Yafei Liu

Wenge Liu, Yi Cheng, Hao Wang et al.

With the rise of telemedicine, the task of developing Dialogue Systems for Medical Diagnosis (DSMD) has received much attention in recent years. Different from early researches that needed to rely on extra human resources and expertise to help construct the system, recent researches focused on how to build DSMD in a purely data-driven manner. However, the previous data-driven DSMD methods largely overlooked the system interpretability, which is critical for a medical application, and they also suffered from the data sparsity issue at the same time. In this paper, we explore how to bring interpretability to data-driven DSMD. Specifically, we propose a more interpretable decision process to implement the dialogue manager of DSMD by reasonably mimicking real doctors' inquiry logics, and we devise a model with highly transparent components to conduct the inference. Moreover, we collect a new DSMD dataset, which has a much larger scale, more diverse patterns and is of higher quality than the existing ones. The experiments show that our method obtains 7.7%, 10.0%, 3.0% absolute improvement in diagnosis accuracy respectively on three datasets, demonstrating the effectiveness of its rational decision process and model design. Our codes and the GMD-12 dataset are available at https://github.com/lwgkzl/BR-Agent.

Feiding, Yongkang Zhang, Yuhao Liao et al.

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the linkage between visual evidence and intermediate steps and often causing unstable optimization and visual hallucinations. We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories, explicitly marking the key positions that require correction. Without costly large-scale step-by-step human annotations, our method enables process-level visual alignment and can be seamlessly integrated into existing GRPO-like frameworks. Experiments on multimodal reasoning benchmarks including MMMStar and MathVista show an average 3% improvement under matched compute budgets. Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.

Ningkang Peng, Qianfeng Yu, Xiaoqian Peng et al.

Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for achieving OOD detection. Existing prototype-based learning methods generally rely on a fixed number of prototypes. This static assumption fails to adapt to the inherent complexity differences across various categories. Currently, there is still a lack of a mechanism that can adaptively adjust the number of prototypes based on data complexity. Inspired by the processes of cell birth and death in biology, we propose a novel method named PID (Prototype bIrth and Death) to adaptively adjust the prototype count based on data complexity. This method relies on two dynamic mechanisms during the training process: prototype birth and prototype death. The birth mechanism instantiates new prototypes in data regions with insufficient representation by identifying the overload level of existing prototypes, thereby meticulously capturing intra-class substructures. Conversely, the death mechanism reinforces the decision boundary by pruning prototypes with ambiguous class boundaries through evaluating their discriminability. Through birth and death, the number of prototypes can be dynamically adjusted according to the data complexity, leading to the learning of more compact and better-separated In-Distribution (ID) embeddings, which significantly enhances the capability to detect OOD samples. Experiments demonstrate that our dynamic method, PID, significantly outperforms existing methods on benchmarks such as CIFAR-100, achieving State-of-the-Art (SOTA) performance, especially on the FPR95 metric.

Zhiwei Jin, Xiaohui Song, Nan Wang et al.

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of edge devices such as mobile phones. This paper introduces AndesVL, a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders. We comprehensively outline the model architectures, training pipeline, and training data of AndesVL, which achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale. Furthermore, we introduce a 1+N LoRA architecture alongside a Quantization-Aware LoRA Fine-Tuning (QALFT) framework to facilitate efficient task adaptation and model compression during mobile-side deployment of AndesVL. Moreover, utilizing our cache eviction algorithm -- OKV -- along with customized speculative decoding and compression strategies, we achieve a 6.7x peak decoding speedup ratio, up to 30.9% memory reduction, and 1.8 bits-per-weight when deploying AndesVL-4B on MediaTek Dimensity 9500 chips. We release all models on https://huggingface.co/OPPOer.

Yifan Wang, Yafei Liu, Chufan Shi et al.

Instruction tuning effectively optimizes Large Language Models (LLMs) for downstream tasks. Due to the changing environment in real-life applications, LLMs necessitate continual task-specific adaptation without catastrophic forgetting. Considering the heavy computational cost, replay-based Continual Learning (CL) methods are the simplest and most widely used for LLMs to address the forgetting issue. However, traditional replay-based methods do not fully utilize instructions to customize the replay strategy. In this work, we propose a novel paradigm called Instruction-based Continual Learning (InsCL). InsCL dynamically replays previous data based on task similarity, calculated by Wasserstein Distance with instructions. Moreover, we further introduce an Instruction Information Metric (InsInfo) to quantify the complexity and diversity of instructions. According to InsInfo, InsCL guides the replay process more inclined to high-quality data. We conduct extensive experiments over 16 tasks with different training orders, observing consistent performance improvements of InsCL. When all tasks have been trained, InsCL achieves performance gains of 3.0 Relative Gain compared with Random Replay, and 27.96 Relative Gain compared with No Replay.

Ningkang Peng, Qianfeng Yu, Yuhao Zhang et al.

Out-of-Distribution (OOD) detection under long-tailed distributions is a highly challenging task because the scarcity of samples in tail classes leads to blurred decision boundaries in the feature space. Current state-of-the-art (sota) methods typically employ Outlier Exposure (OE) strategies, relying on large-scale real external datasets (such as 80 Million Tiny Images) to regularize the feature space. However, this dependence on external data often becomes infeasible in practical deployment due to high data acquisition costs and privacy sensitivity. To this end, we propose a novel data-free framework aimed at completely eliminating reliance on external datasets while maintaining superior detection performance. We introduce a Geometry-guided virtual Outlier Synthesis (GOS) strategy that models statistical properties using the von Mises-Fisher (vMF) distribution on a hypersphere. Specifically, we locate a low-likelihood annulus in the feature space and perform directional sampling of virtual outliers in this region. Simultaneously, we introduce a new Dual-Granularity Semantic Loss (DGS) that utilizes contrastive learning to maximize the distinction between in-distribution (ID) features and these synthesized boundary outliers. Extensive experiments on benchmarks such as CIFAR-LT demonstrate that our method outperforms sota approaches that utilize external real images.

Nan Wang, Yafei Liu, Chen Chen et al.

Recent advancements in language modeling have enabled the translation of natural language into code, and the use of execution feedback to improve code generation. However, these methods often rely heavily on pre-existing test cases, which may not always be available or comprehensive. In this work, we propose a novel approach that concurrently trains a code generation model and a test generation model, utilizing execution feedback to refine and enhance the performance of both. We introduce two strategies for test and code data augmentation and a new scoring function for code and test ranking. We experiment on the APPS dataset and demonstrate that our approach can effectively generate and augment test cases, filter and synthesize correct code solutions, and rank the quality of generated code and tests. The results demonstrate that our models, when iteratively trained with an increasing number of test cases and code solutions, outperform those trained on the original dataset.

Zhengxu Hou, Bang Liu, Ruihui Zhao et al.

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs. In this paper, we propose a multi-level reward modeling approach that factorizes a reward into a three-level hierarchy: domain, act, and slot. Based on inverse adversarial reinforcement learning, our designed reward model can provide more accurate and explainable reward signals for state-action pairs.Extensive evaluations show that our approach can be applied to a wide range of reinforcement learning-based dialog systems and significantly improves both the performance and the speed of convergence.