arXiv subjects

Mengfei Xu

Publications and source records attributed to Mengfei Xu.

5 recordsLinked to original sources

arXiv2026

CLEAR: Coupling Local Evidence with Affective Representations for Multimodal Emotion Recognition in Conversation

In video calls and livestreamed discussions, recognizing speakers' emotions helps identify emotionally salient segments and supports fine-grained video content analysis. Multimodal Emotion Recognition in Conversation (ERC) provides an approach to recognizing emotions in such content by integrating textual, visual, and acoustic information with conversational context. Current mainstream emotion recognition methods largely leverage the contextual understanding capabilities of multimodal large language models (MLLMs) to predict emotions by generating labels. However, emotion understanding and label prediction may be inconsistent, leaving the internal affective information underutilized. Moreover, when the current utterance is jointly modeled with extensive dialogue history and multimodal information, its local discriminative cues may be diluted and become less salient in the resulting contextual representation. To address these limitations, we propose CLEAR, an ERC framework that couples multimodal contextual representations with local discriminative cues. To mitigate the mismatch between emotion understanding and label prediction, we use the continuous internal representation of an emotion-supervised vision-language model (VLM) instead of its generated emotion labels, and further train a classifier based on this representation. To strengthen local discriminative cues, we use sample-adaptive residual coupling to dynamically integrate textual and acoustic evidence from the target utterance into the contextual representation. Experiments on IEMOCAP and MELD demonstrate that CLEAR achieves competitive performance, supporting the effectiveness of the proposed approach. The code is available at https://anonymous.4open.science/r/vlm-210F/.

cs.AI↗

arXiv2026

AdvFidelity: Unifying Preference Alignment and Few-Step Image Generation within Reinforcement Learning

Practical image generation requires both human preference alignment and few-step efficiency, yet combining reinforcement learning (RL) with distillation is often multi-stage and may erode RL gains We observe that few-step RL progressively improves structural coherence, even with specialized rewards, but leaves low-level artifacts that these rewards may fail to penalize. To address this gap, we propose AdvFidelity, which integrates artifact-sensitive fidelity supervision into RL through an online adversarial reward. This enables joint reward alignment and high-fidelity few-step generation within a single RL stage, without distribution matching distillation (DMD) or other explicit distillation objectives. We train a discriminator to rank high-quality references (positives) above content-matched reconstructions (negatives) produced by the current generator. Reconstructing moderately noised references largely preserves style and scene layout while exposing low-level degradations. This encourages the discriminator to assess artifacts rather than content differences. With negatives reconstructed online, alternating updates adapt fidelity supervision to the generator's evolving failure modes. References can come from existing target-domain data or full-step model samples. Built on LeapAlign, AdvFidelity backpropagates gradients from both rewards through the few-step sampling trajectories used at inference. Across two model backbones and three task settings, AdvFidelity matches full-step LeapAlign in alignment, task performance, and overall generation quality and remains highly competitive with other evaluated full-step RL methods, using only 4 or 8 steps without CFG.

cs.CV↗

arXiv2026

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide distillation supervision. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage co-training framework in which a decoupled student learns from the evolving RL teacher's trajectories without changing teacher optimization. Advantage-Modulated Distillation (AMD) transforms rollout advantages into signed weights, strengthening imitation of preferred trajectories and aligning distillation priorities with task value. The resulting framework is general and lightweight, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment demonstrate competitive few-step, CFG-free generation with RAM or DiffusionNFT teachers. With only four sampling steps, REST-RAM achieves a DrawBench PickScore of 23.97, outperforming both the 40-step RAM teacher (23.95) and RTDMD (23.71).

cs.CV↗

arXiv2021

UCNN: A Convolutional Strategy on Unstructured Mesh

In machine learning for fluid mechanics, fully-connected neural network (FNN) only uses the local features for modelling, while the convolutional neural network (CNN) cannot be applied to data on structured/unstructured mesh. In order to overcome the limitations of FNN and CNN, the unstructured convolutional neural network (UCNN) is proposed, which aggregates and effectively exploits the features of neighbour nodes through the weight function. Adjoint vector modelling is taken as the task to study the performance of UCNN. The mapping function from flow-field features to adjoint vector is constructed through efficient parallel implementation on GPU. The modelling capability of UCNN is compared with that of FNN on validation set and in aerodynamic shape optimization at test case. The influence of mesh changing on the modelling capability of UCNN is further studied. The results indicate that UCNN is more accurate in modelling process.

physics.flu-dyn↗

arXiv2020

Machine learning for adjoint vector in aerodynamic shape optimization

Adjoint method is widely used in aerodynamic design because only once solution of flow field is required for adjoint method to obtain the gradients of all design variables. However, the calculation cost of adjoint vector is approximately equal to that of flow computation. In order to accelerate the solution of adjoint vector and improve the adjoint-based optimization efficiency, machine learning for adjoint vector modeling is presented. Deep neural network (DNN) is employed to construct the mapping between the adjoint vector and the local flow variables. DNN can efficiently predict adjoint vector and its generalization is examined by a transonic drag reduction about NACA0012 airfoil. The results indicate that with negligible calculation cost of the adjoint vector, the proposed DNN-based adjoint method can achieve the same optimization results as the traditional adjoint method.

physics.flu-dyn↗