Private Transformer Inference in MLaaS: A Survey

Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service (MLaaS) raises significant privacy concerns, primarily due to the centralized processing of sensitive user data. Private Transformer Inference (PTI) offers a solution by utilizing cryptographic techniques such as secure multi-party computation and homomorphic encryption, enabling inference while preserving both user data and model privacy. This paper reviews recent PTI advancements, highlighting state-of-the-art solutions and challenges. We also introduce a structured taxonomy and evaluation framework for PTI, focusing on balancing resource efficiency with privacy and bridging the gap between high-performance inference and data privacy.

Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence

Multimodal learning enhances the perceptual capabilities of cognitive systems by integrating information from different sensory modalities. However, existing multimodal fusion research typically assumes static integration, not fully incorporating key dynamic mechanisms found in the brain. Specifically, the brain exhibits an inverse effectiveness phenomenon, wherein weaker unimodal cues yield stronger multisensory integration benefits; conversely, when individual modal cues are stronger, the effect of fusion is diminished. This mechanism enables biological systems to achieve robust cognition even with scarce or noisy perceptual cues. Inspired by this biological mechanism, we explore the relationship between multimodal output and information from individual modalities, proposing an inverse effectiveness driven multimodal fusion (IEMF) strategy. By incorporating this strategy into neural networks, we achieve more efficient integration with improved model performance and computational efficiency, demonstrating up to 50% reduction in computational cost across diverse fusion methods. We conduct experiments on audio-visual classification, continual learning, and question answering tasks to validate our method. Results consistently demonstrate that our method performs excellently in these tasks. To verify universality and generalization, we also conduct experiments on Artificial Neural Networks (ANN) and Spiking Neural Networks (SNN), with results showing good adaptability to both network types. Our research emphasizes the potential of incorporating biologically inspired mechanisms into multimodal networks and provides promising directions for the future development of multimodal artificial intelligence. The code is available at https://github.com/Brain-Cog-Lab/IEMF.

FlowHFT: Flow Policy Induced Optimal High-Frequency Trading under Diverse Market Conditions

High-frequency trading (HFT) is an investing strategy that continuously monitors market states and places bid and ask orders at millisecond speeds. Traditional HFT approaches fit models with historical data and assume that future market states follow similar patterns. This limits the effectiveness of any single model to the specific conditions it was trained for. Additionally, these models achieve optimal solutions only under specific market conditions, such as assumptions about stock price's stochastic process, stable order flow, and the absence of sudden volatility. Real-world markets, however, are dynamic, diverse, and frequently volatile. To address these challenges, we propose the FlowHFT, a novel imitation learning framework based on flow matching policy. FlowHFT simultaneously learns strategies from numerous expert models, each proficient in particular market scenarios. As a result, our framework can adaptively adjust investment decisions according to the prevailing market state. Furthermore, FlowHFT incorporates a grid-search fine-tuning mechanism. This allows it to refine strategies and achieve superior performance even in complex or extreme market scenarios where expert strategies may be suboptimal. We test FlowHFT in multiple market environments. We first show that flow matching policy is applicable in stochastic market environments, thus enabling FlowHFT to learn trading strategies under different market conditions. Notably, our single framework consistently achieves performance superior to the best expert for each market condition.

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering.

Rethinking Multimodal Sentiment Analysis: A High-Accuracy, Simplified Fusion Architecture

Multimodal sentiment analysis, a pivotal task in affective computing, seeks to understand human emotions by integrating cues from language, audio, and visual signals. While many recent approaches leverage complex attention mechanisms and hierarchical architectures, we propose a lightweight, yet effective fusion-based deep learning model tailored for utterance-level emotion classification. Using the benchmark IEMOCAP dataset, which includes aligned text, audio-derived numeric features, and visual descriptors, we design a modality-specific encoder using fully connected layers followed by dropout regularization. The modality-specific representations are then fused using simple concatenation and passed through a dense fusion layer to capture cross-modal interactions. This streamlined architecture avoids computational overhead while preserving performance, achieving a classification accuracy of 92% across six emotion categories. Our approach demonstrates that with careful feature engineering and modular design, simpler fusion strategies can outperform or match more complex models, particularly in resource-constrained environments.

CoCoDiff: Diversifying Skeleton Action Features via Coarse-Fine Text-Co-Guided Latent Diffusion

In action recognition tasks, feature diversity is essential for enhancing model generalization and performance. Existing methods typically promote feature diversity by expanding the training data in the sample space, which often leads to inefficiencies and semantic inconsistencies. To overcome these problems, we propose a novel Coarse-fine text co-guidance Diffusion model (CoCoDiff). CoCoDiff generates diverse yet semantically consistent features in the latent space by leveraging diffusion and multi-granularity textual guidance. Specifically, our approach feeds spatio-temporal features extracted from skeleton sequences into a latent diffusion model to generate diverse action representations. Meanwhile, we introduce a coarse-fine text co-guided strategy that leverages textual information from large language models (LLMs) to ensure semantic consistency between the generated features and the original inputs. It is noted that CoCoDiff operates as a plug-and-play auxiliary module during training, incurring no additional inference cost. Extensive experiments demonstrate that CoCoDiff achieves SOTA performance on skeleton-based action recognition benchmarks, including NTU RGB+D, NTU RGB+D 120 and Kinetics-Skeleton.

LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation

Online fake news moderation now faces a new challenge brought by the malicious use of large language models (LLMs) in fake news production. Though existing works have shown LLM-generated fake news is hard to detect from an individual aspect, it remains underexplored how its large-scale release will impact the news ecosystem. In this study, we develop a simulation pipeline and a dataset with ~56k generated news of diverse types to investigate the effects of LLM-generated fake news within neural news recommendation systems. Our findings expose a truth decay phenomenon, where real news is gradually losing its advantageous position in news ranking against fake news as LLM-generated news is involved in news recommendation. We further provide an explanation about why truth decay occurs from a familiarity perspective and show the positive correlation between perplexity and news ranking. Finally, we discuss the threats of LLM-generated fake news and provide possible countermeasures. We urge stakeholders to address this emerging challenge to preserve the integrity of news ecosystems.

TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation

Soccer is a globally popular sporting event, typically characterized by long matches and distinctive highlight moments. Recent advances in Multimodal Large Language Models (MLLMs) offer promising capabilities in temporal grounding and video understanding, soccer commentary generation often requires precise temporal localization and semantically rich descriptions over long-form video. However, existing soccer MLLMs often rely on the temporal a priori for caption generation, so they cannot process the soccer video end-to-end. While some traditional approaches follow a two-step paradigm that is complex and fails to capture the global context to achieve suboptimal performance. To solve the above issues, we present TimeSoccer, the first end-to-end soccer MLLM for Single-anchor Dense Video Captioning (SDVC) in full-match soccer videos. TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling across 45-minute matches. To support long video understanding of soccer matches, we introduce MoFA-Select, a training-free, motion-aware frame compression module that adaptively selects representative frames via a coarse-to-fine strategy, and incorporates complementary training paradigms to strengthen the model's ability to handle long temporal sequences. Extensive experiments demonstrate that our TimeSoccer achieves State-of-The-Art (SoTA) performance on the SDVC task in an end-to-end form, generating high-quality commentary with accurate temporal alignment and strong semantic relevance.

Iterative Collaboration Network Guided By Reconstruction Prior for Medical Image Super-Resolution

High-resolution medical images can provide more detailed information for better diagnosis. Conventional medical image super-resolution relies on a single task which first performs the extraction of the features and then upscaling based on the features. The features extracted may not be complete for super-resolution. Recent multi-task learning,including reconstruction and super-resolution, is a good solution to obtain additional relevant information. The interaction between the two tasks is often insufficient, which still leads to incomplete and less relevant deep features. To address above limitations, we propose an iterative collaboration network (ICONet) to improve communications between tasks by progressively incorporating reconstruction prior to the super-resolution learning procedure in an iterative collaboration way. It consists of a reconstruction branch, a super-resolution branch, and a SR-Rec fusion module. The reconstruction branch generates the artifact-free image as prior, which is followed by a super-resolution branch for prior knowledge-guided super-resolution. Unlike the widely-used convolutional neural networks for extracting local features and Transformers with quadratic computational complexity for modeling long-range dependencies, we develop a new residual spatial-channel feature learning (RSCFL) module of two branches to efficiently establish feature relationships in spatial and channel dimensions. Moreover, the designed SR-Rec fusion module fuses the reconstruction prior and super-resolution features with each other in an adaptive manner. Our ICONet is built with multi-stage models to iteratively upscale the low-resolution images using steps of 2x and simultaneously interact between two branches in multi-stage supervisions.

SkyReels-V2: Infinite-length Film Generative Model

Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions. These intertwined limitations hinder realistic long-form synthesis and professional film-style generation. To address these limitations, we propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. Firstly, we design a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models. Aided with human annotation, we then train a unified Video Captioner, named SkyCaptioner-V1, to efficiently label the video data. Secondly, we establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement: Initial concept-balanced Supervised Fine-Tuning (SFT) improves baseline quality; Motion-specific Reinforcement Learning (RL) training with human-annotated and synthetic distortion data addresses dynamic artifacts; Our diffusion forcing framework with non-decreasing noise schedules enables long-video synthesis in an efficient search space; Final high-quality SFT refines visual fidelity. All the code and models are available at https://github.com/SkyworkAI/SkyReels-V2.