MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation

Medical report generation (MRG) aims to automatically derive radiology-style reports from medical images to aid in clinical decision-making. However, existing methods often generate text that mimics the linguistic style of radiologists but fails to guarantee clinical correctness, because they are trained on token-level objectives which focus on word-choice and sentence structure rather than actual medical accuracy. We propose a semantic-driven reinforcement learning (SRL) method for medical report generation, adopted on a large vision-language model (LVLM). SRL adopts Group Relative Policy Optimization (GRPO) to encourage clinical-correctness-guided learning beyond imitation of language style. Specifically, we optimise a report-level reward: a margin-based cosine similarity (MCCS) computed between key radiological findings extracted from generated and reference reports, thereby directly aligning clinical-label agreement and improving semantic correctness. A lightweight reasoning format constraint further guides the model to generate structured "thinking report" outputs. We evaluate Medical Report Generation with Sematic-driven Reinforment Learning (MRG-R1), on two datasets: IU X-Ray and MIMIC-CXR using clinical efficacy (CE) metrics. MRG-R1 achieves state-of-the-art performance with CE-F1 51.88 on IU X-Ray and 40.39 on MIMIC-CXR. We found that the label-semantic reinforcement is better than conventional token-level supervision. These results indicate that optimizing a clinically grounded, report-level reward rather than token overlap,meaningfully improves clinical correctness. This work is a prior to explore semantic-reinforcement in supervising medical correctness in medical Large vision-language model(Med-LVLM) training.

LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model architectures, and system frameworks, tokenization remains an overlooked bottleneck. Existing parallel tokenization methods accelerate processing through text segmentation and multi-process tokenization, but they suffer from inconsistent results due to boundary artifacts that occur after merging. To address this, we propose LoPT, a novel Lossless Parallel Tokenization framework that ensures output identical to standard sequential tokenization. Our approach employs character-position-based matching and dynamic chunk length adjustment to align and merge tokenized segments accurately. Extensive experiments across diverse long-text datasets demonstrate that LoPT achieves significant speedup while guaranteeing lossless tokenization. We also provide theoretical proof of consistency and comprehensive analytical studies to validate the robustness of our method.

MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

Mass spectrometry (MS) plays a critical role in molecular identification, significantly advancing scientific discovery. However, structure elucidation from MS data remains challenging due to the scarcity of annotated spectra. While large-scale pretraining has proven effective in addressing data scarcity in other domains, applying this paradigm to mass spectrometry is hindered by the complexity and heterogeneity of raw spectral signals. To address this, we propose MS-BART, a unified modeling framework that maps mass spectra and molecular structures into a shared token vocabulary, enabling cross-modal learning through large-scale pretraining on reliably computed fingerprint-molecule datasets. Multi-task pretraining objectives further enhance MS-BART's generalization by jointly optimizing denoising and translation task. The pretrained model is subsequently transferred to experimental spectra through finetuning on fingerprint predictions generated with MIST, a pre-trained spectral inference model, thereby enhancing robustness to real-world spectral variability. While finetuning alleviates the distributional difference, MS-BART still suffers molecular hallucination and requires further alignment. We therefore introduce a chemical feedback mechanism that guides the model toward generating molecules closer to the reference structure. Extensive evaluations demonstrate that MS-BART achieves SOTA performance across 5/12 key metrics on MassSpecGym and NPLIB1 and is faster by one order of magnitude than competing diffusion-based methods, while comprehensive ablation studies systematically validate the model's effectiveness and robustness.

Rec-RIR: Monaural Blind Room Impulse Response Identification via DNN-based Reverberant Speech Reconstruction in STFT Domain

Room impulse response (RIR) characterizes the complete propagation process of sound in an enclosed space. This paper presents Rec-RIR for monaural blind RIR identification. Rec-RIR is developed based on the convolutive transfer function (CTF) approximation, which models reverberation effect within narrow-band filter banks in the short-time Fourier transform (STFT) domain. Specifically, we propose a deep neural network (DNN) with cross-band and narrow-band blocks to estimate the CTF filter. The DNN is trained through reconstructing the noise-free reverberant speech spectra. This objective enables stable and straightforward supervised training. Subsequently, a pseudo intrusive measurement process is employed to convert the CTF filter estimate into time-domain RIR by simulating a common intrusive RIR measurement procedure. Experimental results demonstrate that Rec-RIR achieves state-of-the-art (SOTA) performance in both RIR identification and acoustic parameter estimation. Open-source codes are available online at https://github.com/Audio-WestlakeU/Rec-RIR.

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets

Unified vision large language models (VLLMs) have recently achieved impressive advancements in both multimodal understanding and generation, powering applications such as visual question answering and text-guided image synthesis. However, progress in unified VLLMs remains constrained by the lack of datasets that fully exploit the synergistic potential between these two core abilities. Existing datasets typically address understanding and generation in isolation, thereby limiting the performance of unified VLLMs. To bridge this critical gap, we introduce a novel dataset construction framework, UnifiedVisual, and present UnifiedVisual-240K, a high-quality dataset meticulously designed to facilitate mutual enhancement between multimodal understanding and generation. UnifiedVisual-240K seamlessly integrates diverse visual and textual inputs and outputs, enabling comprehensive cross-modal reasoning and precise text-to-image alignment. Our dataset encompasses a wide spectrum of tasks and data sources, ensuring rich diversity and addressing key shortcomings of prior resources. Extensive experiments demonstrate that models trained on UnifiedVisual-240K consistently achieve strong performance across a wide range of tasks. Notably, these models exhibit significant mutual reinforcement between multimodal understanding and generation, further validating the effectiveness of our framework and dataset. We believe UnifiedVisual represents a new growth point for advancing unified VLLMs and unlocking their full potential. Our code and datasets is available at https://github.com/fnlp-vision/UnifiedVisual.

Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM

Multimodal large language models (MLLMs) have gained significant attention due to their impressive ability to integrate vision and language modalities. Recent advancements in MLLMs have primarily focused on improving performance through high-quality datasets, novel architectures, and optimized training strategies. However, in this paper, we identify a previously overlooked issue, language prior conflict, a mismatch between the inherent language priors of large language models (LLMs) and the language priors in training datasets. This conflict leads to suboptimal vision-language alignment, as MLLMs are prone to adapting to the language style of training samples. To address this issue, we propose a novel training method called Decoupled Proxy Alignment (DPA). DPA introduces two key innovations: (1) the use of a proxy LLM during pretraining to decouple the vision-language alignment process from language prior interference, and (2) dynamic loss adjustment based on visual relevance to strengthen optimization signals for visually relevant tokens. Extensive experiments demonstrate that DPA significantly mitigates the language prior conflict, achieving superior alignment performance across diverse datasets, model families, and scales. Our method not only improves the effectiveness of MLLM training but also shows exceptional generalization capabilities, making it a robust approach for vision-language alignment. Our code is available at https://github.com/fnlp-vision/DPA.

NEFT: A Unified Transformer Framework for Efficient Near-Field CSI Feedback in XL-MIMO Systems

Extremely large-scale multiple-input multiple-output (XL-MIMO) systems, operating in the near-field region due to their massive antenna arrays, are a key enabler of next-generation wireless communications but face significant challenges in channel state information (CSI) feedback. Deep learning has emerged as a powerful tool by learning compact CSI representations for feedback. However, existing methods struggle to capture the intricate structure of near-field CSI while incurring prohibitive computational overhead on practical mobile devices. To overcome these limitations, we propose the Near-Field Efficient Feedback Transformer (NEFT) family for accurate and efficient near-field CSI feedback across diverse hardware platforms. Built on a hierarchical Vision Transformer backbone, NEFT is extended with lightweight variants to meet various deployment constraints: NEFT-Compact applies multi-level knowledge distillation (KD) to reduce complexity while maintaining accuracy, and NEFT-Hybrid and NEFT-Edge address encoder- and edge-constrained scenarios via attention-free encoding and KD. Extensive simulations show that NEFT achieves a 15--21 dB improvement in normalized mean-squared error (NMSE) over state-of-the-art methods, while NEFT-Compact and NEFT-Edge reduce total FLOPs by 25--36% with negligible accuracy loss. Moreover, NEFT-Hybrid lowers encoder-side complexity by up to 64%, enabling deployment in highly asymmetric device scenarios. These results establish NEFT as a practical and scalable solution for near-field CSI feedback in XL-MIMO systems.

Jamming Identification with Differential Transformer for Low-Altitude Wireless Networks

Wireless jamming identification, which detects and classifies electromagnetic jamming from non-cooperative devices, is crucial for emerging low-altitude wireless networks consisting of many drone terminals that are highly susceptible to electromagnetic jamming. However, jamming identification schemes adopting deep learning (DL) are vulnerable to attacks involving carefully crafted adversarial samples, resulting in inevitable robustness degradation. To address this issue, we propose a differential transformer framework for wireless jamming identification. Firstly, we introduce a differential transformer network in order to distinguish jamming signals, which overcomes the attention noise when compared with its traditional counterpart by performing self-attention operations in a differential manner. Secondly, we propose a randomized masking training strategy to improve network robustness, which leverages the patch partitioning mechanism inherent to transformer architectures in order to create parallel feature extraction branches. Each branch operates on a distinct, randomly masked subset of patches, which fundamentally constrains the propagation of adversarial perturbations across the network. Additionally, the ensemble effect generated by fusing predictions from these diverse branches demonstrates superior resilience against adversarial attacks. Finally, we introduce a novel consistent training framework that significantly enhances adversarial robustness through dualbranch regularization. Simulation results demonstrate that our proposed methodology is superior to existing methods in boosting robustness to adversarial samples.

Adversarial Preference Learning for Robust LLM Alignment

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation, (2) the vast diversity of potential adversarial attacks, and (3) the risk of feedback bias and reward hacking. To address these challenges, we introduce Adversarial Preference Learning (APL), an iterative adversarial training method incorporating three key innovations. First, a direct harmfulness metric based on the model's intrinsic preference probabilities, eliminating reliance on external assessment. Second, a conditional generative attacker that synthesizes input-specific adversarial variations. Third, an iterative framework with automated closed-loop feedback, enabling continuous adaptation through vulnerability discovery and mitigation. Experiments on Mistral-7B-Instruct-v0.3 demonstrate that APL significantly enhances robustness, achieving 83.33% harmlessness win rate over the base model (evaluated by GPT-4o), reducing harmful outputs from 5.88% to 0.43% (measured by LLaMA-Guard), and lowering attack success rate by up to 65% according to HarmBench. Notably, APL maintains competitive utility, with an MT-Bench score of 6.59 (comparable to the baseline 6.78) and an LC-WinRate of 46.52% against the base model.

MRGAgents: A Multi-Agent Framework for Improved Medical Report Generation with Med-LVLMs

Medical Large Vision-Language Models (Med-LVLMs) have been widely adopted for medical report generation. Despite Med-LVLMs producing state-of-the-art performance, they exhibit a bias toward predicting all findings as normal, leading to reports that overlook critical abnormalities. Furthermore, these models often fail to provide comprehensive descriptions of radiologically relevant regions necessary for accurate diagnosis. To address these challenges, we proposeMedical Report Generation Agents (MRGAgents), a novel multi-agent framework that fine-tunes specialized agents for different disease categories. By curating subsets of the IU X-ray and MIMIC-CXR datasets to train disease-specific agents, MRGAgents generates reports that more effectively balance normal and abnormal findings while ensuring a comprehensive description of clinically relevant regions. Our experiments demonstrate that MRGAgents outperformed the state-of-the-art, improving both report comprehensiveness and diagnostic utility.