to indicate the percentage of the theoretically efficient use of available memory bandwidth for a specific model running on edge hardware to optimize memory usage. We deploy ELIB on three edge platforms and benchmark using five quantized models to optimize MBU in combination with other metrics such as FLOPS, throughput, latency and accuracy. And we analyze the results to derive the key factors, constraints, unpredictability in optimizing MBU that can guide deploying LLMs on more edge platforms.

cs.PF↗

arXiv2025

Not All Tokens Are What You Need In Thinking

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency toward overthinking -- generating verbose chains of thought (CoT) laden with redundant tokens that contribute minimally to the final answer. To address these issues, we propose Conditional Token Selection (CTS), a token-level compression framework with a flexible and variable compression ratio that identifies and preserves only the most essential tokens in CoT. CTS evaluates each token's contribution to deriving correct answers using conditional importance scoring, then trains models on compressed CoT. Extensive experiments demonstrate that CTS effectively compresses long CoT while maintaining strong reasoning performance. Notably, on the GPQA benchmark, Qwen2.5-14B-Instruct trained with CTS achieves a 9.1% accuracy improvement with 13.2% fewer reasoning tokens (13% training token reduction). Further reducing training tokens by 42% incurs only a marginal 5% accuracy drop while yielding a 75.8% reduction in reasoning tokens, highlighting the prevalence of redundancy in existing CoT.

cs.CL↗

arXiv2025

Note on Euler class 0 taut foliation on the Whitehead link exterior

This paper studies the existence of co-orientable taut foliations on 3-manifolds, particularly focusing on the Whitehead link exterior. We demonstrate fundamental obstructions to the existence of such foliations with certain Euler class properties, contrasting with the more permissive case of the figure-eight knot exterior. Our analysis reveals that most lattice points in the dual unit Thurston ball of the Whitehead link exterior cannot be realized as Euler classes of co-orientable taut foliations, with only limited exceptional cases. The proofs combine techniques from foliation theory, including saddle fillings and index formulas, with topological obstructions derived from Dehn surgery. These results yield general methods for studying foliations on cusped hyperbolic 3-manifolds. These techniques applied to broader classes of manifolds beyond the specific examples considered here

math.GT↗

arXiv2025

Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms

Domain adaptation (DA) is a statistical learning problem that arises when the distribution of the source data used to train a model differs from that of the target data used to evaluate the model. While many DA algorithms have demonstrated considerable empirical success, blindly applying these algorithms can often lead to worse performance on new datasets. To address this, it is crucial to clarify the assumptions under which a DA algorithm has good target performance. In this work, we focus on the assumption of the presence of conditionally invariant components (CICs), which are relevant for prediction and remain conditionally invariant across the source and target data. We demonstrate that CICs, which can be estimated through conditional invariant penalty (CIP), play three prominent roles in providing target risk guarantees in DA. First, we propose a new algorithm based on CICs, importance-weighted conditional invariant penalty (IW-CIP), which has target risk guarantees beyond simple settings such as covariate shift and label shift. Second, we show that CICs help identify large discrepancies between source and target risks of other DA algorithms. Finally, we demonstrate that incorporating CICs into the domain invariant projection (DIP) algorithm can address its failure scenario caused by label-flipping features. We support our new algorithms and theoretical findings via numerical experiments on synthetic data, MNIST, CelebA, Camelyon17, and DomainNet datasets.

stat.ML↗

arXiv2025

Three-Dimensional Isotropic STED Nanoscopy using a Single Objective

Accurate three-dimensional (3D) imaging requires an isotropic point spread function (PSF). However, the inherent missing aperture of a single objective lens results in an elongated, cigar-like PSF, which has rendered isotropic resolution in fluorescence microscopy seemingly insurmountable without a 4π configuration for decades. To address this long-standing challenge, we introduce ISO-STED (Isotropic Single-Objective STED) Nanoscopy, a novel approach that employs a single objective lens and a single depletion beam. By utilizing a hollow depletion focus, ISO-STED achieves an isotropic PSF without relying on a 4π configuration. This innovative design enables uniform fluorescence suppression in all directions, thereby yielding an isotropic 3D resolution of approximately 70 nm. Our work not only demonstrates the potential of ISO-STED Nanoscopy to provide a compact and versatile solution for isotropic 3D imaging in complex specimens but also paves the way for more accessible and practical applications in various research fields, including biomedical research and neuroscience.

physics.optics↗

arXiv2025

Significance of secondary baroclinic hydrodynamic instability on mixing enhancement in shock-bubble interaction

Different strength of hydrodynamic instability can be induced by the variations in the initial diffusion of shock bubble interaction (SBI), while the influence of hydrodynamic instability on variable-density mixing in SBI remains unclear. The present study aims to investigate the hydrodynamic instability of SBI through high-resolution numerical simulations. To isolate each factor within this instability, a circulation control method is employed to ensure consistent Reynolds number Re and Peclect number Pe. An examination of the morphology of the bubbles and vorticity dynamics reveals that the hydrodynamic instability can be characterized by positive circulation. Through vorticity budget analysis, the positive circulation is dominated by the baroclinic torque. Therefore, the identified hydrodynamic instability is labeled as secondary baroclinic hydrodynamic instability (SBHI). Based on the dimensional analysis of vorticity transport equation, a new dimensionless parameter, the secondary baroclinic vorticity (SBV) number, is proposed to characterize the strength of SBHI. Regarding mixing characteristics, cases with stronger SBHI exhibit higher mixing rates. Indicated by the temporal-averaged mixing rate with different SBV numbers, a scaling behavior is revealed: the mixing rate is increased proportionally to the square of SBV numbers. It is widely recognized that unstable flow can also be induced by a high Reynolds number Re. The distinction and connection of SBHI and high Re unstable flow are further studied. The scaling behavior of the mixing rate in SBHI shows distinct from the Reynolds number Re scaling: the mixing can hardly be altered effectively in the limit of large Re, the mechanisms of which are inherently different with respect to the stretch term, closely relating to the principal strain and the alignment angle between the scalar gradient and the principal strain axis.

physics.flu-dyn↗