Knowledge Distillation

Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a student model. We model teacher and student training as coupled stochastic processes and introduce a distillation divergence, defined as the Kullback-Leibler divergence between these two stochastic kernels. Within this framework, we derive two generalization bounds for the student model relative to the teacher's generalization gap: an upper bound under a sub-Gaussian assumption via algorithmic stability, and a lower bound under a central condition with sharper dependence on the distillation divergence. We further develop a loss-sharpness-aware bound with an explicit tightness regime, showing that the teacher's local flatness can strictly tighten the bound. Additionally, in a linear Gaussian case study, the distillation divergence admits an interpretable decomposition into bias, variance, and rank-bottleneck costs, yielding practical guidance for distillation design.

Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained by low-resource settings, where high-quality annotated \texttt{<question, SQL>} pairs are scarce, particularly for domain-specific databases. Additional challenges include opaque schema definitions, abbreviations, and implicit business logic that are not explicitly encoded in the schema. Existing data synthesis and prompting techniques improve coverage but often fail to produce task-specific, semantically grounded examples aligned with database constraints. To address these challenges, we propose a knowledge-aware Text-to-SQL framework that constructs task-specific knowledge base including schema semantics, abbreviations, business logic, and query patterns, and injects them into both training and inference. This framework generates diverse, contextually grounded synthetic training data and enhances inference through targeted knowledge retrieval. Experiments on seven benchmarks, covering both general and domain-specific datasets, demonstrate that our approach substantially improves the performance of open-source and closed-source large language models in Text-to-SQL tasks, especially in low-resource domain-specific settings, enhancing generalization, robustness, and adaptability.

Face presentation attack detection (FacePAD) remains challenging under diverse spoofing representation, including 2D print and replay, 3D mask-based spoofing, makeup-induced appearance manipulation, and physical occlusions, as well as under varying capture conditions. Motion cues are highly discriminative for FacePAD but typically require explicit optical flow estimation, which introduces substantial computational overhead and limits real-time deployment. In this work, we leverage optical flow to enhance motion representation during training while eliminating the need for flow computation at inference. We propose a dual-branch teacher model that fuses appearance cues from RGB frames with motion cues derived from colorwheel-encoded optical flow, enabling effective modeling of micro-motions and temporal consistency. To enable efficient deployment, we introduce a knowledge distillation framework that transfers motion-aware knowledge from the flow-augmented teacher to a lightweight RGB-only student via logit distillation. As a result, the student implicitly learns motion-sensitive representations without requiring explicit flow estimation or additional feature extraction blocks at inference. Extensive experiments demonstrate strong performance across multiple benchmarks, achieving 0.0% HTER on Replay-Attack and Replay-Mobile, 0.94% HTER on ROSE-Youtu, 5.65% HTER on SiW-Mv2, and 0.42% ACER on OULU-NPU. The distilled student achieves performance comparable to or better than the teacher while significantly reducing parameters and FLOPs, achieving 52 FPS on an NVIDIA Jetson Orin Nano, indicating its suitability for real-time and resource-constrained FacePAD deployment.

SNNs promise energy-efficient and low-latency inference, but their performance still trails that of ANNs. ANN-to-SNN knowledge distillation helps narrow this gap, yet the original training data are often unavailable in practical deployment settings. Existing data-free knowledge distillation (DFKD) methods synthesize surrogate data by matching teacher-side priors, especially BN statistics, but these ANN-oriented constraints mainly regularize mean and variance and therefore remain under-constrained for SNN students whose responses depend on threshold-crossing dynamics. In this paper, we propose Spike Tail-Aware Relational Synthesis (STARS), a plug-and-play method for ANN-to-SNN DFKD that augments standard BN-guided synthesis with two complementary objectives: Relational Consistency Alignment, which preserves cross-sample relational consistency between teacher and student, and Tail-Aware Regularization, which regularizes threshold-relevant tail probabilities through soft exceedance over teacher-derived thresholds. Together, these objectives generate synthetic batches that remain teacher-valid while becoming more informative for SNN students. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet across multiple ANN-SNN pairs show that our method consistently improves conventional DFKD baselines and even surpasses several KD methods, with gains of up to 4.6% on CIFAR-10 and 6.7% on CIFAR-100, highlighting the importance of complementing BN matching with relational and tail-aware constraints in SNN-oriented DFKD.

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate representations. While Hidden Layer Distillation (HLD) showed potential for encoder architectures, its application to decoder-only pre-training at scale remains largely unexplored. Through compute-controlled experiments, we benchmark HLD against logit-based KD and self-supervised baselines with Gemma3 3.4B as teacher and 123M and 735M students trained on up to 168B tokens from the C4 dataset. Our experiments show that HLD does not consistently outperform standard KD on downstream evaluation tasks. Nevertheless, we show that HLD can yield a systematic perplexity gain over KD across all shared-hyperparameter configurations, suggesting that a latent signal can be extracted, but a breakthrough may be needed for it to play a more significant role in LLM pre-training.

Multi-window CT imaging captures complementary pathological information across anatomical structures of differing densities, yet existing deep learning methods fuse representations only at later stages, missing cross-density interactions. We propose a cross-window knowledge distillation framework in which student encoders learn latent clinical priors from a teacher trained on the most informative window. Evaluated retrospectively on three cohorts - COPD-CT-DF (n=719), RSNA PE (n=1,433), and an in-house CTEPD dataset (n=161) - distillation improved per-window AUC by 10.1-16.5 percentage points on COPD-CT-DF (0.75-0.81 to 0.90-0.94; all P<0.001), with ensemble AUC reaching 0.9960. Similar gains were observed on RSNA PE (0.80-0.83 to 0.90-0.92) and CTEPD (AUC 0.7481 vs. 0.6264). Cross-window distillation internalises pathological signatures invisible to supervised approaches, offering a generalisable solution for multi-window pulmonary CT analysis.

While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial prefixes. The absence of class-discriminative patterns in partial data can significantly hinder a classifier's ability to generalize. This work uses knowledge distillation (KD) to equip partial time series classifiers with the generalization ability of their full-sequence counterparts. In KD, high-capacity teacher transfers supervision to aid student learning on the target task. Matching with teacher features has shown promise in closing the generalization gap due to limited parameter capacity. However, when the generalization gap arises from training-data differences (full versus partial), the teacher's full-context features can be an overwhelming target signal for the student's short-context features. To provide progressive, diverse, and collective teacher supervision, we propose Generative Diffusion Prior Distillation (GDPD), a novel KD framework that treats short-context student features as degraded observations of the target full-context features. Inspired by the iterative restoration capability of diffusion models, we learn a diffusion-based generative prior over teacher features. Leveraging this prior, we posterior-sample target teacher representations that could best explain the missing long-range information in the student features and optimize the student features to be minimally degraded relative to these targets. GDPD provides each student feature with a distribution of task-relevant long-context knowledge, which benefits learning on the partial classification task. Extensive experiments across earliness settings, datasets, and architectures demonstrate GDPD's effectiveness for full-to-partial distillation.

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factors: the learning order of training data and the capacity mismatch between teacher and student models. This oversight limits distillation performance, as manifested by the counter-intuitive phenomenon where stronger teachers fail to produce better students. In this work, we propose Curriculum Learning-Guided Progressive Distillation (CLPD), a unified framework that explicitly accounts for both factors by aligning data difficulty with teacher strength. CLPD constructs an explicit curriculum by organizing training examples from easy to hard, while simultaneously applying an implicit curriculum over supervision signals by progressively scheduling teachers of increasing capacity. Our framework is modular and can be integrated into standard distillation algorithms with minimal overhead. Empirical results on the reasoning benchmarks demonstrate that CLPD consistently outperforms standard distillation, data ordering alone, and teacher scheduling alone across multiple settings. These findings highlight the importance of jointly considering data ordering and teacher capacity when distilling reasoning abilities into small language models.

Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and compute requirements remain a concern for practical deployment. A promising class of techniques for mitigating this concern is Knowledge Distillation, where knowledge from a high-capacity Teacher network is transferred to a considerably smaller Student network. However, the capacity gap between the two networks is both a blessing and a curse: the smaller the Student network, the better its efficiency, and the larger the Teacher, the more knowledge it carries; yet, beyond a point, the larger capacity gap between the two leads to worse knowledge transfer. To counter this effect, we propose a bottom-up cascaded knowledge distillation (CKD) framework. Instead of treating knowledge transfer as an activity involving one high-capacity Teacher (or an ensemble of such), inspired by human formal education systems, we introduce one (potentially, more) additional Teacher(s) of intermediate capacity that gradually bring the Student network to the next level, where the next (higher-capacity) Teacher can take over. We provide a theoretical analysis in order to study the effect of cascaded distillation in the generalization performance of the Student. We apply the proposed framework on models build upon the LLaVA methodology and evaluate the derived models on seven standard, publicly available VQA benchmarks, demonstrating their SotA performance.

Recent advancements in Neural Machine Translation (NMT) have significantly improved translation quality. However, the increasing size and complexity of state-of-the-art models present significant challenges for deployment on resource-limited devices. Knowledge distillation (KD) is a promising approach for compressing models, but its effectiveness diminishes when there is a large capacity gap between teacher and student models. To address this issue, we propose Evolving Knowledge Distillation (EKD), a progressive training framework in which the student model learns from a sequence of teachers with gradually increasing capacities. Experiments on IWSLT-14, WMT-17, and WMT-23 benchmarks show that EKD leads to consistent improvements at each stage. On IWSLT-14, the final student achieves a BLEU score of 34.24, narrowing the gap to the strongest teacher (34.32 BLEU) to just 0.08 BLEU. Similar trends are observed on other datasets. These results demonstrate that EKD effectively bridges the capacity gap, enabling compact models to achieve performance close to that of much larger teacher models.Code and models are available at https://github.com/agi-content-generation/EKD.

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B teacher to a 2.29B student model. Our approach achieves 8.7x lower inference latency and a 3x reduction in model size while retaining 54-72% of the teacher's performance. The framework utilizes VGGT as the vision encoder and a multi-task distillation pipeline with uncertainty-aware loss weighting. To improve reasoning without chain-of-thought (CoT) data, we introduce "Hidden CoT": learnable latent tokens that serve as an internal scratchpad before answer generation. This is the first use of latent scratchpad reasoning in distilled 3D VLMs. The student model jointly performs spatial description, depth estimation, and object detection. Experiments on ScanNet and 3D-FRONT show strong spatial understanding, reaching 68-72% accuracy on proximity and contact tasks. Our framework enables efficient 3D scene QA on resource-constrained platforms.

Group Relative Policy Optimization (GRPO) has emerged as a powerful algorithm for improving the reasoning capabilities of language models, but often fails to improve small models due to sparse rewards on difficult tasks. Existing works mitigate this issue by leveraging a larger model, either to provide hints for rollouts or to provide dense reward signals through knowledge distillation (KD). However, this assumes the existence of such an oracle, and training one can significantly increase total training time. In this work, we propose CoDistill-GRPO, a co-distillation algorithm that simultaneously trains a large and a small model by maximizing carefully designed GRPO objectives. The two models learn from each other: the small model uses an on-policy KD reward to learn from the large model's distribution, while the large model is updated using rollouts generated by the small model with importance reweighting, reducing the computational overhead of rollout generation. We show that CoDistill-GRPO substantially improves small model performance over standard GRPO on mathematical benchmarks across both Qwen and Llama models. Specifically, with Qwen2.5-Math-1.5B, we observe an accuracy increase of over 11.6 percentage points over the base model and an additional 6.0 percentage points over GRPO on the Minerva dataset. Interestingly, the larger model (Qwen2.5-Math-7B) trained with CoDistill-GRPO nearly matches standard GRPO performance despite training on small-model rollouts. This highlights CoDistill-GRPO as a cost-effective alternative to GRPO for larger models, yielding an approximate 18% speedup, which may be of independent interest.

Structured pruning and knowledge distillation (KD) are typical techniques for compressing large language models, but it remains unclear how they should be applied at pretraining scale, especially to recent mixture-of-experts (MoE) models. In this work, we systematically study MoE compression in large-scale pretraining, focusing on three key questions: whether pruning provides a better initialization than training from scratch, how expert compression choices affect the final model after continued training, and which training strategy is most effective. We have the following findings: First, across depth, width, and expert compression, pruning a pretrained MoE consistently outperforms training the target architecture from scratch under the same training budget. Second, different one-shot expert compression methods converge to similar final performance after large-scale continual pretraining. Motivated by this, we introduce a simple partial-preservation expert merging strategy that improves downstream performance across most benchmarks. Third, combining KD with the language modeling loss outperforms KD alone, particularly on knowledge-intensive tasks. We further propose multi-token prediction (MTP) distillation, which yields consistent gains. Finally, given the same training tokens, progressive pruning schedules outperform one-shot compression, suggesting that gradual architecture transitions lead to better optimization trajectories. Putting it all together, we compress Qwen3-Next-80A3B to a 23A2B model that retains competitive performance. These results offer practical guidance for efficient MoE compression at scale.

In recent years, the use of edge information provided by knowledge graphs together with the advantages of higher-order connectivity in graph neural networks for recommendation systems has become an important research direction. However, existing approaches are often limited by sparse labels, insufficient graph structure learning, and noisy entities in the knowledge graph, which reduce recommendation accuracy. To address these limitations, we propose a multi-view graph contrastive learning framework. The proposed method enhances user representations through multi-view knowledge graph distillation, enabling more accurate modeling of user preferences over entities and relations. The network aggregates neighborhood entity information to construct informative item representations. Furthermore, we design a multi-level self-supervised contrastive learning module that performs comparisons across three perspectives: Inter-Level, Intra-Level, and Interaction-Level. This design improves the model's ability to generalize across intra-class samples while increasing discrimination between inter-class samples, thereby enabling more effective multi-dimensional feature modeling. We conduct extensive experiments on three public datasets using both baseline and ablation settings. Experimental results demonstrate that the proposed framework consistently outperforms existing state-of-the-art methods. Ablation studies further verify the effectiveness of each module in the proposed model.

Large language models (LLMs) achieve strong performance but remain costly to deploy in resource-constrained settings. Training small language models (SLMs) from scratch is computationally expensive, while conventional knowledge distillation requires repeated access to large teachers for different target sizes, leading to poor scalability. To solve these problems, we propose \textbf{Chain-based Distillation (CBD)}, a scalable paradigm for efficiently initializing variable-sized language models. A sparse and limited sequence of intermediate models (called anchors) is constructed via stepwise distillation, forming a distillation chain that progressively transfers knowledge from the source LLMs. To support heterogeneous settings, we introduce \emph{bridge distillation} for cross-architecture and cross-vocabulary transfer. Models of variable sizes are initialized via parameter interpolation between adjacent anchors, eliminating repeated large teacher inference. Experiments show that the proposed method substantially improves efficiency and downstream performance. A 138M-parameter SLM without recovery pre-training, outperforms scratch-trained models on a 10B-token corpus on the specific task. CBD also demonstrates versatility in heterogeneous settings for initialize models with different architectures and vocabularies.

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap induced by the discrepancy between pre-training and downstream tasks, the real-world computation, and speed constraints. Relevant techniques that probably handle this challenge more or less suffer from some intrinsic limitations. For example, knowledge distillation (KD) assumes that teacher and student models share the same task, training strategy, and model structure family, while prevalent parameter-efficient fine-tuning (PEFT) fails to achieve personalized and lightweight deployment. Even the combination of PEFT and KD still struggles to resolve model structures and training strategies inconsistencies between teacher and student models, leading to inefficient knowledge transfer. In this study, we propose a novel framework called Deep Reprogramming Distillation (DRD) to combat the general adaptation challenge. Specifically, DRD introduces the novel reprogramming module that on the one side overcomes the domain and task discrepancy between pretraining and downstream scenarios, and on the other side builds the student-friendly efficient distillation from foundation models to lightweight downstream models. Furthermore, to mitigate variability under different training conditions, we design a centered kernel alignment (CKA) distillation method to promote robust knowledge transfer. Empirical results show that DRD surpasses previous PEFT and KD methods across 18 medical downstream tasks under different foundation models, covering various scenarios including 2D/3D classification and 2D/3D segmentation.

While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibility and memory-access overhead. We propose an NPU-aware hardware-algorithm co-design approach for real-world image denoising on mobile NPUs. Our approach employs a high-capacity teacher to supervise a lightweight student network specifically designed to leverage the tiled-memory architectures of modern mobile SoCs. By prioritizing NPU-native primitives -- standard 3x3 convolutions, ReLU activations, and nearest-neighbor upsampling -- and employing a progressive context expansion strategy (up to 1024x1024 crops), the model achieves 37.66 dB PSNR / 0.9278 SSIM on the validation benchmark and 37.58 dB PSNR / 0.9098 SSIM on the held-out test benchmark at full resolution (2432x3200) in the Mobile AI 2026 challenge. Following the official challenge rules, the inference runtime is measured under a standardized Full HD (1088x1920) protocol, where it runs in 34.0 ms on the MediaTek Dimensity 9500 and 46.1 ms on the Qualcomm Snapdragon 8 Elite NPU. We further reveal an "Inference Inversion" effect, where strict adherence to NPU-compatible operations enables dedicated NPU execution up to 3.88x faster than the integrated mobile GPU. The 1.96M-parameter student recovers 99.8% of the teacher's restoration quality via high-alpha knowledge distillation (alpha = 0.9), achieving a 21.2x parameter reduction while closing the PSNR gap from 1.63 dB to only 0.05 dB. These results establish hardware-aware distillation as an effective strategy for unifying high-fidelity denoising with practical deployment across diverse mobile NPU architectures. The proposed lightweight student model (LiteDenoiseNet) and its training statistics are provided in the NN Dataset, available at https://github.com/ABrain-One/NN-Dataset.

Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unified approach to explore the common mechanism of various KD methods using interactions. Specifically, we decompose the output score of the LLM into the sum of numerous interactions. Each interaction represents a nonlinear relationship involving a set of input variables (e.g., words). Based on the decomposed interactions, we discover that the common mechanism underlying various KD methods is the sparsification of interactions, i.e., student models retain fewer interactions for inference while suppressing other interactions to zero effects. Furthermore, we discover that the performance variance across different KD methods arises from their capabilities in handling complex interactions. A KD method typically yields better performance if it enables the student model to achieve higher sparsity of complex interactions. Motivated by these insights, we propose a plug-and-play loss function called Complex Interaction Penalty (CIP) to explicitly enforce the sparsity of complex interactions during the distillation process. Extensive experiments demonstrate that integrating CIP consistently improves the performance of diverse KD methods on both in-domain and out-of-distribution benchmarks.

Electrodermal activity (EDA) is widely used in wearable Internet of Medical Things (IoMT) systems for continuous health monitoring, including autonomic assessment. However, EDA signals are highly vulnerable to motion artifacts and environmental noise, limiting reliable deployment in harsh operating conditions such as underwater. This study proposes a robust, deployable EDA denoising framework that generalizes across multiple measurement locations and harsh environments. The framework integrates a hybrid CNN-Transformer teacher model with a lightweight depth-wise separable CNN student model via a knowledge distillation (KD) strategy. To further improve robustness, a realistic data augmentation scheme is introduced to simulate diverse motion artifacts and environmental distortions. The KD-based student model significantly reduces model size (7.87 MB to 0.51 MB) and computational cost (105.1M to 11.61M FLOPs) while maintaining denoising performance (MAE: 0.144, SNR improvement: 12.08 dB) using the public dataset validation. In real-world underwater conditions (UMAC dataset) testing, the proposed method substantially improves skin conductance response reconstruction, reducing mean absolute error from 2.809 to 0.215. Furthermore, on independent testing using the CNS-OT dataset, the denoised signals enhanced downstream CNS-OT prediction performance, achieving the highest AUROC (0.806) compared to prior denoising methods. The proposed method also improved the early prediction rate (sensitivity) from 0.550 to 0.767, enabling CNS-OT prediction up to a median of 6.9 minutes before symptom onset. These results demonstrate that the proposed framework not only improves EDA signal quality but also enhances clinically relevant prediction performance while remaining suitable for deployment in resource-constrained wearable Internet of Things systems operating in harsh environments.

Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little surface similarity. Although large language models (LLMs) have shown promise for semantic clone detection, their use as black-box systems raises concerns about cost, reproducibility, privacy, and unreliable output formatting. In particular, compact open-source models often struggle to follow reasoning-oriented prompts and to produce outputs that can be consistently mapped to binary clone labels. To address these limitations, we propose a knowledge distillation framework that transfers reasoning capabilities from DeepSeek-R1 into compact open-source student models for X-CCD. Using cross-language code pairs derived from Project CodeNet, we construct reasoning-oriented synthetic training data and fine-tune Phi3 and Qwen-Coder with LoRA adapters. We further introduce response stabilization methods, including forced conclusion prompting, a binary classification head, and a contrastive classification head, and evaluate model behavior using both predictive metrics and response rate. Experiments on Python--Java, Rust--Java, Rust--Python, and Rust--Ruby show that knowledge distillation consistently improves the reliability of compact models and often improves predictive performance, especially under distribution shift. In addition, classification-head variants substantially reduce inference time compared to generation-based inference. Overall, our results show that reasoning-oriented distillation combined with response stabilization makes compact open-source models more practical and reliable for X-CCD detection.

Large Language Models (LLMs) have substantially advanced the field of Natural Language Processing (NLP), achieving state-of-the-art performance across a wide range of tasks. These improvements have been attributed, in part, to their emerging reasoning capabilities, which are enabled by large-scale training and increased model capacity. However, existing LLMs can generate erroneous responses when addressing complex queries that fall outside their training distribution, due to limited internal knowledge or the need for multi-step reasoning. To address these limitations, recent work has introduced large reasoning models (LRMs), which incorporate explicit internal reasoning processes to improve response accuracy. Additionally, state-of-the-art LRMs often comprise hundreds of billions of parameters and require several seconds per inference, even on advanced multi-GPU systems. These characteristics limit their practicality for deployment in conventional computing environments. Meanwhile, NLP research on multilingual LLMs continues to prioritize high-resource languages. However, these models exhibit limited performance in under-resourced languages, primarily due to insufficient language- and culture-specific training data. In this paper, we focus on Modern Greek, for which only a limited number of question answering (QA) datasets have been proposed, most of which are intended for model evaluation. To address this research gap in Greek QA, we make the following contributions: (i) CulturaQA, a high-quality LRM-generated and human-curated dataset, for Greek LLM training and evaluation; (ii) a memory-efficient LLM evaluation framework adaptable to diverse languages and QA tasks; (iii) Maistros 8B, a state-of-the-art open-weights Greek LLM developed via knowledge distillation and fine-tuning on CulturaQA; and (iv) a comprehensive evaluation of nine LLMs across nine human-curated Greek QA datasets.

Large language models (LLMs) have achieved remarkable performance across diverse domains, yet their enormous computational and memory requirements hinder deployment in resource-constrained environments. Knowledge distillation offers a promising solution by transferring knowledge from a large teacher model to a smaller student model. However, existing distillation methods typically treat all tokens equally, ignoring the fact that different tokens contribute unequally to model decisions. This can lead to inefficient knowledge transfer and reduced learning effectiveness. To address this limitation, we propose an entropy-based adaptive distillation strategy that dynamically adjusts the training process at the token level. Our method leverages the teacher's output entropy to guide three aspects of distillation. Specifically, we introduce a token-level curriculum by dynamically shifting focus from low- to high-entropy tokens during training. We further adjust the distillation temperature based on token entropy to better capture teacher confidence patterns. Moreover, we employ a dual-branch architecture for efficient logits-only distillation on easy tokens and deeper feature-based distillation on difficult tokens. Extensive experiments validate the soundness and effectiveness of our method.

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach employs a teacher-student paradigm in which a joint teacher model aggregates domain-invariant representations learned from diverse source datasets, while a task-specific student model is trained via multi-level knowledge distillation. Originally developed for medical image segmentation, the framework is extended to support image-level classification and object-level detection, enabling a general multi-task formulation for medical image analysis. We evaluate our method on a broad suite of datasets, including six segmentation benchmarks, BrainMetShare, ISLES, BraTS (MRI) and Lung MSD, LiTS, KiTS (CT), as well as multiple classification datasets for pulmonary disease and dementia, and detection datasets with native bounding-box annotations. Across all tasks and modalities, the proposed approach yields consistent improvements over strong dataset-specific and multi-head baselines, demonstrating enhanced robustness to distributional shifts and superior generalization. These findings highlight the potential of multi-dataset knowledge distillation as a scalable and task-agnostic approach for enhancing segmentation, classification, and object detection performance across heterogeneous medical imaging domains.

Online High-Definition (HD) map construction is a key component of autonomous driving. Recent methods rely on multi-view camera images for cost-effective HD map segmentation, but cameras lack depth information for accurate scene geometry. In contrast, LiDAR provides precise 3D measurements but lacks dense semantic cues. In this work, we propose LIE, LiDAR-only semantic map construction method that employ Knowledge Distillation (KD) to handle the lack of dense semantic and texture cues. Specifically, the teacher branch fuses student LiDAR features and the corresponding 2D intensity map tile to provide dense supervision for segmenting map elements using online distillation scheme. Experimental results show that our method outperforms all single-modality approaches, achieving 8.2% higher mIoU than the state-of-the-art camera-based model on nuScenes. LIE is robust over long ranges and under challenging weather and lighting, and efficiently adapts to Argoverse2 with only 10% fine-tuning, surpassing camera-based models trained on the full dataset. Source code will be available \href{https://iv.ee.hm.edu/lie/}{here}.

Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ignoring how representations evolve across depth. As a result, the student is only weakly guided to capture the teacher's internal relational structure during distillation, which limits knowledge transfer. To address this limitation, we propose Multi-Granular Trajectory Alignment (MTA), a framework that aligns teacher and student representations along their layer-wise transformation trajectory. MTA adopts a layer-adaptive strategy: lower layers are aligned at the word level to preserve lexical information, while higher layers operate on phrase-level spans (e.g., noun and verb phrases) to capture compositional semantics. We instantiate this idea through a Dynamic Structural Alignment loss that matches the relative geometry among semantic units within each layer. This design is motivated by empirical findings that Transformer representations become increasingly abstract with depth, and is also consistent with linguistic views in which higher-level meaning emerges through the composition of lower-level lexical units. We further incorporate a Hidden Representation Alignment loss to directly align selected teacher-student layers. Experiments show that MTA consistently outperforms state-of-the-art baselines on standard benchmarks, with ablations confirming the contribution of each component.

Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While existing approaches mainly focus on token-level alignment strategies, which are often brittle and sensitive to discrepancies between tokenizers, we argue that the method of aggregating tokens into more robust representations before distillation is of equal importance. In this paper, we introduce \textbf{SRA} (\textbf{S}pan \textbf{R}epresentation \textbf{A}lignment for Large Language Model Distillation), a novel framework that reframes CTKD through the physical lens of Multi-Particle Dynamical Systems. SRA shifts the fundamental unit of alignment from tokens to robust, tokenizer-agnostic spans. We model each span as a cluster of particles and represent its state by its Center of Mass (CoM) - an attention-weighted average that captures rich semantic information. We leverage the concept of span centers of mass with attention-derived weighting to prioritize the most salient spans. In addition, we employ a geometric regularizer to preserve the structural integrity of the representation space and introduce aligned span logit distillation to enhance knowledge transfer across models. In challenging cross-architecture distillation experiments, SRA consistently and significantly outperforms state-of-the-art CTKD baselines, validating our physically-grounded approach.

Recent advances in large-scale visual representation learning have significantly improved performance in plant species and plant disease recognition tasks. However, state-of-the-art models, often based on high-capacity vision transformers or multimodal foundation models, remain computationally expensive and difficult to deploy in resource-constrained environments such as mobile or edge devices. This limitation hinders the scalability of automated biodiversity monitoring and precision agriculture systems, where efficiency is as critical as accuracy. In this work, we investigate knowledge distillation as an effective approach to transfer the representational capacity of large pretrained models into smaller, more efficient architectures. We focus on plant species and disease recognition, and conduct an extensive empirical study on two challenging benchmarks: Pl@ntNet300K-v2 and Deep-Plant-Disease. We evaluate four representative architectures, including two ConvNeXt models and two vision transformers, under multiple training regimes: from-scratch training and pretrained initialization, each with and without distillation. In total, we train and evaluate 70 models. Our results show that knowledge distillation consistently improves performance across tasks and architectures. Distilled models are able to match the performance of significantly larger models while maintaining substantially lower computational cost. These findings demonstrate the potential of knowledge distillation techniques to enable efficient and scalable deployment of plant recognition systems in real-world environmental applications.

Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational constraints. Large models achieve high accuracy but fail under INT8 quantization required for edge deployment, while small models sacrifice detection performance. This paper presents a knowledge distillation (KD) framework that trains a compact YOLOv8-S student (11.2M parameters) to mimic a YOLOv8-L teacher (43.7M parameters), achieving 3.9x compression while preserving quantization robustness. We evaluate on full-scale BDD100K (70K training images) with Post-Training Quantization to INT8. The teacher suffers catastrophic degradation under INT8 (-23% mAP), while the KD student retains accuracy (-5.6% mAP). Analysis reveals that KD transfers precision calibration rather than raw detection capacity: the KD student achieves 0.748 precision versus 0.653 for direct training at INT8, a 14.5% gain at equivalent recall, reducing false alarms by 44% versus the collapsed teacher. At INT8, the KD student exceeds the teacher's FP32 precision (0.748 vs. 0.718) in a model 3.9x smaller. These findings establish knowledge distillation as a requirement for deploying accurate, safety-critical VRU detection on edge hardware.

Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice. Knowledge distillation (KD) offers a natural way to transfer knowledge from a powerful teacher to an efficient student; however, standard KD is often less effective for part-structured gait models, where supervision is formed from both part-wise classification logits and part-wise retrieval embeddings. In this paper, we propose GaitKD, a distillation framework that decouples gait knowledge transfer into two complementary components: decision-level distillation and boundary-level distillation. Specifically, GaitKD aligns the teacher and student through part-calibrated logit distillation to transfer inter-class decision relations, while preserving the teacher-induced partitioning of the embedding space through an activation-boundary objective instead of direct feature regression. With a simple aligned part-wise design, GaitKD supports heterogeneous teacher-student gait models without introducing additional inference cost. Experimental results across multiple gait recognition benchmarks and teacher-student configurations show consistent improvements over strong gait baselines. Our study demonstrates that the two transfer components are complementary, and boundary-preserving distillation provides more stable performance than direct feature regression. Source code is available at https://github.com/liyiersan/GaitKD/

Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However, most KD methods require a large training set and internal access to the teacher, which are rarely available due to various restrictions. These challenges have originated a more practical setting known as black-box few-shot KD, where the student is trained with few images and a black-box teacher. Recent approaches typically generate additional synthetic images but lack an active strategy to promote their diversity, a crucial factor for student learning. To address these problems, we propose a novel training scheme for generative adversarial networks, where we adaptively select high-confidence images under the teacher's supervision and introduce them to the adversarial learning on-the-fly. Our approach helps expand and improve the diversity of the distillation set, significantly boosting student accuracy. Through extensive experiments, we achieve state-of-the-art results among other few-shot KD methods on seven image datasets. The code is available at https://github.com/votrinhan88/divbfkd.

Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in decentralized or secure AI ecosystems, privacy regulations and proprietary interests often restrict access to the teacher's interface and original datasets. These constraints define a challenging black-box data-free KD scenario where only top-1 predictions and no training data are available. While recent approaches utilize synthetic data, they still face limitations in data diversity and distillation signals. We propose Diverse Image Priors Knowledge Distillation (DIP-KD), a framework that addresses these challenges through a three-phase collaborative pipeline: (1) Synthesis of image priors to capture diverse visual patterns and semantics; (2) Contrast to enhance the collective distinction between synthetic samples via contrastive learning; and (3) Distillation via a novel primer student that enables soft-probability KD. Our evaluation across 12 benchmarks shows that DIP-KD achieves state-of-the-art performance, with ablations confirming data diversity as critical for knowledge acquisition in restricted AI environments.

Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration schedules. These objectives substantially increase per-iteration cost, meaning equal iteration counts do not correspond to equal training budgets. It is therefore unclear whether reported gains reflect stronger distillation signals or simply greater compute. We show that iteration-based comparisons are misleading: when wall-clock compute is matched, canonical logit- and feature-based KD outperform recent segmentation-specific methods. Under extended training, feature-based distillation achieves state-of-the-art ResNet-18 performance on Cityscapes and ADE20K. A PSPNet ResNet-18 student closely approaches its ResNet-101 teacher despite using only one quarter of the parameters, reaching 99% of the teacher's mIoU on Cityscapes (79.0 vs 79.8) and 92% on ADE20K. Our results challenge the prevailing assumption that KD for segmentation requires task-specific mechanisms and suggest that scaling, rather than complex hand-crafted objectives, should guide future method design.

This position paper argues that knowledge distillation must account for what it loses: student models should be judged not only by retained task scores, but by whether they preserve the teacher capabilities that make those scores reliable. This matters because distillation is increasingly used to turn large teacher models into deployable students, yet headline metrics can obscure losses in the capabilities that make teacher behavior reliable. Conceptually, we show that current evaluation often assumes retained task scores imply retained teacher capabilities. Reframing distillation as a lossy projection exposes this flaw: students may match selected teacher observables without preserving the capabilities that make them reliable. We then synthesize existing evidence into a taxonomy of off-metric distillation losses, showing that such losses are concrete, recurring, and measurable, yet often unaccounted for when studies report what students retain rather than what they lose. To make the position actionable, we propose scenario-specific preservation targets and a Distillation Loss Statement that reports what was preserved, what was lost, and why the remaining losses are acceptable. The goal is not lossless distillation, but accountable distillation.

General audio foundation models have recently achieved remarkable progress, enabling strong performance across diverse tasks. However, state-of-the-art models remain extremely large, often with hundreds of millions of parameters, leading to high inference costs and limited deployability on edge devices. Knowledge distillation is a proven strategy for model compression, but prior work in audio has mostly focused on supervised settings, relying on class logits, intermediate features, or architecture-specific techniques. Such assumptions exclude models that output only embeddings, such as self-supervised or metric-learning models. We introduce S-SONDO (Self-Supervised KnOwledge DistillatioN for General AuDio FOundation Models), the first framework to distill general audio models using only their output embeddings. By avoiding the need for logits or layer-level alignment, S-SONDO is architecture-agnostic and broadly applicable to embedding-based teachers. We demonstrate its effectiveness by distilling two audio foundation models into three efficient students that are up to 61 times smaller while retaining up to 96% of teacher performance. We also provide practical insights on loss choice and clustering-based balanced data sampling. Code is available here: https://github.com/MedAliAdlouni/ssondo.

Wearable sensor-based human gait analysis holds great promise in healthcare, rehabilitation, clinical diagnosis and monitoring, and sports activities. Specifically, ground reaction force (GRF) provides essential insights into the body's interaction with the ground during movement and is typically measured using instrumented treadmills equipped with force plates. However, such equipment is expensive and restricted to laboratory environments. To enable a more portable solution, wearable insole sensors have been used to measure GRF. These sensors, however, are prone to noise and external interference, which reduces measurement accuracy. Deep learning methodologies could be adopted to address these issues, but they often require significant computing resources to achieve high accuracy, limiting their applicability for real-time analysis on portable devices. To overcome these limitations, we propose Selective Correlation Based Knowledge Distillation (SCKD) for estimating GRF from data collected by insole sensors. Our proposed method utilizes selected features considering temporal characteristics in the process of extracting correlation maps for knowledge transfer, enhancing interpretability and mitigating issues in high dimensional data processing. We demonstrate the effectiveness of the compact models generated by our distillation framework through comparison with existing methods. Various configurations of teacher-student architectures and training approaches are examined based on multiple evaluation criteria, utilizing data collected at different walking speeds and with different window sizes. Experimental results confirm that our approach outperforms existing methods in estimating GRF from wearable insole sensor data. Therefore, our approach offers a reliable and resource-efficient solution for human gait analysis.

Serving diverse NLP workloads with large language models is costly: at one enterprise partner, inference costs exceeded $200K/month despite over 70% of queries being routine tasks well within the capability of smaller models. We present RouteNLP, a closed-loop framework that routes queries across a tiered model portfolio to minimize cost while satisfying per-task quality constraints. The framework integrates three components: a difficulty-aware router with shared task-conditioned representations trained on preference data and quality signals; confidence-calibrated cascading that uses conformal prediction for distribution-free threshold initialization; and a distillation-routing co-optimization loop that clusters escalation failures, applies targeted knowledge distillation to cheaper models, and automatically retrains the router, yielding over twice the cost improvement of untargeted distillation. In an 8-week pilot deployment processing ~5K queries/day at an enterprise customer-service division, RouteNLP reduced inference costs by 58% while maintaining 91% response acceptance and reducing p99 latency from 1,847 ms to 387 ms. On a six-task benchmark spanning finance, customer service, and legal domains, the framework achieves 40-85% cost reduction while retaining 96-100% quality on structured tasks and 96-98% on generation tasks, with human evaluation confirming that 74.5% of routed generation outputs match or exceed frontier-model quality.

The real-world adoption of portrait relighting is hindered by dataset domain gaps, camera sensitivity, and computational costs. We address these challenges with Hybrid Domain Knowledge Fusion, a paradigm that fuses the specialized strengths of synthetic, One-Light-at-A-Time (OLAT), and real-world datasets into a compact model. Our approach features specialized prior models hardened by domain-aware adaptation, followed by augmented knowledge distillation into a lightweight student model with multi-domain expertise. Our method demonstrates a 6x to 240x inference speedup while maintaining state-of-the-art (SOTA) visual quality in the experiments. Additionally, we construct a massive, high-fidelity synthetic dataset with diverse ground-truth intrinsics to support our training pipeline.

Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained vision models can be leveraged to learn distortion-robust representations, which can then be effectively applied to downstream tasks operating on distorted observations. In particular, we propose an asymmetric knowledge distillation framework in which both teacher and student are initialized from the same pretrained Vision Transformer but receive different views of each image: the teacher processes clean images, while the student sees their distorted versions. We introduce multi-level distillation that aligns global embeddings, patch-level features, and attention maps and show that the student is able to approximate clean-image representations despite never directly accessing clean data. We evaluate our approach on image classification tasks across several datasets and under various distortions, consistently outperforming existing alternatives for the same amount of human supervision.

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to enhance user understanding with their reasoning capabilities, yet existing integration approaches create prohibitive inference costs in real time. To address these limitations, we present a novel knowledge distillation method that utilizes textual user profile generated by pre-trained LLMs into sequential recommenders without requiring LLM inference at serving time. The resulting approach maintains the inference efficiency of traditional sequential models while requiring neither architectural modifications nor LLM fine-tuning.

Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of existing KD methods and present a unified view that establishes connections between them, reformulating KD as a reweighted log-likelihood objective at the token level. We further propose Hybrid Policy Distillation (HPD), which integrates the complementary advantages of forward and reverse KL to balance mode coverage and mode-seeking, and combines off-policy data with lightweight, approximate on-policy sampling. We validate HPD on long-generation math reasoning as well as short-generation dialogue and code tasks, demonstrating improved optimization stability, computational efficiency, and final performance across diverse model families and scales. The code related to this work is available at https://github.com/zwhong714/Hybrid-Policy-Distillation.

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise, off-policy instability, and, most fundamentally, the teacher-student gap, that distort training signals. These traps manifest as overconfident hallucinations, self-correction collapse, and local decoding degradation, causing distillation to fail. Motivated by these findings, we propose a post-hoc calibration method that, to the best of our knowledge, for the first time enables control over a teacher's distillability via reinforcement fine-tuning (RFT). Our objective combines task utility, KL anchor, and across-tokenizer calibration reward. This makes distillability a practical safety lever for foundation models, connecting robust teacher-student transfer with deployment-aware model protection. Experiments across math, knowledge QA, and instruction-following tasks show that students distilled from distillable calibrated teachers outperform SFT and KD baselines, while undistillable calibrated teachers retain their task performance but cause distilled students to collapse, offering a practical knob for both better KD and model IP protection.

Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy. At the heart of developing CL theory lies the challenge that the data distribution varies across tasks, and we argue that properly addressing this challenge requires understanding this variation--dependency among tasks. To explicitly model task dependency, we consider nonlinear regression tasks and propose the assumption that these tasks are dependent in such a way that the data of the current task is a nonlinear transformation of previous data. With this model and under natural assumptions, we prove statistical recovery guarantees (more specifically, bounds on estimation errors) for several CL paradigms in practical use, including experience replay with data-independent regularization and data-independent weights that balance the losses of tasks, replay with data-dependent weights, and continual learning with data-dependent regularization (e.g., knowledge distillation). To the best of our knowledge, our bounds are informative in cases where prior work gives vacuous bounds.

EEG foundation models (EFMs) achieve strong cross-subject and cross-task generalization through large-scale pretraining and downstream fine-tuning. Through empirical analysis, we observe that (i) task-adapted EFMs provide strong decoding performance but incur substantial overhead when retained as inference backbones, making knowledge distillation a natural route for optimizing compact students; and (ii) direct distillation from a fixed teacher representation underutilizes EFM knowledge, as task-discriminative information is distributed across intermediate layers rather than concentrated in the final layer. These observations motivate DLink (Distilling Layer-wise and Dominant Knowledge), a spectrally guided distillation framework with input-conditioned layer routing for transferring EFM knowledge into compact students. DLink uses a lightweight router to aggregate teacher layers for each input, and aligns magnitude and phase spectra to mitigate compression-induced spectral distortion in learned representations. The routed teacher knowledge is internalized by a project-then-compress student; the teacher and router are used only during training. Experiments on four EEG benchmarks show that DLink improves matched compact students and remains competitive with lightweight baselines, narrowing the gap to fine-tuned EFMs while substantially reducing parameters, FLOPs, and CPU-only inference latency.

Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Distillation (KD) offers a viable way to improve model capabilities without increasing model size or data requirements, making deployment more efficient. However, applying KD to VLMs is challenged by modality-specific supervision: although multimodal knowledge in VLMs is fused within the language space, current methods supervise each modality separately without explicitly addressing multimodal alignment, leading to inconsistent multimodal knowledge transfer. To address this, we propose Switch-KD, a visual-switch distillation framework that unifies vision-language knowledge transfer within a shared text-probability space. Switch-KD comprises two key components: (1) Visual-Switch Distillation, which switches the student's visual outputs into the teacher's language pathway to construct cross-modal probabilistic references for implicit visual knowledge transfer; and (2) Dynamic Bi-directional Logits Difference (DBiLD) loss, which adaptively aligns informative probability regions while preserving the distributional structures of teacher and student through bidirectional supervision. Guided by Switch-KD, a 0.5B TinyLLaVA effectively distills rich multimodal knowledge from its 3B teacher, yielding an average improvement of 3.6 points across 10 multimodal benchmarks without any architectural modification.

Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD). However, the absence of dedicated event-stream anomaly detection datasets and effective modeling strategies has significantly hindered progress in this field. In this work, we take the first major step toward establishing event-based VAD as a unified research direction. We first construct multiple event-stream based benchmarks for video anomaly detection, featuring synchronized event and RGB recordings. Leveraging the unique properties of events, we then propose an EVent-centric spatiotemporal Video Anomaly Detection framework, namely EWAD, with three key innovations: an event density aware dynamic sampling strategy to select temporally informative segments; a density-modulated temporal modeling approach that captures contextual relations from sparse event streams; and an RGB-to-event knowledge distillation mechanism to enhance event-based representations under weak supervision. Extensive experiments on three benchmarks demonstrate that our EWAD achieves significant improvements over existing approaches, highlighting the potential and effectiveness of event-driven modeling for video anomaly detection. The benchmark datasets will be made publicly available.

Instead of directly distilling a language model, this study addresses the problem of aligning a base model with a target model in distribution by designing the domain mixture of training data for pretraining or continued pretraining as a fixed training recipe. We propose a method for determining domain weights by viewing models as points in log-likelihood space and aligning the training update direction with the direction toward the target model. Experiments with NanoGPT show that the proposed method consistently reduces the KL divergence between the trained base model and the target model relative to training with Pile-original weighting. Although knowledge distillation remains more effective when available, the proposed method achieves meaningful alignment, and downstream task performance also tends to become closer to that of the target model.

Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the attention window. We further utilize knowledge distillation from a full-attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache memory reduction and length-invariant, near-constant per-step latency.

Knowledge distillation (KD) is widely used to compress and post-train large language models (LLMs), yet many existing frameworks execute teacher inference with the same training-oriented backend as student optimization, leading to suboptimal efficiency. In this paper, we propose KDFlow, a novel framework for LLM distillation that features a decoupled architecture and employs SGLang for teacher inference. KDFlow combines SGLang for teacher inference with PyTorch FSDP2 for student optimization, allowing each model to run on a backend tailored to its workload. To enable efficient full-vocabulary distillation in this decoupled architecture, KDFlow transfers the teacher's final hidden states via Ray's object store and recomputes teacher logits on each student worker using a frozen copy of the teacher's output head. Furthermore, our framework supports both off-policy and on-policy distillation and incorporates cross-tokenizer algorithms through highly extensible and user-friendly APIs. Experiments show that KDFlow achieves a 1.44$\times$ to 6.36$\times$ speedup over MS-SWIFT in off-policy distillation and a 1.43$\times$ to 1.75$\times$ speedup over verl in on-policy distillation. KDFlow further scales to 64 GPUs, achieving 3.68$\times$ and 2.52$\times$ strong-scaling speedups in two representative model configurations. The code and documentation are publicly available.

Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord annotations, which are costly to acquire. At the same time, open-weight pre-trained models are more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use the pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In Stage 1, using only pseudo-labels, the BTC student achieves about 99% of the teacher's performance, while the 2E1D model achieves about 97% of the teacher's performance across seven standard mir_eval metrics. After continual training with labeled data in Stage 2, the resulting BTC student model consistently surpasses both the traditional supervised learning baseline and the original pre-trained teacher model across all metrics. The resulting 2E1D student model also outperforms the supervised baseline and approaches teacher-level performance, with both models demonstrating substantial gains on rare chord qualities.

Knowledge distillation (KD) is a technique to compress a larger teacher system into a smaller student. In machine translation, KD is commonly evaluated through translation quality and inference efficiency, without jointly accounting for the environmental costs of producing and deploying the distilled system. We evaluate representative KD methods both on bespoke MT models and LLMs, by considering both translation quality and computational cost, using the Machine Learning Life Cycle Assessment tool, which accounts for costs throughout the KD model life cycle. Our key finding is that the deployment volume required to amortize KD is serving-dependent and can shift by several orders of magnitude under batching. We include actionable guidance for selecting, developing, and evaluating KD methods under quality and compute-induced constraints.

Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts, improving factual recall but often failing to integrate updated information into a coherent framework usable across contexts. In this work, we argue that knowledge update is fundamentally a reasoning problem rather than a memorization problem. Consequently, a model should be trained in situations where the new information is instrumental to solving a task, combined with pre-existing knowledge, and exercised through multi-step reasoning. Based on this insight, we propose a training strategy based on three principles. First, new knowledge is introduced as a coherent background story that contextualizes novel facts and explains their relation to existing knowledge. Second, models are trained using self-generated multi-hop questions that require multi-step reasoning involving the new information. Third, training is done using knowledge distillation, forcing a student model to internalize the teacher's reasoning behavior without access to the novel information. Experiments show that models trained with this strategy effectively leverage newly acquired knowledge during reasoning and achieve remarkable performance on challenging questions that require combining multiple new facts.

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: $(i)$ when the teacher provides the exact Bayes Class Probabilities (BCPs); and $(ii)$ supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.

Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge distillation (KD) over lengthy sequences with prompt (P), chain-of-thought (CoT), and answer (A) sections makes the process computationally expensive. In this work, we investigate how the allocation of supervision across different sections (P, CoT, A) affects student performance. Our analysis shows that selective KD over only the CoT tokens can be effective when the prompt and answer information is encompassed by it. Building on this insight, we establish a truncation protocol to quantify computation-quality tradeoffs as a function of sequence length. We observe that beyond a specific length, longer training sequences provide marginal returns for downstream performance but require substantially higher memory and FLOPs. To this end, training on only the first $50\%$ of tokens of every training sequence can retain, on average, $\approx91\%$ of full-sequence performance on math benchmarks while reducing training time, memory usage, and FLOPs by about $50\%$ each. Codes are available at https://github.com/weiruichen01/distilling-the-essence.

Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods. However, such methods typically necessitate computationally expensive sampling, involving multiple forward passes to effectively estimate predictive uncertainty. In this paper, we introduce an approach enabling uncertainty estimation in LLMs without incurring the heavy inference latency typically associated with sampling methods. Specifically, we distill uncertainty-aware teachers - originally requiring multiple forward passes - into single-pass students, fine-tuned using LoRA. We compare two distinct distillation strategies: one in which the student employs traditional softmax-based outputs, and another in which the student leverages Dirichlet-distributed outputs to explicitly model epistemic uncertainty via evidential learning. Empirical evaluation on classification tasks demonstrate that such students can achieve comparable predictive and uncertainty quantification performance relative to their teachers, while requiring only a single forward pass.

Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models. Existing work often faces three key challenges: (1) information loss from hard pruning, (2) inefficient alignment of representations, and (3) underutilization of informative activations, particularly from Feed-Forward Networks (FFNs). To address these challenges, we introduce Low-Rank Clone (LRC), an efficient pre-training method that constructs SLMs aspiring to behavioral equivalence with strong teacher models. LRC trains a set of low-rank projection matrices that jointly enable soft pruning by compressing teacher weights, and activation clone by aligning student activations, including FFN signals, with those of the teacher. This unified design maximizes knowledge transfer while removing the need for explicit alignment modules. Extensive experiments with open-source teachers (e.g., Llama-3.2-3B-Instruct, Qwen2.5-3B/7B-Instruct) show that LRC matches or surpasses state-of-the-art models trained on trillions of tokens--while using only 20B tokens, achieving over 1,000x training efficiency. Our codes and model checkpoints are available at https://github.com/CURRENTF/LowRankClone and https://huggingface.co/collections/JitaiHao/low-rank-clone-lrc-6828389e96a93f1d4219dfaf.

Knowledge distillation is widely used to transfer behavior from a large teacher model to a smaller student. It is often assumed to be safe when the teacher is clean, because classic backdoor attacks rely on poisoned labels and triggers in supervised training, whereas distillation trains the student to match a teacher's outputs. We show that this assumption can fail when the distillation dataset itself is poisoned. Our attack injects triggered and manipulated images that a clean teacher already predicts as an attacker chosen target label, which causes the student to learn a backdoor even though the teacher remains unaffected. We evaluate this threat across multiple manipulation strategies, including targeted adversarial perturbations and targeted GAN based class transitions, and study how distillation settings influence both accuracy and attack success. We show that the attack remains effective even at a 10% poisoning rates. The results demonstrate that a clean teacher alone is not a sufficient safeguard: poisoned distillation data can produce a strongly backdoored student while maintaining competitive performance on clean images. These findings show that the integrity and provenance of distillation data are part of the security boundary of data intensive KD pipelines, even when the teacher itself is trusted.

Knowledge distillation (KD) has been widely studied in unsupervised image Anomaly Detection (AD), but its application to unsupervised multimodal AD remains underexplored. Existing KD-based methods for multimodal AD that use fused multimodal features to obtain teacher representations face challenges. Anomalies that only exist in one modality may not be effectively captured in the fused teacher features, leading to detection failures. Besides, these methods do not fully leverage the rich intra- and inter-modality information that are critical for effective anomaly detection. In this paper, we propose Tuned Reverse Distillation (TRD) based on Multi-branch design to realize Multimodal Industrial AD. By assigning independent branches to each modality, our method enables finer detection of anomalies within each modality. Furthermore, we enhance the interaction between modalities during the distillation process by designing two Crossmodal Tuners including Crossmodal Filter and Amplifier. With the idea of crossmodal mapping, the student network is allowed to better learn normal features while anomalies in all modalities are ensured to be effectively detected. Experimental verifications on multimodal AD datasets demonstrate that our method achieves state-of-the-art performance in multimodal anomaly detection and localization. Code is available at https://github.com/hito2448/TRD.

A novel Learning-by-Education Node Community framework (LENC) for Collaborative Knowledge Distillation (CKD) is presented, which facilitates continual collective learning through effective knowledge exchanges among diverse deployed Deep Neural Network (DNN) peer nodes. These DNNs dynamically and autonomously adopt either the role of a student, seeking knowledge, or that of a teacher, imparting knowledge, fostering a collaborative learning environment. The proposed framework triggers knowledge transfer via autonomous teacher discovery and stream-driven DNN distillation as needed, while enhancing their learning capabilities and promoting their collaboration. LENC addresses the challenges of handling diverse training data distributions and the limitations of individual DNN node learning abilities. \hl{It enables the exploitation of selected peer-teacher knowledge upon learning a new task and mitigates catastrophic forgetting in DNN nodes.} \hl{Additionally, it supports task-boundary-free continual adaptation in distributed settings via autonomous role assignment and modular forgetting mitigation, as DNN nodes receive no explicit task-boundary metadata during deployment.} Experimental evaluation on a proof-of-concept implementation demonstrates the LENC framework's functionalities and benefits across multiple DNN learning and inference scenarios. The conducted experiments showcase its ability to gradually improve the average test accuracy of the community of interacting DNN nodes in image classification problems, by appropriately leveraging the collective knowledge of all node peers. The LENC framework achieves strong performance in on-line unlabelled CKD.

Knowledge distillation transfers knowledge from large teacher models to more compact student networks. The standard approach minimizes the Kullback-Leibler (KL) divergence between the probabilistic outputs of the teacher and student, aligning predictions but neglecting the structural relationships encoded within the teacher's internal representations. Recent advances have adopted contrastive learning objectives to address this limitation; however, such instance-discrimination-based methods induce a "class collision problem", in which semantically related samples are inappropriately pushed apart despite belonging to similar classes. To overcome this, we propose Relational Representation Distillation (RRD) that preserves the relative relationships among instances rather than enforcing absolute separation. Our method introduces separate temperature parameters for teacher and student distributions, with a sharper teacher (low $τ_t$) emphasizing primary relationships and a softer student (high $τ_s$) maintaining secondary similarities. This dual-temperature formulation creates an implicit information bottleneck that preserves fine-grained relational structure while avoiding the over-separation characteristic of contrastive losses. We establish theoretical connections showing that InfoNCE emerges as a limiting case of our objective when $τ_t \rightarrow 0$, and empirically demonstrate that this relaxed formulation yields superior relational alignment and generalization across classification and detection tasks.

We introduce a training-free safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning or reinforcement learning from human feedback. Our main idea is to provide a robust plug-and-play approach to prevent shadow alignment when models are adapted to downstream tasks. Specifically, we leverage knowledge distillation to extract alignment signals from well-aligned LLMs and inject them into shadow-aligned models via model fusion, enabling plug-and-play alignment correction. In our methodology, we employ delta debugging to identify the critical components of knowledge necessary for effective distillation. On the harmful question dataset, our method significantly enhances the average defense success rate by approximately 14.42%, reaching as high as 51.39% across 17 influenced LLMs, without compromising performance. Our code is available at https://github.com/NWULIST/DAPA.