arXiv subjects

Yuquan Li

Publications and source records attributed to Yuquan Li.

6 recordsLinked to original sources

arXiv2026

AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memory

Foundation-model-based monocular depth estimation offers a viable alternative to active sensors for robot perception, yet its computational cost often prohibits deployment on edge platforms. Existing methods perform independent per-frame inference, wasting the substantial computational redundancy between adjacent viewpoints in continuous robot operation. This paper presents AsyncMDE, an asynchronous depth perception system consisting of a frozen foundation model and a lightweight fast path that amortizes the foundation model's computational cost over time. The foundation model periodically produces high-quality spatial features in the background, while the lightweight fast path runs asynchronously in the foreground, fusing cached memory with current observations through complementary fusion, outputting depth estimates, and autoregressively updating memory. This enables cross-frame feature reuse with bounded accuracy degradation. With 3.83M trainable fast-path parameters and a 97.5M frozen slow path, AsyncMDE's fast path operates at 237 FPS on an RTX 4090, recovering 77% of the accuracy gap to the foundation model. Across indoor static, dynamic, and synthetic extreme-motion benchmarks, AsyncMDE degrades predictably and reaches 161 FPS fast-path inference on a TensorRT-optimized Jetson AGX Orin, supporting real-time edge deployment.

cs.RO↗

arXiv2026

DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either prune or merge tokens uniformly, degrading the spatial reasoning essential for robotic control. We present DepthCache, a training-free framework that leverages depth as a structural prior for visual token compression. It partitions observations into depth-based regions and applies spatially differentiated merge ratios, preserving the near-field workspace while compressing the distant background. To exploit temporal redundancy, DepthCache distributes the merging process across consecutive frames, ensuring consistent representations while reducing per-step computation. A motion-adaptive pipeline further optimizes auxiliary view compression based on end-effector dynamics. The framework requires no model modification, generalizing across diverse VLA architectures. On the LIBERO benchmark, DepthCache achieves up to 1.28x inference speedup with less than 1% average success rate degradation across three VLA models (pi_0.5, OpenVLA, GR00T), whereas pruning and merging baselines incur 4--24% degradation at comparable compression. Real-world experiments on a physical manipulator demonstrate that DepthCache enables faster task throughput and more responsive closed-loop control in latency-sensitive scenarios.

cs.RO↗

arXiv2026

Structured Personality Control and Adaptation for LLM Agents

Large Language Models (LLMs) are increasingly shaping human-computer interaction (HCI), from personalized assistants to social simulations. Beyond language competence, researchers are exploring whether LLMs can exhibit human-like characteristics that influence engagement, decision-making, and perceived realism. Personality, in particular, is critical, yet existing approaches often struggle to achieve both nuanced and adaptable expression. We present a framework that models LLM personality via Jungian psychological types, integrating three mechanisms: a dominant-auxiliary coordination mechanism for coherent core expression, a reinforcement-compensation mechanism for temporary adaptation to context, and a reflection mechanism that drives long-term personality evolution. This design allows the agent to maintain nuanced traits while dynamically adjusting to interaction demands and gradually updating its underlying structure. Personality alignment is evaluated using Myers-Briggs Type Indicator questionnaires and tested under diverse challenge scenarios as a preliminary structured assessment. Findings suggest that evolving, personality-aware LLMs can support coherent, context-sensitive interactions, enabling naturalistic agent design in HCI.

cs.AI↗

arXiv2026

SoK: Stablecoins in Retail Payments

Stablecoins have emerged as a rapidly growing digital payment instrument, raising the question of whether blockchain-based settlement can function as a substitute for incumbent card networks in retail payments. This Systematization of Knowledge (SoK) provides a systematic comparison between stablecoin payment arrangements and card networks by situating both within a unified analytical framework. We first map their respective payment infrastructures, participant roles, and transaction lifecycles, highlighting fundamental differences in how authorization, settlement, and recourse are organized. Building on this mapping, we introduce the CLEAR framework, which evaluates retail payment systems across five dimensions: cost, legality, experience, architecture, and reach. Our analysis shows that stablecoins deliver efficient, continuous, and programmable settlement, often compressing rail-level merchant fees and enabling 24/7 value transfer. However, these advantages are accompanied by an inversion of the traditional pricing and risk-allocation structure. Card networks internalize consumer-side frictions through subsidies, standardized liability rules, and post-transaction recourse, thereby supporting mass-market adoption. Stablecoin arrangements, by contrast, externalize transaction fees, error prevention, and dispute resolution to users, intermediaries, and courts, resulting in weaker consumer protection, higher cognitive burden at the point of interaction, and fragmented acceptance. Accordingly, stablecoins exhibit a conditional comparative advantage in closed-loop environments, cross-border corridors, and high-friction payment contexts, but remain structurally disadvantaged as open-loop retail payment instruments.

q-fin.GN↗

arXiv2025

Measuring Memecoin Fragility

Memecoins, emerging from internet culture and community-driven narratives, have rapidly evolved into a unique class of crypto assets. Unlike technology-driven cryptocurrencies, their market dynamics are primarily shaped by viral social media diffusion, celebrity influence, and speculative capital inflows. To capture the distinctive vulnerabilities of these ecosystems, we present the first Memecoin Ecosystem Fragility Framework (ME2F). ME2F formalizes memecoin risks in three dimensions: i) Volatility Dynamics Score capturing persistent and extreme price swings together with spillover from base chains; ii) Whale Dominance Score quantifying ownership concentration among top holders; and iii) Sentiment Amplification Score measuring the impact of attention-driven shocks on market stability. We apply ME2F to representative tokens (over 65% market share) and show that fragility is not evenly distributed across the ecosystem. Politically themed tokens such as TRUMP, MELANIA, and LIBRA concentrate the highest risks, combining volatility, ownership concentration, and sensitivity to sentiment shocks. Established memecoins such as DOGE, SHIB, and PEPE fall into an intermediate range. Benchmark tokens ETH and SOL remain consistently resilient due to deeper liquidity and institutional participation. Our findings provide the first ecosystem-level evidence of memecoin fragility and highlight governance implications for enhancing market resilience in the Web3 era.

cs.CR↗

arXiv2025

Learning Hierarchical Interaction for Accurate Molecular Property Prediction

Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning models, such as Graph Neural Networks (GNNs) and Transformers, to predict these molecular properties by learning from diverse chemical information. However, these models often fail to efficiently capture and utilize the hierarchical nature of molecular structures, and often lack mechanisms for effective interaction among multi-level features. To address these limitations, we propose a Hierarchical Interaction Message Passing Mechanism, which serves as the foundation of our novel model, the Hierarchical Interaction Message Net (HimNet). Our method enables interaction-aware representation learning across atomic, motif, and molecular levels via hierarchical attention-guided message passing. This design allows HimNet to effectively balance global and local information, ensuring rich and task-relevant feature extraction for downstream property prediction tasks, such as Blood-Brain Barrier Permeability (BBBP). We systematically evaluate HimNet on eleven datasets, including eight widely-used MoleculeNet benchmarks and three challenging, high-value datasets for metabolic stability, malaria activity, and liver microsomal clearance, covering a broad range of pharmacologically relevant properties. Extensive experiments demonstrate that HimNet achieves the best or near-best performance in most molecular property prediction tasks. Furthermore, our method exhibits promising hierarchical interpretability, aligning well with chemical intuition on representative molecules. We believe that HimNet offers an accurate and efficient solution for molecular activity and ADMET property prediction, contributing to advanced decision-making in the early stages of drug discovery.

q-bio.BM↗