MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering

Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs). Existing approaches either update the parametric knowledge of LLMs with new facts, which is resource-intensive and often impractical, or integrate LLMs with external knowledge retrieval (i.e., retrieval-augmented generation). However, off-the-shelf retrievers often struggle to identify relevant documents that require intensive temporal reasoning. To systematically study time-sensitive question answering, we introduce the TempRAGEval benchmark, which repurposes existing datasets by incorporating temporal perturbations and gold evidence labels. As anticipated, all existing retrieval methods struggle with these temporal reasoning-intensive questions. We further propose Modular Retrieval (MRAG), a trainless framework that includes three modules: (1) Question Processing that decomposes question into a main content and a temporal constraint; (2) Retrieval and Summarization that retrieves evidence and uses LLMs to summarize according to the main content; (3) Semantic-Temporal Hybrid Ranking that scores each evidence summarization based on both semantic and temporal relevance. On TempRAGEval, MRAG significantly outperforms baseline retrievers in retrieval performance, leading to further improvements in final answer accuracy.

PROFIT: A Specialized Optimizer for Deep Fine Tuning

Fine-tuning pre-trained models has become invaluable in computer vision and robotics. Recent fine-tuning approaches focus on improving efficiency rather than accuracy by using a mixture of smaller learning rates or frozen backbones. To return the spotlight to model accuracy, we present PROFIT (Proximally Restricted Optimizer For Iterative Training), one of the first optimizers specifically designed for incrementally fine-tuning converged models on new tasks or datasets. Unlike traditional optimizers such as SGD or Adam, which make minimal assumptions due to random initialization, PROFIT leverages the structure of a converged model to regularize the optimization process, leading to improved results. By employing a simple temporal gradient orthogonalization process, PROFIT outperforms traditional fine-tuning methods across various tasks: image classification, representation learning, and large-scale motion prediction. Moreover, PROFIT is encapsulated within the optimizer logic, making it easily integrated into any training pipeline with minimal engineering effort. A new class of fine-tuning optimizers like PROFIT can drive advancements as fine-tuning and incremental training become increasingly prevalent, reducing reliance on costly model training from scratch.

PROFIT: A PROximal FIne Tuning Optimizer for Multi-Task Learning

Fine-tuning pre-trained models has become invaluable in computer vision and robotics. Recent fine-tuning approaches focus on improving efficiency rather than accuracy by using a mixture of smaller learning rates or frozen backbones. To return the spotlight to model accuracy, we present PROFIT, one of the first optimizers specifically designed for incrementally fine-tuning converged models on new tasks or datasets. Unlike traditional optimizers such as SGD or Adam, which make minimal assumptions due to random initialization, PROFIT leverages the structure of a converged model to regularize the optimization process, leading to improved results. By employing a simple temporal gradient orthogonalization process, PROFIT outperforms traditional fine-tuning methods across various tasks: image classification, representation learning, and large-scale motion prediction. Moreover, PROFIT is encapsulated within the optimizer logic, making it easily integrated into any training pipeline with minimal engineering effort. A new class of fine-tuning optimizers like PROFIT can drive advancements as fine-tuning and incremental training become increasingly prevalent, reducing reliance on costly model training from scratch.

LightWeather: Harnessing Absolute Positional Encoding to Efficient and Scalable Global Weather Forecasting

Recently, Transformers have gained traction in weather forecasting for their capability to capture long-term spatial-temporal correlations. However, their complex architectures result in large parameter counts and extended training times, limiting their practical application and scalability to global-scale forecasting. This paper aims to explore the key factor for accurate weather forecasting and design more efficient solutions. Interestingly, our empirical findings reveal that absolute positional encoding is what really works in Transformer-based weather forecasting models, which can explicitly model the spatial-temporal correlations even without attention mechanisms. We theoretically prove that its effectiveness stems from the integration of geographical coordinates and real-world time features, which are intrinsically related to the dynamics of weather. Based on this, we propose LightWeather, a lightweight and effective model for station-based global weather forecasting. We employ absolute positional encoding and a simple MLP in place of other components of Transformer. With under 30k parameters and less than one hour of training time, LightWeather achieves state-of-the-art performance on global weather datasets compared to other advanced DL methods. The results underscore the superiority of integrating spatial-temporal knowledge over complex architectures, providing novel insights for DL in weather forecasting.

HDR Imaging for Dynamic Scenes with Events

High dynamic range imaging (HDRI) for real-world dynamic scenes is challenging because moving objects may lead to hybrid degradation of low dynamic range and motion blur. Existing event-based approaches only focus on a separate task, while cascading HDRI and motion deblurring would lead to sub-optimal solutions, and unavailable ground-truth sharp HDR images aggravate the predicament. To address these challenges, we propose an Event-based HDRI framework within a Self-supervised learning paradigm, i.e., Self-EHDRI, which generalizes HDRI performance in real-world dynamic scenarios. Specifically, a self-supervised learning strategy is carried out by learning cross-domain conversions from blurry LDR images to sharp LDR images, which enables sharp HDR images to be accessible in the intermediate process even though ground-truth sharp HDR images are missing. Then, we formulate the event-based HDRI and motion deblurring model and conduct a unified network to recover the intermediate sharp HDR results, where both the high dynamic range and high temporal resolution of events are leveraged simultaneously for compensation. We construct large-scale synthetic and real-world datasets to evaluate the effectiveness of our method. Comprehensive experiments demonstrate that the proposed Self-EHDRI outperforms state-of-the-art approaches by a large margin. The codes, datasets, and results are available at https://lxp-whu.github.io/Self-EHDRI.

SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors

We present SHIFT3D, a differentiable pipeline for generating 3D shapes that are structurally plausible yet challenging to 3D object detectors. In safety-critical applications like autonomous driving, discovering such novel challenging objects can offer insight into unknown vulnerabilities of 3D detectors. By representing objects with a signed distanced function (SDF), we show that gradient error signals allow us to smoothly deform the shape or pose of a 3D object in order to confuse a downstream 3D detector. Importantly, the objects generated by SHIFT3D physically differ from the baseline object yet retain a semantically recognizable shape. Our approach provides interpretable failure modes for modern 3D object detectors, and can aid in preemptive discovery of potential safety risks within 3D perception systems before these risks become critical failures.

Structural Inference of Networked Dynamical Systems with Universal Differential Equations

Networked dynamical systems are common throughout science in engineering; e.g., biological networks, reaction networks, power systems, and the like. For many such systems, nonlinearity drives populations of identical (or near-identical) units to exhibit a wide range of nontrivial behaviors, such as the emergence of coherent structures (e.g., waves and patterns) or otherwise notable dynamics (e.g., synchrony and chaos). In this work, we seek to infer (i) the intrinsic physics of a base unit of a population, (ii) the underlying graphical structure shared between units, and (iii) the coupling physics of a given networked dynamical system given observations of nodal states. These tasks are formulated around the notion of the Universal Differential Equation, whereby unknown dynamical systems can be approximated with neural networks, mathematical terms known a priori (albeit with unknown parameterizations), or combinations of the two. We demonstrate the value of these inference tasks by investigating not only future state predictions but also the inference of system behavior on varied network topologies. The effectiveness and utility of these methods is shown with their application to canonical networked nonlinear coupled oscillators.

HyperPrompt: Prompt-based Task-Conditioning of Transformers

Prompt-Tuning is a new paradigm for finetuning pre-trained language models in a parameter-efficient way. Here, we explore the use of HyperNetworks to generate hyper-prompts: we propose HyperPrompt, a novel architecture for prompt-based task-conditioning of self-attention in Transformers. The hyper-prompts are end-to-end learnable via generation by a HyperNetwork. HyperPrompt allows the network to learn task-specific feature maps where the hyper-prompts serve as task global memories for the queries to attend to, at the same time enabling flexible information sharing among tasks. We show that HyperPrompt is competitive against strong multi-task learning baselines with as few as $0.14\%$ of additional task-conditioning parameters, achieving great parameter and computational efficiency. Through extensive empirical experiments, we demonstrate that HyperPrompt can achieve superior performances over strong T5 multi-task learning baselines and parameter-efficient adapter variants including Prompt-Tuning and HyperFormer++ on Natural Language Understanding benchmarks of GLUE and SuperGLUE across many model sizes.

GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting

We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions. Unlike conventional long-tail classifiers which operate on converged - and possibly overfit - models, we demonstrate that an approach based on gradient dot product agreement can isolate long-tailed data early on during model training and improve performance by dynamically picking higher sample weights for that data. We show that such upweighting leads to model improvements for both classification and regression models, the latter of which are relatively unexplored in the long-tail literature, and that the long-tail examples found by gradient alignment are consistent with our semantic expectations.

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

The vast majority of deep models use multiple gradient signals, typically corresponding to a sum of multiple loss terms, to update a shared set of trainable weights. However, these multiple updates can impede optimal training by pulling the model in conflicting directions. We present Gradient Sign Dropout (GradDrop), a probabilistic masking procedure which samples gradients at an activation layer based on their level of consistency. GradDrop is implemented as a simple deep layer that can be used in any deep net and synergizes with other gradient balancing approaches. We show that GradDrop outperforms the state-of-the-art multiloss methods within traditional multitask and transfer learning settings, and we discuss how GradDrop reveals links between optimal multiloss training and gradient stochasticity.