In-context learning (ICL) capabilities are becoming increasingly appealing for building general intelligence due to their sample efficiency and independence from artificial optimization skills. To enhance generalization, biological neural systems primarily inherit learning capabilities and subsequently refine their memory, acquiring diverse skills and knowledge through extensive lifelong experiences. This process gives rise to the concept of general-purpose in-context learning (GPICL). Compared to standard ICL, GPICL addresses a broader range of tasks, extends learning horizons, and starts at a lower zero-shot baseline. We introduce two lightweight but insightful benchmarks specifically crafted to train and evaluate GPICL functionalities. Each benchmark includes a vast number of tasks characterized by significant task variance and minimal transferable knowledge among tasks, facilitating lifelong in-context learning through continuous generation and interaction. These features pose significant challenges for models that rely on context or interactions to improve their proficiency, including language models, decision models, and world models. Our experiments reveal that parameter scale alone may not be crucial for ICL or GPICL, suggesting alternative approaches such as increasing the scale of contexts and memory states.
Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined norm and then injects calibrated noise into the training procedure. Existing DPSGD works typically assume the gradients follow sub-Gaussian distributions and design various clipping mechanisms to optimize training performance. However, recent studies have shown that the gradients in deep learning exhibit a heavy-tail phenomenon, that is, the tails of the gradient have infinite variance, which may lead to excessive clipping loss to the gradients with existing DPSGD mechanisms. To address this problem, we propose a novel approach, Discriminative Clipping~(DC)-DPSGD, with two key designs. First, we introduce a subspace identification technique to distinguish between body and tail gradients. Second, we present a discriminative clipping mechanism that applies different clipping thresholds for body and tail gradients to reduce the clipping loss. Under the non-convex condition, \ourtech{} reduces the empirical gradient norm from {${\mathbb{O}\left(\log^{\max(0,\theta-1)}(T/\delta)\log^{2\theta}(\sqrt{T})\right)}$} to {${\mathbb{O}\left(\log(\sqrt{T})\right)}$} with heavy-tailed index $\theta\geq 1/2$, iterations $T$, and arbitrary probability $\delta$. Extensive experiments on four real-world datasets demonstrate that our approach outperforms three baselines by up to 9.72\% in terms of accuracy.
Knowledge tracing (KT) enhances student learning by leveraging past performance to predict future performance. Current research utilizes models based on attention mechanisms and recurrent neural network structures to capture long-term dependencies and correlations between exercises, aiming to improve model accuracy. Due to the growing amount of data in smart education scenarios, this poses a challenge in terms of time and space consumption for knowledge tracing models. However, existing research often overlooks the efficiency of model training and inference and the constraints of training resources. Recognizing the significance of prioritizing model efficiency and resource usage in knowledge tracing, we introduce Mamba4KT. This novel model is the first to explore enhanced efficiency and resource utilization in knowledge tracing. We also examine the interpretability of the Mamba structure both sequence-level and exercise-level to enhance model interpretability. Experimental findings across three public datasets demonstrate that Mamba4KT achieves comparable prediction accuracy to state-of-the-art models while significantly improving training and inference efficiency and resource utilization. As educational data continues to grow, our work suggests a promising research direction for knowledge tracing that improves model prediction accuracy, model efficiency, resource utilization, and interpretability simultaneously.
The extraction of essential news elements through the 5W1H framework (\textit{What}, \textit{When}, \textit{Where}, \textit{Why}, \textit{Who}, and \textit{How}) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as ChatGPT presents an opportunity to address language-related tasks through simple prompts without fine-tuning models with much time. While ChatGPT has encountered challenges in processing longer news texts and analyzing specific attributes in context, especially answering questions about \textit{What}, \textit{Why}, and \textit{How}. The effectiveness of extraction tasks is notably dependent on high-quality human-annotated datasets. However, the absence of such datasets for the 5W1H extraction increases the difficulty of fine-tuning strategies based on open-source LLMs. To address these limitations, first, we annotate a high-quality 5W1H dataset based on four typical news corpora (\textit{CNN/DailyMail}, \textit{XSum}, \textit{NYT}, \textit{RA-MDS}); second, we design several strategies from zero-shot/few-shot prompting to efficient fine-tuning to conduct 5W1H aspects extraction from the original news documents. The experimental results demonstrate that the performance of the fine-tuned models on our labelled dataset is superior to the performance of ChatGPT. Furthermore, we also explore the domain adaptation capability by testing the source-domain (e.g. NYT) models on the target domain corpus (e.g. CNN/DailyMail) for the task of 5W1H extraction.
Understanding egocentric human-object interaction (HOI) is a fundamental aspect of human-centric perception, facilitating applications like AR/VR and embodied AI. For the egocentric HOI, in addition to perceiving semantics e.g., ''what'' interaction is occurring, capturing ''where'' the interaction specifically manifests in 3D space is also crucial, which links the perception and operation. Existing methods primarily leverage observations of HOI to capture interaction regions from an exocentric view. However, incomplete observations of interacting parties in the egocentric view introduce ambiguity between visual observations and interaction contents, impairing their efficacy. From the egocentric view, humans integrate the visual cortex, cerebellum, and brain to internalize their intentions and interaction concepts of objects, allowing for the pre-formulation of interactions and making behaviors even when interaction regions are out of sight. In light of this, we propose harmonizing the visual appearance, head motion, and 3D object to excavate the object interaction concept and subject intention, jointly inferring 3D human contact and object affordance from egocentric videos. To achieve this, we present EgoChoir, which links object structures with interaction contexts inherent in appearance and head motion to reveal object affordance, further utilizing it to model human contact. Additionally, a gradient modulation is employed to adopt appropriate clues for capturing interaction regions across various egocentric scenarios. Moreover, 3D contact and affordance are annotated for egocentric videos collected from Ego-Exo4D and GIMO to support the task. Extensive experiments on them demonstrate the effectiveness and superiority of EgoChoir. Code and data will be open.
Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.
Human mobility data offers valuable insights for many applications such as urban planning and pandemic response, but its use also raises privacy concerns. In this paper, we introduce the Hierarchical and Multi-Resolution Network (HRNet), a novel deep generative model specifically designed to synthesize realistic human mobility data while guaranteeing differential privacy. We first identify the key difficulties inherent in learning human mobility data under differential privacy. In response to these challenges, HRNet integrates three components: a hierarchical location encoding mechanism, multi-task learning across multiple resolutions, and private pre-training. These elements collectively enhance the model's ability under the constraints of differential privacy. Through extensive comparative experiments utilizing a real-world dataset, HRNet demonstrates a marked improvement over existing methods in balancing the utility-privacy trade-off.
Real-SR endeavors to produce high-resolution images with rich details while mitigating the impact of multiple degradation factors. Although existing methods have achieved impressive achievements in detail recovery, they still fall short when addressing regions with complex gradient arrangements due to the intensity-based linear weighting feature extraction manner. Moreover, the stochastic artifacts introduced by degradation cues during the imaging process in real LR increase the disorder of the overall image details, further complicating the perception of intrinsic gradient arrangement. To address these challenges, we innovatively introduce kernel-wise differential operations within the convolutional kernel and develop several learnable directional gradient convolutions. These convolutions are integrated in parallel with a novel linear weighting mechanism to form an Adaptive Directional Gradient Convolution (DGConv), which adaptively weights and fuses the basic directional gradients to improve the gradient arrangement perception capability for both regular and irregular textures. Coupled with DGConv, we further devise a novel equivalent parameter fusion method for DGConv that maintains its rich representational capabilities while keeping computational costs consistent with a single Vanilla Convolution (VConv), enabling DGConv to improve the performance of existing super-resolution networks without incurring additional computational expenses. To better leverage the superiority of DGConv, we further develop an Adaptive Information Interaction Block (AIIBlock) to adeptly balance the enhancement of texture and contrast while meticulously investigating the interdependencies, culminating in the creation of a DGPNet for Real-SR through simple stacking. Comparative results with 15 SOTA methods across three public datasets underscore the effectiveness and efficiency of our proposed approach.
Interaction intention anticipation aims to jointly predict future hand trajectories and interaction hotspots. Existing research often treated trajectory forecasting and interaction hotspots prediction as separate tasks or solely considered the impact of trajectories on interaction hotspots, which led to the accumulation of prediction errors over time. However, a deeper inherent connection exists between hand trajectories and interaction hotspots, which allows for continuous mutual correction between them. Building upon this relationship, a novel Bidirectional prOgressive Transformer (BOT), which introduces a Bidirectional Progressive mechanism into the anticipation of interaction intention is established. Initially, BOT maximizes the utilization of spatial information from the last observation frame through the Spatial-Temporal Reconstruction Module, mitigating conflicts arising from changes of view in first-person videos. Subsequently, based on two independent prediction branches, a Bidirectional Progressive Enhancement Module is introduced to mutually improve the prediction of hand trajectories and interaction hotspots over time to minimize error accumulation. Finally, acknowledging the intrinsic randomness in human natural behavior, we employ a Trajectory Stochastic Unit and a C-VAE to introduce appropriate uncertainty to trajectories and interaction hotspots, respectively. Our method achieves state-of-the-art results on three benchmark datasets Epic-Kitchens-100, EGO4D, and EGTEA Gaze+, demonstrating superior in complex scenarios.
This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing a variety of 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 10ms. Out of the 160 participants, 25 teams submitted their code and models. The solutions present novel designs tailored for memory-efficiency and runtime on edge devices. This survey describes the best solutions for real-time SR of compressed high-resolution images.