Beyond Video-to-SFX: Video to Audio Synthesis with Environmentally Aware Speech

The generation of realistic, context-aware audio is important in real-world applications such as video game development. While existing video-to-audio (V2A) methods mainly focus on Foley sound generation, they struggle to produce intelligible speech. Meanwhile, current environmental speech synthesis approaches remain text-driven and fail to temporally align with dynamic video content. In this paper, we propose Beyond Video-to-SFX (BVS), a method to generate synchronized audio with environmentally aware intelligible speech for given videos. We introduce a two-stage modeling method: (1) stage one is a video-guided audio semantic (V2AS) model to predict unified audio semantic tokens conditioned on phonetic cues; (2) stage two is a video-conditioned semantic-to-acoustic (VS2A) model that refines semantic tokens into detailed acoustic tokens. Experiments demonstrate the effectiveness of BVS in scenarios such as video-to-context-aware speech synthesis and immersive audio background conversion, with ablation studies further validating our design. Our demonstration is available at~\href{https://xinleiniu.github.io/BVS-demo/}{BVS-Demo}.

FMGS-Avatar: Mesh-Guided 2D Gaussian Splatting with Foundation Model Priors for 3D Monocular Avatar Reconstruction

Reconstructing high-fidelity animatable human avatars from monocular videos remains challenging due to insufficient geometric information in single-view observations. While recent 3D Gaussian Splatting methods have shown promise, they struggle with surface detail preservation due to the free-form nature of 3D Gaussian primitives. To address both the representation limitations and information scarcity, we propose a novel method, \textbf{FMGS-Avatar}, that integrates two key innovations. First, we introduce Mesh-Guided 2D Gaussian Splatting, where 2D Gaussian primitives are attached directly to template mesh faces with constrained position, rotation, and movement, enabling superior surface alignment and geometric detail preservation. Second, we leverage foundation models trained on large-scale datasets, such as Sapiens, to complement the limited visual cues from monocular videos. However, when distilling multi-modal prior knowledge from foundation models, conflicting optimization objectives can emerge as different modalities exhibit distinct parameter sensitivities. We address this through a coordinated training strategy with selective gradient isolation, enabling each loss component to optimize its relevant parameters without interference. Through this combination of enhanced representation and coordinated information distillation, our approach significantly advances 3D monocular human avatar reconstruction. Experimental evaluation demonstrates superior reconstruction quality compared to existing methods, with notable gains in geometric accuracy and appearance fidelity while providing rich semantic information. Additionally, the distilled prior knowledge within a shared canonical space naturally enables spatially and temporally consistent rendering under novel views and poses.

TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation

Referring Image Segmentation (RIS) is a task that segments image regions based on language expressions, requiring fine-grained alignment between two modalities. However, existing methods often struggle with multimodal misalignment and language semantic loss, especially in complex scenes containing multiple visually similar objects, where uniquely described targets are frequently mislocalized or incompletely segmented. To tackle these challenges, this paper proposes TFANet, a Three-stage Image-Text Feature Alignment Network that systematically enhances multimodal alignment through a hierarchical framework comprising three stages: Knowledge Plus Stage (KPS), Knowledge Fusion Stage (KFS), and Knowledge Intensification Stage (KIS). In the first stage, we design the Multiscale Linear Cross-Attention Module (MLAM), which facilitates bidirectional semantic exchange between visual features and textual representations across multiple scales. This establishes rich and efficient alignment between image regions and different granularities of linguistic descriptions. Subsequently, the KFS further strengthens feature alignment through the Cross-modal Feature Scanning Module (CFSM), which applies multimodal selective scanning to capture long-range dependencies and construct a unified multimodal representation. This is essential for modeling long-range cross-modal dependencies and enhancing alignment accuracy in complex scenes. Finally, in the KIS, we propose the Word-level Linguistic Feature-guided Semantic Deepening Module (WFDM) to compensate for semantic degradation introduced in earlier stages.

Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices

Age-related Macular Degeneration (AMD) is a prevalent eye condition affecting visual acuity. Anti-vascular endothelial growth factor (anti-VEGF) treatments have been effective in slowing the progression of neovascular AMD, with better outcomes achieved through timely diagnosis and consistent monitoring. Tracking the progression of neovascular activity in OCT scans of patients with exudative AMD allows for the development of more personalized and effective treatment plans. This was the focus of the Monitoring Age-related Macular Degeneration Progression in Optical Coherence Tomography (MARIO) challenge, in which we participated. In Task 1, which involved classifying the evolution between two pairs of 2D slices from consecutive OCT acquisitions, we employed a fusion CNN network with model ensembling to further enhance the model's performance. For Task 2, which focused on predicting progression over the next three months based on current exam data, we proposed the Patch Progression Masked Autoencoder that generates an OCT for the next exam and then classifies the evolution between the current OCT and the one generated using our solution from Task 1. The results we achieved allowed us to place in the Top 10 for both tasks. Some team members are part of the same organization as the challenge organizers; therefore, we are not eligible to compete for the prize.

Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language Models

Interactive online learning environments, represented by Massive AI-empowered Courses (MAIC), leverage LLM-driven multi-agent systems to transform passive MOOCs into dynamic, text-based platforms, enhancing interactivity through LLMs. This paper conducts an empirical study on a specific MAIC course to explore three research questions about dropouts in these interactive online courses: (1) What factors might lead to dropouts? (2) Can we predict dropouts? (3) Can we reduce dropouts? We analyze interaction logs to define dropouts and identify contributing factors. Our findings reveal strong links between dropout behaviors and textual interaction patterns. We then propose a course-progress-adaptive dropout prediction framework (CPADP) to predict dropouts with at most 95.4% accuracy. Based on this, we design a personalized email recall agent to re-engage at-risk students. Applied in the deployed MAIC system with over 3,000 students, the feasibility and effectiveness of our approach have been validated on students with diverse backgrounds.

Structural Energy-Guided Sampling for View-Consistent Text-to-3D

Text-to-3D generation often suffers from the Janus problem, where objects look correct from the front but collapse into duplicated or distorted geometry from other angles. We attribute this failure to viewpoint bias in 2D diffusion priors, which propagates into 3D optimization. To address this, we propose Structural Energy-Guided Sampling (SEGS), a training-free, plug-and-play framework that enforces multi-view consistency entirely at sampling time. SEGS defines a structural energy in a PCA subspace of intermediate U-Net features and injects its gradients into the denoising trajectory, steering geometry toward the intended viewpoint while preserving appearance fidelity. Integrated seamlessly into SDS/VSD pipelines, SEGS significantly reduces Janus artifacts, achieving improved geometric alignment and viewpoint consistency without retraining or weight modification.

S5: Scalable Semi-Supervised Semantic Segmentation in Remote Sensing

Semi-supervised semantic segmentation (S4) has advanced remote sensing (RS) analysis by leveraging unlabeled data through pseudo-labeling and consistency learning. However, existing S4 studies often rely on small-scale datasets and models, limiting their practical applicability. To address this, we propose S5, the first scalable framework for semi-supervised semantic segmentation in RS, which unlocks the potential of vast unlabeled Earth observation data typically underutilized due to costly pixel-level annotations. Built upon existing large-scale RS datasets, S5 introduces a data selection strategy that integrates entropy-based filtering and diversity expansion, resulting in the RS4P-1M dataset. Using this dataset, we systematically scales S4 methods by pre-training RS foundation models (RSFMs) of varying sizes on this extensive corpus, significantly boosting their performance on land cover segmentation and object detection tasks. Furthermore, during fine-tuning, we incorporate a Mixture-of-Experts (MoE)-based multi-dataset fine-tuning approach, which enables efficient adaptation to multiple RS benchmarks with fewer parameters. This approach improves the generalization and versatility of RSFMs across diverse RS benchmarks. The resulting RSFMs achieve state-of-the-art performance across all benchmarks, underscoring the viability of scaling semi-supervised learning for RS applications. All datasets, code, and models will be released at https://github.com/MiliLab/S5

REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation

Reinforcement learning (RL) is emerging as a powerful paradigm for enabling large language models (LLMs) to perform complex reasoning tasks. Recent advances indicate that integrating RL with retrieval-augmented generation (RAG) allows LLMs to dynamically incorporate external knowledge, leading to more informed and robust decision making. However, we identify a critical challenge during policy-driven trajectory sampling: LLMs are frequently trapped in unproductive reasoning paths, which we refer to as "dead ends", committing to overconfident yet incorrect conclusions. This severely hampers exploration and undermines effective policy optimization. To address this challenge, we propose REX-RAG (Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation), a novel framework that explores alternative reasoning paths while maintaining rigorous policy learning through principled distributional corrections. Our approach introduces two key innovations: (1) Mixed Sampling Strategy, which combines a novel probe sampling method with exploratory prompts to escape dead ends; and (2) Policy Correction Mechanism, which employs importance sampling to correct distribution shifts induced by mixed sampling, thereby mitigating gradient estimation bias. We evaluate it on seven question-answering benchmarks, and the experimental results show that REX-RAG achieves average performance gains of 5.1% on Qwen2.5-3B and 3.6% on Qwen2.5-7B over strong baselines, demonstrating competitive results across multiple datasets. The code is publicly available at https://github.com/MiliLab/REX-RAG.

TEFormer: Texture-Aware and Edge-Guided Transformer for Semantic Segmentation of Urban Remote Sensing Images

Semantic segmentation of urban remote sensing images (URSIs) is crucial for applications such as urban planning and environmental monitoring. However, geospatial objects often exhibit subtle texture differences and similar spatial structures, which can easily lead to semantic ambiguity and misclassification. Moreover, challenges such as irregular object shapes, blurred boundaries, and overlapping spatial distributions of semantic objects contribute to complex and diverse edge morphologies, further complicating accurate segmentation. To tackle these issues, we propose a texture-aware and edge-guided Transformer (TEFormer) that integrates texture awareness and edge-guidance mechanisms for semantic segmentation of URSIs. In the encoder, a texture-aware module (TaM) is designed to capture fine-grained texture differences between visually similar categories to enhance semantic discrimination. Then, an edge-guided tri-branch decoder (Eg3Head) is constructed to preserve local edges and details for multiscale context-awareness. Finally, an edge-guided feature fusion module (EgFFM) is to fuse contextual and detail information with edge information to realize refined semantic segmentation. Extensive experiments show that TEFormer achieves mIoU of 88.57%, 81.46%, and 53.55% on the Potsdam, Vaihingen, and LoveDA datasets, respectively, shows the effectiveness in URSI semantic segmentation.

How and Why: Taming Flow Matching for Unsupervised Anomaly Detection and Localization

We propose a new paradigm for unsupervised anomaly detection and localization using Flow Matching (FM), which fundamentally addresses the model expressivity limitations of conventional flow-based methods. To this end, we formalize the concept of time-reversed Flow Matching (rFM) as a vector field regression along a predefined probability path to transform unknown data distributions into standard Gaussian. We bring two core observations that reshape our understanding of FM. First, we rigorously prove that FM with linear interpolation probability paths is inherently non-invertible. Second, our analysis reveals that employing reversed Gaussian probability paths in high-dimensional spaces can lead to trivial vector fields. This issue arises due to the manifold-related constraints. Building on the second observation, we propose Worst Transport (WT) displacement interpolation to reconstruct a non-probabilistic evolution path. The proposed WT-Flow enhances dynamical control over sample trajectories, constructing ''degenerate potential wells'' for anomaly-free samples while allowing anomalous samples to escape. This novel unsupervised paradigm offers a theoretically grounded separation mechanism for anomalous samples. Notably, FM provides a computationally tractable framework that scales to complex data. We present the first successful application of FM for the unsupervised anomaly detection task, achieving state-of-the-art performance at a single scale on the MVTec dataset. The reproducible code for training will be released upon camera-ready submission.