Adaptive Dependency-aware Prompt Optimization Framework for Multi-Step LLM Pipeline

Multi-step LLM pipelines invoke large language models multiple times in a structured sequence and can effectively solve complex tasks, but their performance heavily depends on the prompts used at each step. Jointly optimizing these prompts is difficult due to missing step-level supervision and inter-step dependencies. Existing end-to-end prompt optimization methods struggle under these conditions and often yield suboptimal or unstable updates. We propose ADOPT, an Adaptive Dependency-aware Prompt Optimization framework for multi-step LLM pipelines. ADOPT explicitly models the dependency between each LLM step and the final task outcome, enabling precise text-gradient estimation analogous to computing analytical derivatives. It decouples textual gradient estimation from gradient updates, reducing multi-prompt optimization to flexible single-prompt optimization steps, and employs a Shapley-based mechanism to adaptively allocate optimization resources. Experiments on real-world datasets and diverse pipeline structures show that ADOPT is effective and robust, consistently outperforming state-of-the-art prompt optimization baselines.

FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment

Mixture-of-Experts (MoE) models enable scalable neural networks through conditional computation. However, their deployment with federated learning (FL) faces two critical challenges: 1) resource-constrained edge devices cannot store full expert sets, and 2) non-IID data distributions cause severe expert load imbalance that degrades model performance. To this end, we propose \textbf{FLEX-MoE}, a novel federated MoE framework that jointly optimizes expert assignment and load balancing under limited client capacity. Specifically, our approach introduces client-expert fitness scores that quantify the expert suitability for local datasets through training feedback, and employs an optimization-based algorithm to maximize client-expert specialization while enforcing balanced expert utilization system-wide. Unlike existing greedy methods that focus solely on personalization while ignoring load imbalance, our FLEX-MoE is capable of addressing the expert utilization skew, which is particularly severe in FL settings with heterogeneous data. Our comprehensive experiments on three different datasets demonstrate the superior performance of the proposed FLEX-MoE, together with its ability to maintain balanced expert utilization across diverse resource-constrained scenarios.

DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis

Whole Slide Images (WSIs) are typically analyzed using multiple instance learning (MIL) methods. However, the scale and heterogeneity of WSIs generate highly redundant and dispersed information, making it difficult to identify and integrate discriminative signals. Existing MIL methods either fail to discard uninformative cues effectively or have limited ability to consolidate relevant features from multiple patches, which restricts their performance on large and heterogeneous WSIs. To address this issue, we propose DeltaMIL, a novel MIL framework that explicitly selects semantically relevant regions and integrates the discriminative information from WSIs. Our method leverages the gated delta rule to efficiently filter and integrate information through a block combining forgetting and memory mechanisms. The delta mechanism dynamically updates the memory by removing old values and inserting new ones according to their correlation with the current patch. The gating mechanism further enables rapid forgetting of irrelevant signals. Additionally, DeltaMIL integrates a complementary local pattern mixing mechanism to retain fine-grained pathological locality. Our design enhances the extraction of meaningful cues and suppresses redundant or noisy information, which improves the model's robustness and discriminative power. Experiments demonstrate that DeltaMIL achieves state-of-the-art performance. Specifically, for survival prediction, DeltaMIL improves performance by 3.69\% using ResNet-50 features and 2.36\% using UNI features. For slide-level classification, it increases accuracy by 3.09\% with ResNet-50 features and 3.75\% with UNI features. These results demonstrate the strong and consistent performance of DeltaMIL across diverse WSI tasks.

Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination

Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis.

Never Too Rigid to Reach: Adaptive Virtual Model Control with LLM- and Lyapunov-Based Reinforcement Learning

Robotic arms are increasingly deployed in uncertain environments, yet conventional control pipelines often become rigid and brittle when exposed to perturbations or incomplete information. Virtual Model Control (VMC) enables compliant behaviors by embedding virtual forces and mapping them into joint torques, but its reliance on fixed parameters and limited coordination among virtual components constrains adaptability and may undermine stability as task objectives evolve. To address these limitations, we propose Adaptive VMC with Large Language Model (LLM)- and Lyapunov-Based Reinforcement Learning (RL), which preserves the physical interpretability of VMC while supporting stability-guaranteed online adaptation. The LLM provides structured priors and high-level reasoning that enhance coordination among virtual components, improve sample efficiency, and facilitate flexible adjustment to varying task requirements. Complementarily, Lyapunov-based RL enforces theoretical stability constraints, ensuring safe and reliable adaptation under uncertainty. Extensive simulations on a 7-DoF Panda arm demonstrate that our approach effectively balances competing objectives in dynamic tasks, achieving superior performance while highlighting the synergistic benefits of LLM guidance and Lyapunov-constrained adaptation.

Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

There is a growing demand for deploying large generative AI models on mobile devices. For recent popular video generative models, however, the Variational AutoEncoder (VAE) represents one of the major computational bottlenecks. Both large parameter sizes and mismatched kernels cause out-of-memory errors or extremely slow inference on mobile devices. To address this, we propose a low-cost solution that efficiently transfers widely used video VAEs to mobile devices. (1) We analyze redundancy in existing VAE architectures and get empirical design insights. By integrating 3D depthwise separable convolutions into our model, we significantly reduce the number of parameters. (2) We observe that the upsampling techniques in mainstream video VAEs are poorly suited to mobile hardware and form the main bottleneck. In response, we propose a decoupled 3D pixel shuffle scheme that slashes end-to-end delay. Building upon these, we develop a universal mobile-oriented VAE decoder, Turbo-VAED. (3) We propose an efficient VAE decoder training method. Since only the decoder is used during deployment, we distill it to Turbo-VAED instead of retraining the full VAE, enabling fast mobile adaptation with minimal performance loss. To our knowledge, our method enables real-time 720p video VAE decoding on mobile devices for the first time. This approach is widely applicable to most video VAEs. When integrated into four representative models, with training cost as low as $95, it accelerates original VAEs by up to 84.5x at 720p resolution on GPUs, uses as low as 17.5% of original parameter count, and retains 96.9% of the original reconstruction quality. Compared to mobile-optimized VAEs, Turbo-VAED achieves a 2.9x speedup in FPS and better reconstruction quality on the iPhone 16 Pro. The code and models will soon be available at https://github.com/hustvl/Turbo-VAED.

CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervision

The integration of contextual information has significantly enhanced the performance of large language models (LLMs) on knowledge-intensive tasks. However, existing methods often overlook a critical challenge: the credibility of context documents can vary widely, potentially leading to the propagation of unreliable information. In this paper, we introduce CrEst, a novel weakly supervised framework for assessing the credibility of context documents during LLM inference--without requiring manual annotations. Our approach is grounded in the insight that credible documents tend to exhibit higher semantic coherence with other credible documents, enabling automated credibility estimation through inter-document agreement. To incorporate credibility into LLM inference, we propose two integration strategies: a black-box approach for models without access to internal weights or activations, and a white-box method that directly modifies attention mechanisms. Extensive experiments across three model architectures and five datasets demonstrate that CrEst consistently outperforms strong baselines, achieving up to a 26.86% improvement in accuracy and a 3.49% increase in F1 score. Further analysis shows that CrEst maintains robust performance even under high-noise conditions.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision tasks. We provide a mathematical definition of generalized attention and formulate both vanilla softmax attention and linear attention within the general framework. We prove that generalized attention disperses, that is, as the number of keys tends to infinity, the query assigns equal weights to all keys. Motivated by the dispersion property and recent development of Mamba form of attention, we design Scalable and Efficient Mamba like Attention (SEMA) which utilizes token localization to avoid dispersion and maintain focusing, complemented by theoretically consistent arithmetic averaging to capture global aspect of attention. We support our approach on Imagenet-1k where classification results show that SEMA is a scalable and effective alternative beyond linear attention, outperforming recent vision Mamba models on increasingly larger scales of images at similar model parameter sizes.

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing

The rapid advancements in large language models (LLMs) have led to the emergence of routing techniques, which aim to efficiently select the optimal LLM from diverse candidates to tackle specific tasks, optimizing performance while reducing costs. Current LLM routing methods are limited in effectiveness due to insufficient exploration of the intrinsic connection between user queries and the characteristics of LLMs. To address this issue, in this paper, we present RadialRouter, a novel framework for LLM routing which employs a lightweight Transformer-based backbone with a radial structure named RadialFormer to articulate the query-LLMs relationship. The optimal LLM selection is performed based on the final states of RadialFormer. The pipeline is further refined by an objective function that combines Kullback-Leibler divergence with the query-query contrastive loss to enhance robustness. Experimental results on RouterBench show that RadialRouter significantly outperforms existing routing methods by 9.2\% and 5.8\% in the Balance and Cost First scenarios, respectively. Additionally, its adaptability toward different performance-cost trade-offs and the dynamic LLM pool demonstrates practical application potential.

ELDeR: Getting Efficient LLMs through Data-Driven Regularized Layer-wise Pruning

The deployment of Large language models (LLMs) in many fields is largely hindered by their high computational and memory costs. Recent studies suggest that LLMs exhibit sparsity, which can be used for pruning. Previous pruning methods typically follow a prune-then-finetune paradigm. Since the pruned parts still contain valuable information, statically removing them without updating the remaining parameters often results in irreversible performance degradation, requiring costly recovery fine-tuning (RFT) to maintain performance. To address this, we propose a novel paradigm: first apply regularization, then prune. Based on this paradigm, we propose ELDeR: Getting Efficient LLMs through Data-Driven Regularized Layer-wise Pruning. We multiply the output of each transformer layer by an initial weight, then we iteratively learn the weights of each transformer layer by using a small amount of data in a simple way. After that, we apply regularization to the difference between the output and input of the layers with smaller weights, forcing the information to be transferred to the remaining layers. Compared with direct pruning, ELDeR reduces the information loss caused by direct parameter removal, thus better preserving the model's language modeling ability. Experimental results show that ELDeR achieves superior performance compared with powerful layer-wise structured pruning methods, while greatly reducing RFT computational costs. Since ELDeR is a layer-wise pruning method, its end-to-end acceleration effect is obvious, making it a promising technique for efficient LLMs.