arXiv subjects

Qizheng Yang

Publications and source records attributed to Qizheng Yang.

6 recordsLinked to original sources

arXiv2026

HADIS: A Hybrid Architecture for Query-Aware Diffusion Model Serving

Query-aware model serving routes queries through cascades of increasing cost to balance quality and throughput. Existing cascade systems force all queries through the lightweight stage, wasting resources on hard queries, and fix the model pair regardless of workload dynamics. In text-to-image diffusion serving, this waste is severe: quality is assessable only after full generation completes, and rejected lightweight outputs cannot be reused by the heavyweight model. HADIS is a diffusion model serving system built on a hybrid cascade architecture that combines a pre-generation router (bypassing the lightweight model for predicted-hard queries) with a post-generation discriminator (catching false-easy cases). The hybrid architecture creates a coupled optimization space: routing thresholds, model-pair selection, and GPU allocation must be jointly adapted as workloads shift. HADIS reduces this space by establishing that two-model cascades match the Pareto frontier of deeper cascades, pruning candidates into a compact Pareto-optimal configuration table offline, and re-optimizing allocation at runtime via an online MILP. The hybrid design dominates both router-only and discriminator-only alternatives under mild accuracy conditions. On a 16-GPU cluster with real-world traces, HADIS improves response quality by up to 35% and reduces SLO violations by 2.7-45$\times$ compared to baselines.

cs.DC↗

arXiv2026

PINEAPPLE: Physics-Informed Neuro-Evolution Algorithm for Prognostic Parameter Inference in Lithium-Ion Battery Electrodes

Accurate, real-time, yet non-destructive estimation of internal states in lithium-ion batteries is critical for predicting degradation, optimizing usage strategies, and extending operational lifespan. Here, we introduce PINEAPPLE (Physics-Informed Neuro-Evolution Algorithm for Prognostic Parameter inference in Lithium-ion battery Electrodes), a novel framework that integrates physics-informed neural networks (PINNs) with an evolutionary search algorithm to enable rapid, scalable, and interpretable parameter inference with potential for application to next-generation batteries. The meta-learned PINN utilizes fundamental physics principles to achieve accurate zero-shot prediction of electrode behavior with test errors below 0.1$\%$ while maintaining an order-of-magnitude speed-up over conventional solvers. PINEAPPLE demonstrates robust parameter inference solely from voltage-time discharge curves across multiple batteries from the open-source CALCE repository, recovering the evolution of key internal state parameters such as Li-ion diffusion coefficients across usage cycles. Notably, the inferred cycle-dependent evolution of these parameters exhibit consistent trends across different batteries without any customized degradation physics-embedded heuristic, highlighting the effective regularizing effect and robustness that can be conferred through incorporation of fundamental physics in PINEAPPLE. By enabling computationally efficient, real-time parameter estimation, PINEAPPLE offers a promising route towards the non-destructive, physics-based characterization of inter-cell and intra-cell variability of battery modules and battery packs, thereby unlocking new opportunities for downstream on-the-fly needs in next-generation battery management systems such as individual cell-scale state-of-health diagnostics.

cs.CE↗

arXiv2025

Unbiased Visual Reasoning with Controlled Visual Inputs

End-to-end Vision-language Models (VLMs) often answer visual questions by exploiting spurious correlations instead of causal visual evidence, and can become more shortcut-prone when fine-tuned. We introduce VISTA (Visual-Information Separation for Text-based Analysis), a modular framework that decouples perception from reasoning via an explicit information bottleneck. A frozen VLM sensor is restricted to short, objective perception queries, while a text-only LLM reasoner decomposes each question, plans queries, and aggregates visual facts in natural language. This controlled interface defines a reward-aligned environment for training unbiased visual reasoning with reinforcement learning. Instantiated with Qwen2.5-VL and Llama3.2-Vision sensors, and trained with GRPO from only 641 curated multi-step questions, VISTA significantly improves robustness to real-world spurious correlations on SpuriVerse (+16.29% with Qwen-2.5-VL-7B and +6.77% with Llama-3.2-Vision-11B), while remaining competitive on MMVP and a balanced SeedBench subset. VISTA transfers robustly across unseen VLM sensors and is able to recognize and recover from VLM perception failures. Human analysis further shows that VISTA's reasoning traces are more neutral, less reliant on spurious attributes, and more explicitly grounded in visual evidence than end-to-end VLM baselines.

cs.CV↗

arXiv2025

DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling

Text-to-image generation using diffusion models has gained increasing popularity due to their ability to produce high-quality, realistic images based on text prompts. However, efficiently serving these models is challenging due to their computation-intensive nature and the variation in query demands. In this paper, we aim to address both problems simultaneously through query-aware model scaling. The core idea is to construct model cascades so that easy queries can be processed by more lightweight diffusion models without compromising image generation quality. Based on this concept, we develop an end-to-end text-to-image diffusion model serving system, DiffServe, which automatically constructs model cascades from available diffusion model variants and allocates resources dynamically in response to demand fluctuations. Our empirical evaluations demonstrate that DiffServe achieves up to 24% improvement in response quality while maintaining 19-70% lower latency violation rates compared to state-of-the-art model serving systems.

cs.DC↗

arXiv2024

AdapMTL: Adaptive Pruning Framework for Multitask Learning Model

In the domain of multimedia and multimodal processing, the efficient handling of diverse data streams such as images, video, and sensor data is paramount. Model compression and multitask learning (MTL) are crucial in this field, offering the potential to address the resource-intensive demands of processing and interpreting multiple forms of media simultaneously. However, effectively compressing a multitask model presents significant challenges due to the complexities of balancing sparsity allocation and accuracy performance across multiple tasks. To tackle these challenges, we propose AdapMTL, an adaptive pruning framework for MTL models. AdapMTL leverages multiple learnable soft thresholds independently assigned to the shared backbone and the task-specific heads to capture the nuances in different components' sensitivity to pruning. During training, it co-optimizes the soft thresholds and MTL model weights to automatically determine the suitable sparsity level at each component to achieve both high task accuracy and high overall sparsity. It further incorporates an adaptive weighting mechanism that dynamically adjusts the importance of task-specific losses based on each task's robustness to pruning. We demonstrate the effectiveness of AdapMTL through comprehensive experiments on popular multitask datasets, namely NYU-v2 and Tiny-Taskonomy, with different architectures, showcasing superior performance compared to state-of-the-art pruning methods.

cs.CV↗

arXiv2022

Rethinking Hard-Parameter Sharing in Multi-Domain Learning

Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sharing practice is to share the bottom layers of a deep neural network among domains while using separate top layers for each domain. In this work, we revisit this common practice via an empirical study on image classification tasks from a diverse set of visual domains and make two surprising observations. (1) Using separate bottom-layer parameters could achieve significantly better performance than the common practice and this phenomenon holds with different experimental settings. (2) A multi-domain model with a small proportion of domain-specific parameters from bottom layers can achieve competitive performance with independent models trained on each domain separately. Our observations suggest that people adopt the new strategy of using separate bottom-layer parameters as a stronger baseline for model design in MDL.

cs.LG↗