Biqing Qi

Deep learning holds immense promise for spectroscopy, yet research and evaluation in this emerging field often lack standardized formulations. To address this issue, we introduce SpectrumWorld, a unified infrastructure for AI-driven spectroscopy. SpectrumWorld consists of SpectrumLab, a pioneering unified platform designed to systematize and accelerate deep learning research in spectroscopy; SpectrumAnnotator, an annotation and curation module that generates high-quality benchmarks from limited seed data; and SpectrumVQA, a multi-layered benchmark suite covering 14 spectroscopic tasks and over 10 spectrum types, featuring spectra curated from over 1.2 million distinct chemical substances. Thorough empirical studies on SpectrumVQA with 23 cutting-edge multimodal LLMs reveal critical limitations of current approaches. We hope SpectrumWorld will serve as a crucial foundation for future advancements in deep learning-driven spectroscopy. Code is released at https://github.com/InternScience/SpectrumLab.

Molecular function is governed by three-dimensional conformational space, yet foundation models and large language models naturally operate over discrete tokens rather than continuous molecular geometry. Here we introduce Chem3DLLM, a foundation-model interface that makes molecular conformational space accessible through representation, conditioning and physics-informed feedback. Chem3DLLM combines reversible compression of molecular tokenization (RCMT), which encodes atom types, coordinates and bond connectivity into compact language-compatible sequences; protein alignment, which conditions ligand conformational generation on binding-pocket context for structure-based drug design; and reinforcement learning with scientific feedback (RLSF), which uses molecular energetics to refine generated conformations. RCMT gives about threefold character compression while preserving deterministic reconstruction with root-mean-square deviation (RMSD) = 0. In protein-pocket-conditioned generation, Chem3DLLM achieves favourable predicted docking profiles, with average and median Vina scores of -7.21 and -7.10. The same interface supports SMILES-to-3D generation on QM9 with 100\% validity and 100\% uniqueness.Ablation indicates that RLSF adds a modest physics-informed refinement to a representation-driven framework. These results suggest a route for connecting foundation models to 3D molecular design through reversible representation, biological conditioning and physics-informed feedback.

Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of the stored samples. Current Rehearsal-based CL methods typically construct the memory buffer by selecting a representative subset (referred to as coresets), aiming to approximate the training efficacy of the full dataset with minimal storage overhead. However, mainstream Coreset Selection (CS) methods generally formulate the CS problem as a bi-level optimization problem that relies on numerous inner and outer iterations to solve, leading to substantial computational cost thus limiting their practical efficiency. In this paper, we aim to provide a more efficient selection logic and scheme for coreset construction. To this end, we first analyze the Mean Squared Error (MSE) between the buffer-trained model and the Bayes-optimal model through the perspective of localized error decomposition to investigate the contribution of samples from different regions to MSE suppression. Further theoretical and experimental analyses demonstrate that samples with high probability density play a dominant role in error suppression. Inspired by this, we propose the Probability Density-Aware Coreset (PDAC) method. PDAC leverages the Projected Gaussian Mixture (PGM) model to estimate each sample's joint density, enabling efficient density-prioritized buffer selection. Finally, we introduce the streaming Expectation Maximization (EM) algorithm to enhance the adaptability of PGM parameters to streaming data, yielding Streaming PDAC (SPDAC) for streaming scenarios. Extensive comparative experiments show that our methods outperforms other baselines across various CL settings while ensuring favorable efficiency.

Graph Transformers have garnered significant attention due to their ability to address the challenges of long-distance interactions in previous GNNs. However, most current graph Transformers face difficulties when dealing with heterophilic graphs. To investigate this issue, we first analyzed the distribution of attention weights for homophilic and heterophilic graphs. We discovered that heterophily interferes with the allocation of attention weights, leading to errors in node classification. Further investigation revealed that the root cause may be the difficulty of current graph Transformers in capturing the difference between the features of each node and its neighbors. To alleviate this issue, we propose a position encoding strategy called DiSP to better capture the feature difference and introduce FDphormer, a new efficient and simple graph Transformer model based on DiSP. Additionally, we analyze the generalization error of existing graph Transformer models and provide an upper bound on the generalization error of current graph Transformers with the introduction of DiSP. Extensive experiments demonstrate that FDphormer not only outperforms state-of-the-art methods on diverse heterogeneous datasets but also exhibits competitive performance under homophily.

Graph Retrieval Augmented Generation (GraphRAG) effectively enhances external knowledge integration capabilities by explicitly modeling knowledge relationships, thereby improving the factual accuracy and generation quality of Large Language Models (LLMs) in specialized domains. However, existing methods suffer from two inherent limitations: 1) Inefficient Information Aggregation: They rely on a single agent and fixed iterative patterns, making it difficult to adaptively capture multi-level textual, structural, and degree information within graph data. 2) Rigid Reasoning Mechanism: They employ preset reasoning schemes, which cannot dynamically adjust reasoning depth nor achieve precise semantic correction. To overcome these limitations, we propose Graph Counselor, an GraphRAG method based on multi-agent collaboration. This method uses the Adaptive Graph Information Extraction Module (AGIEM), where Planning, Thought, and Execution Agents work together to precisely model complex graph structures and dynamically adjust information extraction strategies, addressing the challenges of multi-level dependency modeling and adaptive reasoning depth. Additionally, the Self-Reflection with Multiple Perspectives (SR) module improves the accuracy and semantic consistency of reasoning results through self-reflection and backward reasoning mechanisms. Experiments demonstrate that Graph Counselor outperforms existing methods in multiple graph reasoning tasks, exhibiting higher reasoning accuracy and generalization ability. Our code is available at https://github.com/gjq100/Graph-Counselor.git.

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this issue, hypernetwork based methods, which utilize neural networks to learn the gradients of non-differentiable quantization functions, have emerged as a promising approach due to their adaptive learning capabilities to reduce estimation errors. However, existing hypernetwork based methods typically rely solely on current gradient information, neglecting the influence of historical gradients. This oversight can lead to accumulated gradient errors when calculating gradient momentum during optimization. To incorporate historical gradient information, we design a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. To further enhance gradient generation in hypernetworks, we propose a Fast and Slow Gradient Generation (FSG) method. Additionally, to produce more precise gradients, we introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients. Extensive comparative experiments on the CIFAR-10 and CIFAR-100 datasets demonstrate that our method achieves faster convergence and lower loss values, outperforming existing baselines.

Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent years for its pivotal role in addressing continuously arriving classes. However, it encounters additional challenges. The scarcity of samples in new sessions intensifies overfitting, causing incompatibility between the output features of new and old classes, thereby escalating catastrophic forgetting. A prevalent strategy involves mitigating catastrophic forgetting through the Explicit Memory (EM), which comprise of class prototypes. However, current EM-based methods retrieves memory globally by performing Vector-to-Vector (V2V) interaction between features corresponding to the input and prototypes stored in EM, neglecting the geometric structure of local features. This hinders the accurate modeling of their positional relationships. To incorporate information of local geometric structure, we extend the V2V interaction to Graph-to-Graph (G2G) interaction. For enhancing local structures for better G2G alignment and the prevention of local feature collapse, we propose the Local Graph Preservation (LGP) mechanism. Additionally, to address sample scarcity in classes from new sessions, the Contrast-Augmented G2G (CAG2G) is introduced to promote the aggregation of same class features thus helps few-shot learning. Extensive comparisons on CIFAR100, CUB200, and the challenging ImageNet-R dataset demonstrate the superiority of our method over existing methods.

Junqi Gao, Xiang Zou, Ying Ai, Dong Li, Yichen Niu, Biqing Qi, Jianxing Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this issue, hypernetwork based methods, which utilize neural networks to learn the gradients of non-differentiable quantization functions, have emerged as a promising approach due to their adaptive learning capabilities to reduce estimation errors. However, existing hypernetwork based methods typically rely solely on current gradient information, neglecting the influence of historical gradients. This oversight can lead to accumulated gradient errors when calculating gradient momentum during optimization. To incorporate historical gradient information, we design a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. To further enhance gradient generation in hypernetworks, we propose a Fast and Slow Gradient Generation (FSG) method. Additionally, to produce more precise gradients, we introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients. Extensive comparative experiments on the CIFAR-10 and CIFAR-100 datasets demonstrate that our method achieves faster convergence and lower loss values, outperforming existing baselines.Code is available at http://github.com/two-tiger/FSG .