Statistical Theory of Multi-stage Newton Iteration Algorithm for Online Continual Learning

We focus on the critical challenge of handling non-stationary data streams in online continual learning environments, where constrained storage capacity prevents complete retention of historical data, leading to catastrophic forgetting during sequential task training. To more effectively analyze and address the problem of catastrophic forgetting in continual learning, we propose a novel continual learning framework from a statistical perspective. Our approach incorporates random effects across all model parameters and allows the dimension of parameters to diverge to infinity, offering a general formulation for continual learning problems. To efficiently process streaming data, we develop a Multi-step Newton Iteration algorithm that significantly reduces computational costs in certain scenarios by alleviating the burden of matrix inversion. Theoretically, we derive the asymptotic normality of the estimator, enabling subsequent statistical inference. Comprehensive validation through synthetic data experiments and two real datasets analyses demonstrates the effectiveness of our proposed method.

MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying

Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equipped memory module to help the person recall incomplete or vague memories. The limited size of memory module hinders the acquisition of complete memories and impacts the memory recall performance in practice. Memory theories suggest that the person's relevant memory can be proactively activated through some effective cues. Inspired by this, we propose a novel strategy-guided agent-assisted memory recall method, allowing the agent to transform an original query into a cue-rich one via the judiciously designed strategy to help the person recall memories. To this end, there are two key challenges. (1) How to choose the appropriate recall strategy for diverse forgetting scenarios with distinct memory-recall characteristics? (2) How to obtain the high-quality responses leveraging recall strategies, given only abstract and sparsely annotated strategy patterns? To address the challenges, we propose a Recall Router framework. Specifically, we design a 5W Recall Map to classify memory queries into five typical scenarios and define fifteen recall strategy patterns across the corresponding scenarios. We then propose a hierarchical recall tree combined with the Monte Carlo Tree Search algorithm to optimize the selection of strategy and the generation of strategy responses. We construct an instruction tuning dataset and fine-tune multiple open-source large language models (LLMs) to develop MemoCue, an agent that excels in providing memory-inspired responses. Experiments on three representative datasets show that MemoCue surpasses LLM-based methods by 17.74% in recall inspiration. Further human evaluation highlights its advantages in memory-recall applications.

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Recent advances in learning rate (LR) scheduling have demonstrated the effectiveness of decay-free approaches that eliminate the traditional decay phase while maintaining competitive performance. Model merging techniques have emerged as particularly promising solutions in this domain. We present Warmup-Stable and Merge (WSM), a general framework that establishes a formal connection between learning rate decay and model merging. WSM provides a unified theoretical foundation for emulating various decay strategies-including cosine decay, linear decay and inverse square root decay-as principled model averaging schemes, while remaining fully compatible with diverse optimization methods. Through extensive experiments, we identify merge duration-the training window for checkpoint aggregation-as the most critical factor influencing model performance, surpassing the importance of both checkpoint interval and merge quantity. Our framework consistently outperforms the widely-adopted Warmup-Stable-Decay (WSD) approach across multiple benchmarks, achieving significant improvements of +3.5% on MATH, +2.9% on HumanEval, and +5.5% on MMLU-Pro. The performance advantages extend to supervised fine-tuning scenarios, highlighting WSM's potential for long-term model refinement.

Singular Value Fine-tuning for Few-Shot Class-Incremental Learning

Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. The more challenging Few-shot CIL (FSCIL) setting further complicates this by providing only a limited number of samples for each new class, increasing the risk of overfitting in addition to standard CIL challenges. While catastrophic forgetting has been extensively studied, overfitting in FSCIL, especially with large foundation models, has received less attention. To fill this gap, we propose the Singular Value Fine-tuning for FSCIL (SVFCL) and compared it with existing approaches for adapting foundation models to FSCIL, which primarily build on Parameter Efficient Fine-Tuning (PEFT) methods like prompt tuning and Low-Rank Adaptation (LoRA). Specifically, SVFCL applies singular value decomposition to the foundation model weights, keeping the singular vectors fixed while fine-tuning the singular values for each task, and then merging them. This simple yet effective approach not only alleviates the forgetting problem but also mitigates overfitting more effectively while significantly reducing trainable parameters. Extensive experiments on four benchmark datasets, along with visualizations and ablation studies, validate the effectiveness of SVFCL. The code will be made available.

Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution

Burst image processing (BIP), which captures and integrates multiple frames into a single high-quality image, is widely used in consumer cameras. As a typical BIP task, Burst Image Super-Resolution (BISR) has achieved notable progress through deep learning in recent years. Existing BISR methods typically involve three key stages: alignment, upsampling, and fusion, often in varying orders and implementations. Among these stages, alignment is particularly critical for ensuring accurate feature matching and further reconstruction. However, existing methods often rely on techniques such as deformable convolutions and optical flow to realize alignment, which either focus only on local transformations or lack theoretical grounding, thereby limiting their performance. To alleviate these issues, we propose a novel framework for BISR, featuring an equivariant convolution-based alignment, ensuring consistent transformations between the image and feature domains. This enables the alignment transformation to be learned via explicit supervision in the image domain and easily applied in the feature domain in a theoretically sound way, effectively improving alignment accuracy. Additionally, we design an effective reconstruction module with advanced deep architectures for upsampling and fusion to obtain the final BISR result. Extensive experiments on BISR benchmarks show the superior performance of our approach in both quantitative metrics and visual quality.

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks. However, the complete technical details remain unrevealed, and the techniques that are believed certainly to be adopted are only reinforcement learning (RL) and the long chain of thoughts. This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through \textbf{O}utcome \textbf{RE}w\textbf{A}rd-based reinforcement \textbf{L}earning for mathematical reasoning tasks, where only binary outcome rewards are easily accessible. We theoretically prove that behavior cloning on positive trajectories from best-of-N (BoN) sampling is sufficient to learn the KL-regularized optimal policy in binary feedback environments. This formulation further implies that the rewards of negative samples should be reshaped to ensure the gradient consistency between positive and negative samples. To alleviate the long-existing difficulties brought by sparse rewards in RL, which are even exacerbated by the partial correctness of the long chain of thought for reasoning tasks, we further apply a token-level reward model to sample important tokens in reasoning trajectories for learning. With OREAL, for the first time, a 7B model can obtain 94.0 pass@1 accuracy on MATH-500 through RL, being on par with 32B models. OREAL-32B also surpasses previous 32B models trained by distillation with 95.0 pass@1 accuracy on MATH-500. Our investigation also indicates the importance of initial policy models and training queries for RL. Code, models, and data will be released to benefit future research\footnote{https://github.com/InternLM/OREAL}.

Computational Protein Science in the Era of Large Language Models (LLMs)

Considering the significance of proteins, computational protein science has always been a critical scientific field, dedicated to revealing knowledge and developing applications within the protein sequence-structure-function paradigm. In the last few decades, Artificial Intelligence (AI) has made significant impacts in computational protein science, leading to notable successes in specific protein modeling tasks. However, those previous AI models still meet limitations, such as the difficulty in comprehending the semantics of protein sequences, and the inability to generalize across a wide range of protein modeling tasks. Recently, LLMs have emerged as a milestone in AI due to their unprecedented language processing & generalization capability. They can promote comprehensive progress in fields rather than solving individual tasks. As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems. While witnessing prosperous developments, it's necessary to present a systematic overview of computational protein science empowered by LLM techniques. First, we summarize existing pLMs into categories based on their mastered protein knowledge, i.e., underlying sequence patterns, explicit structural and functional information, and external scientific languages. Second, we introduce the utilization and adaptation of pLMs, highlighting their remarkable achievements in promoting protein structure prediction, protein function prediction, and protein design studies. Then, we describe the practical application of pLMs in antibody design, enzyme design, and drug discovery. Finally, we specifically discuss the promising future directions in this fast-growing field.

DroughtSet: Understanding Drought Through Spatial-Temporal Learning

Drought is one of the most destructive and expensive natural disasters, severely impacting natural resources and risks by depleting water resources and diminishing agricultural yields. Under climate change, accurately predicting drought is critical for mitigating drought-induced risks. However, the intricate interplay among the physical and biological drivers that regulate droughts limits the predictability and understanding of drought, particularly at a subseasonal to seasonal (S2S) time scale. While deep learning has been demonstrated with potential in addressing climate forecasting challenges, its application to drought prediction has received relatively less attention. In this work, we propose a new dataset, DroughtSet, which integrates relevant predictive features and three drought indices from multiple remote sensing and reanalysis datasets across the contiguous United States (CONUS). DroughtSet specifically provides the machine learning community with a new real-world dataset to benchmark drought prediction models and more generally, time-series forecasting methods. Furthermore, we propose a spatial-temporal model SPDrought to predict and interpret S2S droughts. Our model learns from the spatial and temporal information of physical and biological features to predict three types of droughts simultaneously. Multiple strategies are employed to quantify the importance of physical and biological features for drought prediction. Our results provide insights for researchers to better understand the predictability and sensitivity of drought to biological and physical conditions. We aim to contribute to the climate field by proposing a new tool to predict and understand the occurrence of droughts and provide the AI community with a new benchmark to study deep learning applications in climate science.

Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Prediction

In recent years, histopathological whole slide image (WSI)- based survival analysis has attracted much attention in medical image analysis. In practice, WSIs usually come from different hospitals or laboratories, which can be seen as different domains, and thus may have significant differences in imaging equipment, processing procedures, and sample sources. These differences generally result in large gaps in distribution between different WSI domains, and thus the survival analysis models trained on one domain may fail to transfer to another. To address this issue, we propose a Dual-branch Encoder and Two-level Alignment (DETA) framework to explore both feature and category-level alignment between different WSI domains. Specifically, we first formulate the concerned problem as graph domain adaptation (GDA) by virtue the graph representation of WSIs. Then we construct a dual-branch graph encoder, including the message passing branch and the shortest path branch, to explicitly and implicitly extract semantic information from the graph-represented WSIs. To realize GDA, we propose a two-level alignment approach: at the category level, we develop a coupling technique by virtue of the dual-branch structure, leading to reduced divergence between the category distributions of the two domains; at the feature level, we introduce an adversarial perturbation strategy to better augment source domain feature, resulting in improved alignment in feature distribution. To the best of our knowledge, our work is the first attempt to alleviate the domain shift issue for WSI data analysis. Extensive experiments on four TCGA datasets have validated the effectiveness of our proposed DETA framework and demonstrated its superior performance in WSI-based survival analysis.

Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method

In this paper, we delve into the realm of 4-D light fields (LFs) to enhance underwater imaging plagued by light absorption, scattering, and other challenges. Contrasting with conventional 2-D RGB imaging, 4-D LF imaging excels in capturing scenes from multiple perspectives, thereby indirectly embedding geometric information. This intrinsic property is anticipated to effectively address the challenges associated with underwater imaging. By leveraging both explicit and implicit depth cues present in 4-D LF images, we propose a progressive, mutually reinforcing framework for underwater 4-D LF image enhancement and depth estimation. Specifically, our framework explicitly utilizes estimated depth information alongside implicit depth-related dynamic convolutional kernels to modulate output features. The entire framework decomposes this complex task, iteratively optimizing the enhanced image and depth information to progressively achieve optimal enhancement results. More importantly, we construct the first 4-D LF-based underwater image dataset for quantitative evaluation and supervised training of learning-based methods, comprising 75 underwater scenes and 3675 high-resolution 2K pairs. To craft vibrant and varied underwater scenes, we build underwater environments with various objects and adopt several types of degradation. Through extensive experimentation, we showcase the potential and superiority of 4-D LF-based underwater imaging vis-a-vis traditional 2-D RGB-based approaches. Moreover, our method effectively corrects color bias and achieves state-of-the-art performance. The dataset and code will be publicly available at https://github.com/linlos1234/LFUIE.