arXiv subjects

Jinyi Li

Publications and source records attributed to Jinyi Li.

8 recordsLinked to original sources

arXiv2026

AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization

Contrastive Language-Image Pretraining learns a shared representation space through large-scale contrastive learning. However, existing methods that enforce global consistency regularization overlook a key challenge: the inherent information asymmetry between images and text: captions typically describe only one specific aspect of an image, thus images with similar visual content can be paired with completely divergent textual content and semantic information. Consequently, global regularizers inadvertently impose constraints between visually similar images whose captions describe divergent aspects, introducing semantic distortion into the representation space. We propose AspectCLIP, a framework that reformulates consistency regularization to respect this one-to-many structure. AspectCLIP first partitions training samples into attribute clusters based on textual similarity to identify aspect-coherent groups, then applies full cyclic consistency within each cluster while restricting cross-cluster regularization to prototype-level comparisons. This aspect-guided regularization enforces strict geometric alignment only when images and texts describe a consistent facet, while allowing flexibility across divergent aspects. Extensive experiments on downstream tasks demonstrate that AspectCLIP consistently outperforms traditional methods and achieves a more structured representation space.

cs.CV↗

arXiv2026

SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies

Vision-Language-Action (VLA) policies that execute fixed-length action chunks can exhibit multimodal bifurcation: a cross-chunk inconsistency in which adjacent chunks generated from independent Gaussian latents can converge to incompatible trajectory modes, producing abrupt discontinuities at chunk boundaries. Existing remedies either require backpropagation through the policy at each denoising step, rely on rejection sampling, or require retraining, each trading computational cost or task reliability for smoother transitions. We propose SEAM (Smooth Execution of Action-Chunked Motion), a training-free inference-time method for flow matching VLAs. SEAM exploits a simple synchronous-execution insight: after the robot consumes the executed prefix, the previous chunk's unexecuted tail is already available as an analytic consistency reference. Its core mechanism, Velocity-guided Loss Steering (VLS), derives a time-dependent target from this tail and applies a closed-form correction after each Euler step without backpropagating through the policy network. On LIBERO-10 with pi_0.5, SEAM reduces boundary jerk by 28%, reduces chunk transition discontinuity by 27%, preserves baseline-level task success, and keeps denoising-loop cost near the unguided baseline.

cs.RO↗

arXiv2026

NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps

Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency. While recent approaches attempt to leverage pre-built environment maps, they often rely on incrementally updating memory graphs or scoring discrete path proposals, which restricts continuous spatial reasoning and creates discrete bottlenecks. We propose Top-Down VLN (TD-VLN), reformulating navigation as a one-step global path planning problem on pre-built top-down maps, supported by our newly constructed R2R-TopDown dataset. To solve this, we introduce NavOne, a unified framework that directly predicts dense path probabilities over multi-modal maps in a single end-to-end forward pass. NavOne features a Top-Down Map Fuser for joint multi-modal map representation, and extends Attention Residuals for spatial-aware depth mixing. Extensive experiments on R2R-TopDown show that NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation.

cs.CV↗

arXiv2026

Thermal vapor quantum battery based on collective atomic spins

Quantum batteries harness non-classical resources, such as quantum coherence and entanglement, to surpass the performance limits of classical energy-storage devices. Here we realize a room-temperature quantum battery based on a collective atomic spin ensemble in a thermal alkali-metal vapor, containing approximately $10^{12}$ $^{87}$Rb atoms with coherence times exceeding 110 ms. We operationally determine the battery capacity by directly measuring the extremal internal energies accessible under unitary evolution. This tomography-free protocol agrees closely with the conventional state-based definition and verifies the decomposition of capacity into coherent and incoherent contributions. We further show that quantum coherence can substantially enhance the storage capability independently of level populations, and experimentally establish quantitative relations linking battery capacity to von Neumann, Tsallis and linear entropies. By introducing a controlled dephasing channel with a magnetic-field gradient, we observe a monotonic reduction of capacity with coherence loss and track the corresponding evolution of the entropy-capacity relations. Our results identify thermal atomic spin ensembles as a scalable platform for quantum batteries and connect macroscopic quantum energy storage with operational quantum thermodynamics.

quant-ph↗

arXiv2026

Adaptive low-rank exponential integrators for large-scale differential Riccati equation

Matrix differential Riccati equation (DRE) typically exhibits transient and steady-state phases, posing challenges for fixed-step time integration methods, which may lack accuracy during transients or oversample in steady regimes. In this work, we propose adaptive low-rank matrix-valued exponential integrators for large-scale stiff DRE. The methods combine embedded exponential Rosenbrock-type schemes and adaptive step-size control, enabling an automatic adjustment to the evolving solution dynamics. This improves the accuracy during rapid transient phases while maintaining high accuracy in the steady state. Numerical experiments on benchmark problems demonstrate that the proposed adaptive integrators consistently improve accuracy and computational efficiency compared with fixed-step low-rank schemes.

math.NA↗

arXiv2025

Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and texture bias. While recent approaches integrate 3D data with 2D foundation models (e.g., CLIP), they suffer from semantic blurring caused by texture-biased projections and indiscriminate fusion of geometric-textural cues, leading to unstable decision prototypes and catastrophic forgetting. To address these issues, we propose Cross-Modal Geometric Rectification (CMGR), a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics. Specifically, we introduce a Structure-Aware Geometric Rectification module that hierarchically aligns 3D part structures with CLIP's intermediate spatial priors through attention-driven geometric fusion. Additionally, a Texture Amplification Module synthesizes minimal yet discriminative textures to suppress noise and reinforce cross-modal consistency. To further stabilize incremental prototypes, we employ a Base-Novel Discriminator that isolates geometric variations. Extensive experiments demonstrate that our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias across cross-domain and within-domain settings.

cs.CV↗

arXiv2025

An Empirical Study on Prompt Compression for Large Language Models

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression methods for LLMs, aiming to reduce prompt length while maintaining LLM response quality. In this paper, we present a comprehensive analysis covering aspects such as generation performance, model hallucinations, efficacy in multimodal tasks, word omission analysis, and more. We evaluate these methods across 13 datasets, including news, scientific articles, commonsense QA, math QA, long-context QA, and VQA datasets. Our experiments reveal that prompt compression has a greater impact on LLM performance in long contexts compared to short ones. In the Longbench evaluation, moderate compression even enhances LLM performance. Our code and data is available at https://github.com/3DAgentWorld/Toolkit-for-Prompt-Compression.

cs.CL↗

arXiv2024

PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models

Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information. To facilitate quick-start services, user-friendly interfaces, and compatibility with common datasets and metrics, we present the Prompt Compression Toolkit (PCToolkit). This toolkit is a unified plug-and-play solution for compressing prompts in Large Language Models (LLMs), featuring cutting-edge prompt compressors, diverse datasets, and metrics for comprehensive performance evaluation. PCToolkit boasts a modular design, allowing for easy integration of new datasets and metrics through portable and user-friendly interfaces. In this paper, we outline the key components and functionalities of PCToolkit. We conducted evaluations of the compressors within PCToolkit across various natural language tasks, including reconstruction, summarization, mathematical problem-solving, question answering, few-shot learning, synthetic tasks, code completion, boolean expressions, multiple choice questions, and lies recognition.

cs.CL↗