Wenxin Xu

Xuefeng Liang, Hexin Jiang, Wenxin Xu et al.

In speech emotion recognition tasks, models learn emotional representations from datasets. We find the data distribution in the IEMOCAP dataset is very imbalanced, which may harm models to learn a better representation. To address this issue, we propose a novel Pairwise-emotion Data Distribution Smoothing (PDDS) method. PDDS considers that the distribution of emotional data should be smooth in reality, then applies Gaussian smoothing to emotion-pairs for constructing a new training set with a smoother distribution. The required new data are complemented using the mixup augmentation. As PDDS is model and modality agnostic, it is evaluated with three SOTA models on the IEMOCAP dataset. The experimental results show that these models are improved by 0.2\% - 4.8\% and 1.5\% - 5.9\% in terms of WA and UA. In addition, an ablation study demonstrates that the key advantage of PDDS is the reasonable data distribution rather than a simple data augmentation.

Wenxin Xu, Hexin Jiang, Xuefeng Liang et al.

Subjective time-series regression (STR) tasks have gained increasing attention recently. However, most existing methods overlook the label distribution bias in STR data, which results in biased models. Emerging studies on imbalanced regression tasks, such as age estimation and depth estimation, hypothesize that the prior label distribution of the dataset is uniform. However, we observe that the label distributions of training and test sets in STR tasks are likely to be neither uniform nor identical. This distinct feature calls for new approaches that estimate more reasonable distributions to train a fair model. In this work, we propose Utopia Label Distribution Approximation (ULDA) for time-series data, which makes the training label distribution closer to real-world but unknown (utopia) label distribution. This would enhance the model's fairness. Specifically, ULDA first convolves the training label distribution by a Gaussian kernel. After convolution, the required sample quantity at each regression label may change. We further devise the Time-slice Normal Sampling (TNS) to generate new samples when the required sample quantity is greater than the initial sample quantity, and the Convolutional Weighted Loss (CWL) to lower the sample weight when the required sample quantity is less than the initial quantity. These two modules not only assist the model training on the approximated utopia label distribution, but also maintain the sample continuity in temporal context space. To the best of our knowledge, ULDA is the first method to address the label distribution bias in time-series data. Extensive experiments demonstrate that ULDA lifts the state-of-the-art performance on two STR tasks and three benchmark datasets.

Yang Zhang, Wenxin Xu, Xiaoyan Zhao et al.

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data. However, these methods face significant practical limitations due to (1) the difficulty of obtaining high-quality CoT data in recommendation and (2) the high inference latency caused by generating CoT reasoning. In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning. This approach eliminates the need for explicit CoT generation and improves inference efficiency, as few latent tokens can effectively capture the entire reasoning process. Building on this idea, we propose \textit{\underline{R}einforced \underline{Latent} \underline{R}easoning for \underline{R}ecommendation} (LatentR$^3$), a novel end-to-end training framework that leverages reinforcement learning (RL) to optimize latent reasoning without relying on any CoT data. LatentR$^3$ adopts a two-stage training strategy: first, supervised fine-tuning to initialize the latent reasoning module, followed by pure RL training to encourage exploration through a rule-based reward design. Our RL implementation is based on a modified GRPO algorithm, which reduces computational overhead during training and introduces continuous reward signals for more efficient learning. Extensive experiments demonstrate that LatentR$^3$ enables effective latent reasoning without any direct supervision of the reasoning process, significantly improving performance when integrated with different LLM-based recommendation methods. Our codes are available at https://github.com/xuwenxinedu/R3.

Peiran Yun, Wenxin Xu, Jiayuan Liu et al.

As Large Language Models (LLMs) transition into conversational agents, generative advertising emerges as a crucial monetization strategy. However, embedding advertisements within unstructured LLM outputs introduces a critical trilemma: balancing advertiser payoffs, platform revenue, and user experience. Existing methods, such as prompt injection or rigid position slots, disrupt semantic coherence and lack a parametric framework for independent control, rendering rigorous mechanism design intractable. To bridge this gap, we introduce Neuron Auctions, a novel paradigm that shifts the auction object from the surface text space to the LLM's internal representations. Leveraging mechanistic interpretability, we identify brand-specific feed-forward network (FFN) neurons and demonstrate that competing brands activate within approximately orthogonal subspaces. This near-perfect independence allows us to define continuous, disentangled intervention budgets (specifically, neuron counts and amplification factors) as auctionable commodities. Building on this computational carrier, we design a continuous menu-based auction mechanism that naturally guarantees strategy-proofness and optimizes revenue for the platform. By explicitly incorporating a user utility penalty into the platform's optimization objective, our framework dynamically prices out overly aggressive interventions. Extensive experiments demonstrate that Neuron Auctions effectively preserve natural discourse quality while achieving an optimal alignment between commercial incentives and user satisfaction.

Linyong Gan, Zimo Li, Wenxin Xu et al.

Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors. Existing methods often struggle to maintain global directional consistency, leading to drifting or implausible trajectories when extrapolated over long time horizons. To address this issue, we propose a semantic-key-point-conditioned trajectory modeling framework, in which future trajectories are predicted by conditioning on a high-level Next Key Point (NKP) that captures navigational intent. This formulation decomposes long-horizon prediction into global semantic decision-making and local motion modeling, effectively restricting the support of future trajectories to semantically feasible subsets. To efficiently estimate the NKP prior from historical observations, we adopt a pretrain-finetune strategy. Extensive experiments on real-world AIS data demonstrate that the proposed method consistently outperforms state-of-the-art approaches, particularly for long travel durations, directional accuracy, and fine-grained trajectory prediction.

Guowei Xu, Wenxin Xu, Jiawang Zhao et al. · tsinghua

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains challenging, as they lack precise probability estimates at each denoising step. While the diffusion mechanism enables the model to reason over entire sequences, it also makes the generation process less predictable and often inconsistent. This highlights the importance of controlling key tokens that guide the direction of generation. To address this issue, we propose WeFT, a weighted SFT method for diffusion language models, where tokens are assigned different weights based on their entropy. Derived from diffusion theory, WeFT delivers substantial gains: training on s1K, s1K-1.1, and 3k samples from open-r1, it achieves relative improvements of 39%, 64%, and 83% over standard SFT on four widely used reasoning benchmarks (Sudoku, Countdown, GSM8K, and MATH-500). The code and models will be made publicly available.