Recent advances in reinforcement learning (RL) methods such as Grouped Relative Policy Optimization (GRPO) have strengthened the reasoning capabilities of Large Vision-Language Models (LVLMs). However, due to the inherent entanglement between visual and textual modalities, applying GRPO to LVLMs often leads to reward convergence across different responses to the same sample as training progresses, hindering effective gradient updates and causing the enhancement of chain-of-thought reasoning to stagnate or even collapse. To address this issue, we propose a progressive instruction evolution framework, EvolvedGRPO, to gradually generate more complex questions via editing instructions in an adversarial way, progressively aligned with the model's evolving capabilities. Specifically, we design two instruction editing strategies across modalities, incorporating incrementally increasing editing instructions and RL-based adversarial data augmentation to improve the effectiveness of model training. To address GRPO's limitations on overly difficult problems, we first train on basic subproblem versions of complex multi-modal questions in both the visual and textual modalities, progressively increasing difficulty to enable prefix-style process rewards, effectively combining the strengths of both process rewards and group-wise relative rewards. Finally, EvolvedGRPO achieves state-of-the-art performance among open-source RL models on multi-modal reasoning tasks, even approaching the closed-source GPT-4o in reasoning capabilities, and demonstrates better performance on unseen LVLM general benchmarks.

This paper explores the weakly-supervised referring image segmentation (WRIS) problem, and focuses on a challenging setup where target localization is learned directly from image-text pairs. We note that the input text description typically already contains detailed information on how to localize the target object, and we also observe that humans often follow a step-by-step comprehension process (\ie, progressively utilizing target-related attributes and relations as cues) to identify the target object. Hence, we propose a novel Progressive Comprehension Network (PCNet) to leverage target-related textual cues from the input description for progressively localizing the target object.Specifically, we first use a Large Language Model (LLM) to decompose the input text description into short phrases. These short phrases are taken as target-related cues and fed into a Conditional Referring Module (CRM) in multiple stages, to allow updating the referring text embedding and enhance the response map for target localization in a multi-stage manner.Based on the CRM, we then propose a Region-aware Shrinking (RaS) loss to constrain the visual localization to be conducted progressively in a coarse-to-fine manner across different stages.Finally, we introduce an Instance-aware Disambiguation (IaD) loss to suppress instance localization ambiguity by differentiating overlapping response maps generated by different referring texts on the same image. Extensive experiments show that our method outperforms SOTA methods on three common benchmarks.

Details regarding the datasets used in the experiments are included in Table 2. For Yang et al. [2020], we progressively doubled the number of regions searched which is the only adjustable hyperparameter. To make this figure, we run all the experiments (all attacks, datasets, and choices of hyperparameters)onaserverwith40coresofIntel(R)Xeon(R)Gold6230CPU@2.10GHz. This outcome is seemingly perplexing than the previous one. We explain it for different values ofm, namely the small-mandthelarge-mregions.

In this work, we focus on obtaining supervision from text descriptions only.

Deep learning models have become increasingly large and complex, resulting in higher memory consumption and computational demands. Consequently, model loading times and initial inference latency have increased, posing significant challenges in mobile and latency-sensitive environments where frequent model loading and unloading are required, which directly impacts user experience. While Knowledge Distillation (KD) offers a solution by compressing large teacher models into smaller student ones, it often comes at the cost of reduced performance. To address this trade-off, we propose Progressive Weight Loading (PWL), a novel technique that enables fast initial inference by first deploying a lightweight student model, then incrementally replacing its layers with those of a pre-trained teacher model. To support seamless layer substitution, we introduce a training method that not only aligns intermediate feature representations between student and teacher layers, but also improves the overall output performance of the student model. Our experiments on VGG, ResNet, and ViT architectures demonstrate that models trained with PWL maintain competitive distillation performance and gradually improve accuracy as teacher layers are loaded--matching the final accuracy of the full teacher model without compromising initial inference speed. This makes PWL particularly suited for dynamic, resource-constrained deployments where both responsiveness and performance are critical.

Recent work has framed constrained text generation with autoregressive language models as a probabilistic inference problem. Among these, Zhao et al. (2024) introduced a promising approach based on twisted Sequential Monte Carlo, which incorporates learned twist functions and twist-induced proposals to guide the generation process. However, in constrained generation settings where the target distribution concentrates on outputs that are unlikely under the base model, learning becomes challenging due to sparse and uninformative reward signals. We show that iteratively refining the base model through self-distillation alleviates this issue by making the model progressively more aligned with the target, leading to substantial gains in generation quality.