Searcharxiv⌕ Search

arXiv subjects

Pengyu Huang

Publications and source records attributed to Pengyu Huang.

4 recordsLinked to original sources

Layer Roles Matter: Mitigating Modality Imbalance in Multimodal Emotion Reasoning via Adaptive Layer Profiling

Multimodal Emotion Reasoning (MER) requires perceiving and integrating emotion cues from multiple modalities. Recent advances increasingly leverage Multimodal Large Language Models (MLLMs) to enhance reasoning capacity. However, due to the inherent heterogeneity in conveying emotions across modalities, these models often suffer from modality imbalance and confront flawed emotion understanding. In this paper, we conduct an in-depth analysis on MER models and uncover two key empirical insights. (i) In MER, modality imbalance manifests two distinct failure modes: unimodal over-reliance and insufficient cross-modal utilization, which call for different intervention strategies. (ii) MLLM layers exhibit implicit functional hierarchies in multimodal emotion processing, playing separable roles in stabilizing unimodal representations and integrating cross-modal information. Motivated by these observations, we propose a Layer-Aware Modality Rebalancing (LAMR) framework by explicitly aligning intervention strategies with layer roles. Specifically, we first introduce two quantized metrics for adaptive layer role profiling. In each layer, Modality Entropy (ME) measures the dispersion of modality contributions, and Cross-modal Intensity (CMI) captures the strength of cross-modal interactions. Then, we respectively enhance modality equilibrium in stabilization layers and cross-modal propagation in integration layers. Extensive experiments on two comprehensive MER benchmarks demonstrate that LAMR effectively mitigates modality imbalance and improves emotion reasoning across diverse MLLM backbones, without additional training.

cs.AI↗

Evolving Support Priorities in Empathetic Reinforcement Learning

We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned rubric priorities systematically vary across dialogue stages and user emotions, demonstrating that CARE adapts what is rewarded as support needs evolve. Code is available at https://asa13opp.github.io/CARE-project-page.

cs.AI↗

Squeezing Edge Performance: A Sensitivity-Aware Container Management for Heterogeneous Tasks

Edge computing enables latency-critical applications to process data close to end devices, yet task heterogeneity and limited resources pose significant challenges to efficient orchestration. This paper presents a measurement-driven, container-based resource management framework for intra-node optimization on a single edge server hosting multiple heterogeneous applications. Extensive profiling experiments are conducted to derive a nonlinear fitting model that characterizes the relationship among CPU/memory allocations and processing latency across diverse workloads, enabling reliable estimation of performance under varying configurations and providing quantitative support for subsequent optimization. Using this model and a queueing-based delay formulation, we formulate a mixed-integer nonlinear programming (MINLP) problem to jointly minimize system latency and power consumption, which is shown to be NP-hard. The problem is decomposed into tractable convex subproblems and solved through a two-stage container-based resource management scheme (CRMS) combining convex optimization and greedy refinement. The proposed scheme achieves polynomial-time complexity and supports quasi-dynamic execution under global resource constraints. Simulation results demonstrate that CRMS reduces latency by over 14\% and improves energy efficiency compared with heuristic and search-based baselines, offering a practical and scalable solution for heterogeneous edge environments with dynamic workload characteristics.

cs.DC↗

Globalization Process in Emerging Capital Markets -- Lessons and Implications to China

Since 2002 when China first introduced QFII (Qualified Foreign Institutional Investors) system, QFII has been developing in China for 14 years, during when RQFII, Shanghai-Hongkong Stock Connect Program, Shanghai-London Stock Connect Program furthur broadened the avenue for foreign capital to invest in Chinese Security Market. As FTA (Free Trade Area) Financial Reform Program emerged, RMB (CNY) Capital Project is likely to make the currency exchangeable. With the success in QFII, RQFII and Shanghai-Hongkong Stock Connect Program, China's long term advantage in interest rate, and the relatively low stock index value after the recent stock market crashes in mid 2015 and early 2016, foreign capitals' demand for Chinese market to loosen its restrictions continually increases. This article picks the three most representative emerging capital markets in the world, namely Taiwan, Korea and India, by comparing and analyzing their paths of globalization, attempts to shed light on China's next steps regarding globalization.

q-fin.GN↗