Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation

A compressed student has two shapes that need not agree: the weight it deploys at inference and the weight family its training can reach. We show that a state-of-the-art weight-inheritance distiller, Low-Rank Clone (LRC), deploys a full-width student MLP but ties training to a teacher-induced slice, leaving 62.5-81.4% of each deployed matrix's independent linear degrees of freedom unreachable-paid for at inference, never trainable. Our principle is one line: train what you deploy. From the identical LRC warm start, we make the training object the entire deployed matrix, with no change in deployed shape, deployed parameter count, or inference FLOPs, via two mergeable realizations (Dense-LRC and CORE-LRC) that both collapse to one deployed weight. This recovers stranded capacity: taking the stronger realization per teacher, +2.36/+2.71/+10.45 Avg9 over matched-budget plain-LRC baselines across three teachers (Llama3.2-3B, Llama3.1-8B, Qwen2.5-3B), with the largest gain on the widest teacher (Qwen), where it reaches the original recipe's approx. 20B-token accuracy at 10B tokens (2x token efficiency); there the strictly same-lineage arm still recovers +6.39, the fully controlled figure. Controls strongly support attributing the gain to the enlarged reachable set, rather than to added parameters or the recipe. From approx. 10B distillation tokens plus a short SFT, a half-parameter 1.5B student matches its approx. 9T-token teacher's 9-task macro-average, within evaluation noise and with a residual MMLU deficit, and a 2.7B student beats Meta's own official compression of Llama3.1-8B at ~900x fewer compression tokens (a token count under unmatched recipes, not a compute claim). All results are from single-seed runs on the LRC backbone.

Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Edge-Deployable Virtual Sensing

Virtual sensing enables digital twins and safety-critical systems to reconstruct and forecast spatial-temporal physics in real time. However, conventional computational and data-driven methods often face challenges in generalization, latency, and energy efficiency for edge deployment. Neural operators offer a promising alternative but remain reliant on power-intensive hardware. Spiking neurons and neuromorphic computing can improve efficiency, yet surrogate-gradient training and multi-step spiking introduce convergence and latency challenges. We propose the Sparse-Activation-ReLU (SAR) layer, a single-step alternative that promotes activation sparsity without surrogate-gradient training while remaining compatible with event-based computing. Within a trunk-based NOMAD architecture, SAR achieves over a fivefold improvement in the combined Latency-Error-Energy (LEE) metric compared with Variable Spiking Neuron (VSN) and Leaky Integrate-and-Fire (LIF) implementations. We further analyze spiking entropy and feature usage and introduce synthetic knowledge distillation, reducing the LEE score by more than twofold. Finally, we improve VSN through a ReLU-based spiking loss and graph-neighbor thresholding. On the Heat Exchanger dataset, these approaches reduce L2 error by more than twofold and nearly sevenfold, respectively, while reducing spiking and spatial aggregation. Overall, the work presented is a step towards energy-efficient virtual sensing by providing an alternative framework that can be positioned towards neuromorphic or other edge device integration that can be a gold standard to compare latency, energy, and error performance for future efficient designs that are sparsity or brain-inspired spiking based.

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together these steps degrade reasoning, mathematics, coding, and long-context behavior enough to require a recovery, or healing, stage before deployment. The default recipe, quantization-aware training (QAT), re-fits the compressed, quantized model to hard labels; in our pipeline it converged slowly and collapsed past its peak. We adopted Quantization-Aware Healing (QAH) instead. Because a structurally compressed model is never independently trained at full precision, its bfloat16 checkpoint is a distillation-recovered approximation of the original; QAH distills the 4-bit student directly from the original, uncompressed model. On a GPT-OSS 120B to 60B to MXFP4 pipeline, the QAH student matches or beats its bfloat16 source on 7 of 9 benchmarks at roughly 4 times less weight memory and half the teacher's parameter count, and is released open-weight as Hypernova-60B. Against a matched QAT baseline it reaches a comparable peak about 7 times faster and stays stable under continued training, without hand-tuned early stopping. We also report deployment lessons, including a large, reproducible quality gap between distributed-training backends. Our aim is a recipe deployable without a multi-week hyper-parameter search.

Bern2Edge: A Neurosymbolic Compiler for Edge Deployment via Bernstein Polynomial Networks

Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, and hardware synthesis as separate stages, leaving a gap between software-trained models and efficient end-to-end deployment with limited support for interpretability. We propose Bern2Edge, an end-to-end framework that uses knowledge distillation to convert a pretrained teacher feed-forward network into hardware-efficient representations via Bernstein polynomial activations. This representation enables two deployment paths: (i) a high-fidelity LUT-based realization that preserves model fidelity under compression, and (ii) a symbolic rule-based representation derived from Bernstein activation geometry, enabling interpretable inference with explicit input-space constraints. The resulting BNNs achieve up to 2.12 percentage-point (pp) accuracy improvement over ReLU under identical compression constraints. At the system level, Bern2Edge achieves up to 99.8% latency reduction and 95.2% BRAM reduction relative to a W8A8 quantized teacher on an AMD Xilinx KV260 FPGA, while maintaining accuracy within 0.5 pp, and further deploys on a low-power Spartan-7 XC7S15 FPGA. The rule-based path reduces DSP usage by up to 89.0% at a cost of 1.5 pp in total accuracy.

Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation

Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge. Federated knowledge distillation (FedKD) alleviates model heterogeneity by combining prototype-wise parameter aggregation and knowledge transfer across heterogeneous models. However, transmitting gradients still introduces considerable communication overhead, while existing compression approaches typically apply a uniform strategy across clients and ignore their diverse model characteristics and resource capacities. To address this issue, we propose a heterogeneous compression framework for FedKD that enables each client to select a compression strategy from a candidate strategy set. We formulate the compression strategy selection problem as a non-stationary stochastic multi-armed bandit (MAB), where each arm corresponds to a compression strategy. An efficiency-aware reward is designed by jointly considering local optimization improvement, global knowledge alignment, and execution time. Based on this formulation, we develop an Adaptive heterogeneouS Compression algorithm for fEderated kNowledge Distillation (ASCEND), which employs an exponential moving average (EMA)-enhanced $ε$-greedy policy to balance exploration and exploitation. Experimental results on multiple datasets demonstrate that ASCEND effectively adapts to heterogeneous model and resource settings, reducing communication overhead and training time while maintaining competitive model accuracy.

SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often unavailable due to privacy, copyright, or cost constraints. Knowledge Distillation (KD) is a common approach to address this challenge, but we observe that prior work combining QAT with KD suffers from a fundamental limitation: during distillation, the range mismatch between the teacher and the quantized student model induces an unattainable residual, resulting in an irreducible lower bound on the distillation loss. Motivated by this observation, we propose SQuaT (Student-Aware Quantized Teacher Features), a label-free QAT framework with KD that theoretically eliminates this lower bound by applying the student's quantization parameters to quantize the teacher's features during distillation. Through comprehensive experiments across diverse settings, we demonstrate that SQuaT consistently outperforms strong baselines, with particularly pronounced gains in extreme low-bit (e.g., 1- and 2-bit) settings. Furthermore, extensive evaluations across various model design choices show that our approach does not rely on specific architectural assumptions, making it broadly applicable across diverse architectures and quantization settings. The source code is available at https://github.com/lcdbsa522/SQuaT.

Out-of-Distribution Federated Distillation with Domain-Aware Proxy

Federated Learning is a distributed machine learning paradigm that trains a global model by aggregating local clients without sharing private data of each client. Federated Distillation (FD) builds upon this paradigm by leveraging knowledge distillation to exchange soft predictions on proxy data instead of model parameters, enabling more efficient communication and supporting heterogeneous model collaboration. However, FD models trained on In-Distribution data are hardly adapted to Out-of-Distribution (OOD) scenarios. In this paper, we propose a domain-aware proxy selection framework to better adopt proxy data for OOD problems. The experimental results show that the proposed models effectively address the challenges of distribution shifts under OOD with and without proxy data by achieving average 82.9\% and 80.6\% over existing works on standard benchmarks. The codes and data are released in https://anonymous.4open.science/r/DPS-FD-8596.

A Controlled Study of Feature-Based Knowledge Distillation Across Student Designs

Knowledge distillation trains a smaller student to match the outputs of a larger teacher. Feature-based methods also align intermediate representations, but this extra constraint may affect students differently. We study this question on CIFAR-100 using a ResNet-50 teacher, a width-controlled CustomResNet family and MobileNetV2 as a cross-design comparison. For each student, we evaluate each feature method against a matched logit-KD run using the same teacher, optimizer settings, training schedule and seed. We repeat the main comparisons across multiple seeds. Logit KD improved every tested student over its scratch baseline. Attention Transfer showed no clear relationship with size inside the CustomResNet family, but its average effect was negative for that family and positive for MobileNetV2. FitNets was below logit KD in all 15 paired runs. Within the constant-depth width sweep, its gap increased for wider students, although the different-depth w=48 student did not follow this trend. Finally, the same auxiliary coefficient produced different gradient scales across students, showing that a fixed coefficient does not create a uniform training condition.

EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models

Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training. Nevertheless, increasing model sizes impose substantial computational demands on client devices, limiting FL applicability in resource-constrained settings. We introduce a novel multi-domain federated learning framework in which lightweight client-side proxy models collaborate with a server-side Foundation Model (FM) to learn new concepts without sharing private data. Our approach, EFFEKT, enables efficient server-side training of domain-specific LoRA adapters while preserving feature-space alignment between the FM and proxy extractors via novel bi-directional cross-distillation strategies. Experiments on multiple real-world datasets and deployments on low-power edge devices demonstrate improvements over state-of-the-art baselines in most considered domains while maintaining lightweight computation at the client side.

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained from scratch: a compressed model is usually recovered through knowledge distillation (KD). This recovery step largely decides the final quality, yet it is expensive. We present a practitioner's study of how to make distillation training efficient, organised around two systems contributions. First, we show that offline KD (caching the teacher's top-$K$ logits once and training the student against the cache) matches online distillation at near-identical training loss while removing the teacher from memory, running about 29\% faster per iteration, and reaching up to 41\% higher throughput on a single H200 GPU. Second, we introduce a \emph{fused, chunked KL loss} that never materialises the full vocabulary-sized logit tensor, making peak memory linear in the sequence length. This removes the memory spike that otherwise caps context length and lets us train at four times the context (32{,}768 tokens) on a single GPU. A separate output-head-only toy benchmark isolates the loss kernel and confirms its memory and iteration-rate scaling from 4K to 256K tokens. Together these make large-scale healing and hundreds of ablations affordable. We also report supporting ablations on loss design and sequence packing. We release our chunked-loss implementation: https://github.com/CompactifAI/Full-Chunked-KL-Loss.

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-constrained edge devices, Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Artificial Neural Networks (ANNs) due to their sparse computing mechanisms and high energy efficiency. However, jointly training ANNs and SNNs exposes a challenge of representational misalignment, which is intrinsically caused by differences in information representation, specifically the semantic gap between continuous real-valued activations in ANNs and discrete spatio-temporal spikes in SNNs. To overcome this barrier, we propose AS-FedBridge, a novel federated learning framework tailored for mixed ANN-SNN clients. AS-FedBridge features a lightweight Bridge equipped with a Pseudo-Spike Interface, which effectively projects continuous signals into a spike-compatible space to facilitate ANN-SNN alignment. Given the absence of existing mixed ANN-SNN federated frameworks, we establish a comprehensive benchmark to evaluate against multiple advanced heterogeneous FL methods. Our empirical analysis demonstrates a positive correlation between the degree of ANN-SNN alignment and the collaborative FL performance. Across four datasets, AS-FedBridge consistently demonstrates advanced accuracy while mitigating extreme scale, architecture, and client heterogeneity challenge. Furthermore, our framework enables a highly controllable trade-off between model performance and resource efficiency. AS-FedBridge accomplishes these robust performance gains while introducing only marginal computational overhead, establishing a robust and practical foundation for mixed ANN-SNN federated learning systems.

CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation

Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression. The emergence of diverse model architectures has extended KD from homogeneous to heterogeneous settings. However, differences in architectural inductive biases between the teacher and student models often result in substantial representation discrepancies, limiting the effectiveness of direct knowledge transfer. Recently, redundancy suppression has offered a new perspective on heterogeneous KD by preserving cross-architecture invariance and reducing feature redundancy through decorrelation of teacher-student feature correlations. Nevertheless, this formulation may weaken useful structural information through uniform decorrelation, while a fixed coefficient may make the effective contribution of redundancy suppression sensitive to teacher-student pairs and training stages. To address these problems, Correlation Calibration-based Redundancy Suppression (CoCaRS) is proposed to better retain structural information while suppressing redundancy and reduce sensitivity to coefficient settings across teacher-student pairs and training stages. Specifically, CoCaRS calibrates feature decorrelation through Confusion Evidence Estimation (CEE) and Strength Allocation Control (SAC), which respectively capture reliable semantic relations for correlation estimation and preserve discriminative structure during decorrelation. Adaptive Coefficient Regulation (ACR) further regulates the contribution of the calibrated redundancy suppression objective according to its relative loss scale, reducing sensitivity to coefficient settings. Extensive experiments on CIFAR-100 and ImageNet-1K validate the effectiveness of CoCaRS in improving distillation performance and reducing sensitivity to coefficient settings. Code will be released soon.

SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation

Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute settings such as hospital equipment and energy infrastructure. Predominant knowledge distillation (KD) methods favor replication: smaller students mimic teacher output logits, yet empirically yield low task performance, hamper convergence, and act merely as regularization rather than substantive knowledge transfer. We propose Saddle Point Recruitment for Knowledge Distillation (SPRKD), reframing distillation from replication to employing teachers as optimization-curvature and domain proxies, characterizing saddle points as regions of strong further-descent potential via embedding and basin-fractal properties. Using Hessian eigenvalue spectral density (ESD), SPRKD identifies low-loss saddle regions for student re-exploration; weak-teacher ensembles are aggregated into an Approximated Saddle Region (ASR), re-parameterized into the student via Transfer Learning by Injection, and approached with exponentially decaying Euclidean transformations, Negative Hessian Eigensteps, and Gaussian perturbations. On malaria blood smear classification with a 6,430-parameter CNN distilled from a weak 25,546-parameter teacher, SPRKD reaches 94.8% validation accuracy, outperforming Response KD by 24.70 percentage points (McNemar p = 6.3e-87) and matching scratch-trained baselines of the same architecture to statistical equivalence (p = 1.0). Across MNIST, CIFAR-100, and TinyImageNet, SPRKD exceeds scratch-trained baselines by up to 8 percentage points on preliminary benchmarks. Hessian ESD and 2-D loss landscape analysis show convergence to wider minima with substantially smaller Hessian trace and spectral radius than Response KD and control students, indicating smoother descent and greater noise robustness.

Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems

The rapid deployment of machine learning systems across cloud, edge, and enterprise environments has brought model optimization to the forefront of systems-engineering. Despite a rich literature spanning quantization, pruning, knowledge distillation, parameter-efficient fine-tuning (PEFT), and inference-time optimization, practitioners are often left navigating these techniques through heuristics rather than principled methodology. We argue that optimization should be formulated as a constraint-driven, multi-objective engineering decision and introduce a unified framework that characterizes any production deployment along five interacting constraint dimensions: data availability, latency budget, memory budget, accuracy tolerance, and retraining budget. Building on this taxonomy, we synthesize empirical gains reported across the research literature and map them to operational constraints rather than algorithmic categories. To ensure practical relevance, we selected these techniques by reviewing recent literature for methods that report measurable improvements against critical deployment bottlenecks. We propose a prescriptive decision framework and provide optimization pipelines for four representative industrial scenarios to illustrate it in practice. To the best of our knowledge, this work provides one of the first structured attempts to formalize model optimization as a constraint-aware, multi-objective engineering process, synthesizing quantitative evidence from the research literature.

EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models

Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillation (OPD) instead collects teacher or evaluator supervision on student-generated rollouts. However, existing OPD methods differ substantially in supervision form, tokenizer compatibility, teacher access, and supervision granularity, leading to fragmented implementations that are difficult to reproduce and extend. We present \textsc{EasyOPD}, an on-policy distillation framework built on verl, a distributed reinforcement-learning framework for large language models. \textsc{EasyOPD} separates user-side configuration, method-specific supervision logic, and verl-based execution. Its method modules connect to the shared backend through extension boundaries for loss construction, rollout metadata, reward processing, tokenizer alignment, and teacher-side computation. We instantiate representative methods for three OPD settings -- cross-tokenizer OPD, on-policy self-distillation, and step-wise OPD. Experiments on reasoning, code-generation, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles. We release \textsc{EasyOPD} with runnable YAML configurations, documentation, and an installable demonstration package and video.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs

We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the model to maximize server throughput under high user throughput constraints. In interactive serving workloads on a single 8xB200 node, Puzzle-75B-A9B achieves approximately 2x higher server throughput than Nemotron-3-Super at matched user throughput constraints. In ultra-long-context deployment on a single H100 GPU, the compressed model increases 1M-token concurrency from 1 request to 8 requests. Puzzle-75B-A9B is constructed using a multi-stage pipeline that combines the Iterative Puzzle compression framework with knowledge distillation, reinforcement learning, quantization, and a Multi-Token Prediction head. The compression process jointly optimizes heterogeneous MoE pruning, active parameter budget, and Mamba pruning to improve inference efficiency while preserving model quality. We evaluate Puzzle-75B-A9B on a broad suite of reasoning, coding, multilingual, long-context, and agentic benchmarks. Despite substantial compression, the model retains strong downstream accuracy relative to the parent model across a wide range of tasks. These results demonstrate that large hybrid MoE models can be substantially optimized for deployment efficiency while maintaining strong downstream capability. Our model is publicly available on Hugging Face.

Data-driven Video Codec with Implicit Neural Representations

A conventional codec stores a video as compressed pixel data. We instead store the video, together with its audio track, as the weights of a single sinusoidal representation network (SIREN) that maps space-time coordinates to RGB values and audio amplitudes. The network uses separate audio and video initialization layers, a stack of shared fully connected hidden layers, and three output branches: one for video and two Siamese audio branches whose disagreement is used to estimate and subtract residual noise. The overfitted teacher network is then compressed by response-based knowledge distillation into a smaller student, followed by 16-bit symmetric weight quantization and lossless LZMA2 (xz) encoding. On a 6.08 MiB test video, the quantized student reaches a video PSNR of 28.72 dB with SSIM of 0.75, and an audio PSNR of 24.18 dB with a log spectral distance of 10.69 dB, while the pipeline shrinks the representation from 9.05 MiB to 2.33 MiB, an overall compression ratio of 2.61. A bit-width sweep from 1-bit to 32-bit quantization shows that reconstruction quality saturates at 16 bits. We compare against H.264, HEVC, and MP3, report where the approach falls short of them, and describe a browser-based prototype that trains, transfers, and decodes these models over WebRTC.

Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification

Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware. We present a multi-seed benchmark jointly evaluating federated learning (FL) and knowledge distillation (KD) for 3D point cloud classification. It spans 13 FL algorithms and 10 KD objectives (a 130-pair cross-product) across 504 training runs, evaluated on ModelNet40 and a clinical craniosynostosis dataset. We report three findings. First, under extreme non-IID label skew, standalone FL degrades sharply: on ModelNet40, the strongest method reaches 76.32% against a 92.26% centralized reference; on clinical data, the best reaches 75.83% against 100%. Second, distillation successfully compresses the teacher into a student 74.51% smaller and roughly twice as fast at inference, often matching or surpassing the teacher. Third, the combined pipeline exposes an evaluation pitfall: when distillation keeps a hard-label cross-entropy term on a labeled proxy split, a collapsed federated teacher (8.50%) paired with Logit-MSE still yields a 92.94% student. This 84.4-point gap reflects the proxy labels rather than the federated model, reusing the very labels whose privacy motivated federation. Objectives without hard labels instead track teacher quality ($r \approx 0.99$) and collapse when the teacher does. We therefore recommend evaluating FL-KD pipelines with label-free distillation so reported accuracy reflects the federated teacher, not the proxy.

SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks

Log parsing is a fundamental step in automated log analysis, transforming raw system logs into structured event templates for downstream tasks such as anomaly detection and system monitoring. Existing log parsing methods range from rule-based and clustering-based approaches to neural models that learn semantic representations from log messages. However, neural approaches typically rely on dense matrix multiplications, which can result in high computational cost and energy consumption. This paper presents SpikeLogBERT, a spiking neural network framework for energy-efficient log parsing. The proposed model integrates a spiking transformer architecture with knowledge distillation from a BERT teacher model, enabling spike-driven computation while preserving semantic representation capability. By leveraging sparse spike activations and event-driven processing, the number of active operations during inference can be significantly reduced. As an initial benchmark study, experiments on the HDFS dataset demonstrate that SpikeLogBERT outperforms ANN-based neural log parsing models with a parsing accuracy of 0.99997, while reducing estimated theoretical energy consumption by up to 62.6% under standard 45nm CMOS assumptions.

Optimizing Teacher-Student Partitioning for Scalable Knowledge Distillation on HPC Systems

Knowledge Distillation (KD) enables training smaller student models under the guidance of larger teacher models, and the widely adopted TRL library implements it. Yet, TRL treats both models symmetrically, missing opportunities to exploit their pronounced asymmetry in memory footprint, and communication requirements. This paper presents an HPC-aware methodology for KD that decouples teacher and student partitioning efficiently. Our approach achieves up to 67% higher samples-per-second than TRL by avoiding unnecessary teacher-model data structures and selecting the best split strategy. We combine vertical and horizontal partitioning of models, deriving an analytical expression that identifies the existence of inflection points between splitting regimes. These results showed that exploiting teacher--student asymmetry through topology-aware parallelism notably accelerated GKD training on production HPC clusters at our company

Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning

Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational overhead of the distillation process itself is often overlooked, raising the question of whether a better student model can be obtained with less data and less compute via data pruning. However, existing data pruning methods are not designed for KD: some introduce substantial overhead, such as obtaining training dynamics through retraining, while others rely on heuristic selection rules that fail to capture what KD actually requires, often resulting in suboptimal subsets. To address these issues, we propose IF-Beta, an efficient data pruning framework that combines influence functions with a learnable sampling policy. Empirically, we first demonstrate that influence functions can serve as an effective and efficient estimator of sample impact in KD settings, where only a pretrained teacher is available. Building on this, our sampling policy is specifically parameterized by a Beta distribution, whose highly flexible two-parameter family allows the policy to adapt to diverse pruning regimes rather than being tied to fixed heuristic forms. Next, we formulate KD pruning as optimizing this policy through a bilevel objective, where the inner loop operates in the teacher feature space with a KD-aligned objective, enabling fast proxy training, while the outer loop updates the policy parameters to maximize distillation performance. This design ensures that IF-Beta is both computationally efficient and inherently aligned with the goals of KD. Extensive experiments on CIFAR-10/100 and ImageNet show that IF-Beta consistently outperforms other baselines across a wide range of pruning ratios. Remarkably, IF-Beta enables students trained on less data and less compute to surpass the performance of students distilled on the full dataset.

Scaling Laws for Task-Specific LLM Distillation

Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives empirical scaling laws for domain-specific LLM compression, quantifying how in-domain and general knowledge performance scale with dataset size, compression ratio, supervision format, and iterative pruning schedule. Using quantitative finance as our application domain, we compare logit-based and LoRA-based distillation under iterative structural pruning, introducing a blended chain-of-thought supervision loss that stabilizes KL-divergence distillation over reasoning traces. In-domain task quality degrades predictably under compression while general-knowledge benchmarks collapse well before the same point; supervision format is the key driver of this tradeoff, with chain-of-thought supervision actively recovering general knowledge that pruning erases. We release the headline dataset FinHeadlineMix, scaling law results, and practical recommendations to provide a reusable framework for domain-specific compression decisions.

Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models

State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment. Prior ternary SSM work (Slender-Mamba) trains from scratch on 150B tokens; we show a pretrained checkpoint suffices, reducing the marginal token budget by 1,000x. Using grouped quantization-aware training (QAT) with knowledge distillation from a frozen FP16 teacher, we compress Mamba-2 1.3B to 3.61x (2,687 to 744 MB) and achieve 48.1% zero-shot accuracy (7-task average) in just 102M tokens (4 GPU-hours, single H100) -- approaching Bi-Mamba's 48.4% (within +/-0.9pp CI). This QAT-from-pretrained setting reveals zero-ratio collapse, a novel instability caused by learnable quantization scales that does not arise in from-scratch training. We further show that post-hoc correction strategies effective for Transformers fail for SSMs due to error accumulation through the recurrence. These results demonstrate that ternary SSMs do not require expensive from-scratch training: QAT from pretrained checkpoints with KD is a data-efficient alternative.

Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation

Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments. Quantization-aware distillation (QAD) helps recover accuracy lost under low bit quantization by training a quantized student to match the output distribution of a frozen higher precision teacher via a KL-divergence loss. In this work, we first provide a representation level diagnosis of QAD: output matching alone can mask internal degradation, because many intermediate activation geometries can yield similar teacher-aligned logits. Using CKA, we show that KL-only QAD can reduce layerwise representational similarity relative to the BF16 teacher, with especially severe drift in RL-post-trained models. This drift correlates with downstream bottlenecks on reasoning and coding tasks, suggesting that low bit recovery requires preserving internal geometry rather than matching outputs alone. Motivated by this finding, we propose \textbf{CKA-QAD}, a CKA-guided representational alignment method for NVFP4 QAD and low bit LLM accuracy recovery. The method adds a lightweight regularizer that preserves internal representational geometry during distillation by aligning layerwise Gram matrices through CKA. Across Nemotron 3 Nano and Qwen3-4B-Thinking-2507, CKA-QAD substantially improves representational alignment and improves downstream reasoning and coding accuracy with modest training overhead. Our findings position CKA-guided representational alignment as a practical complement to output matching for quantized LLM recovery.

Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data

Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degradation. These gains are particularly relevant for edge and on-device deployment, where memory capacity and bandwidth are primary constraints. In this work, we extend Recover-LoRA -- a lightweight, data-free accuracy recovery method originally developed for general model weight corruption -- to the setting of ultra-low-bit quantization. We propose a selective mixed-precision strategy in which only gate and up projection layers of the MLP are quantized to 2-bit (W2), while all other linear layers remain at higher precision, yielding a mixed-precision GateUp configuration. We demonstrate via roofline analysis across three model families (4B--20B) and two hardware platforms that a W4/W2-GateUp deployment (4-bit base with 2-bit gate/up) delivers 7.5--23.3\% TPS improvement over uniform W4 depending on model and context length, while confining quantization error to a predictable subset of layers. We then apply Recover-LoRA -- training low-rank adapters on the quantized layers via logit distillation with synthetic data -- to recover accuracy lost from 2-bit quantization of the gate and up layers. In a case study on Qwen3-4B, Recover-LoRA achieves 80--95\% accuracy recovery on 9 of 12 benchmarks, using only 10k synthetic training samples and no labeled data. We further demonstrate that synthetic data performs comparably to curated labeled data for distillation-based recovery, and that recovery generalizes to out-of-distribution evaluation tasks. Our results present Recover-LoRA as a practical post-quantization accuracy recovery tool for aggressive weight compression in deployment settings.

FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning Environment

Federated learning (FL) is a decentralized approach that enables collaborative model training without exposing raw data. Instead of transferring sensitive data, it allows devices to share only model weights, keeping personal data locally and secure. However, in real world settings, the data held by devices is often not evenly distributed and devices mostly differ in computing power and memory capacity. These differences make FL harder to maintain consistent performance across the system. To address these issues, we propose FedMTFI, a novel architecture that combines multi-teacher knowledge distillation (MTKD) with feature importance to improve the FL process in heterogeneous environments. In FedMTFI, clients are clustered based on similar hardware and model types. Each cluster trains a specific model on not independently and identically distributed (non-IID) data. Within a cluster, every client updates that model using only its own local private data. The server then aggregates the locally trained models in each cluster using FedAvg to form multiple prototype models. Then these prototypes serve as teacher models to train a global generalized student model using MTKD. What makes FedMTFI more unique is the integration of Shapley values (SHAP) to emphasize important features during distillation, which enhances both accuracy and interpretability. Experimental results show that FedMTFI achieves higher accuracy than traditional FL algorithms and performs more effectively under non-IID data conditions.

Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search

Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address statistical heterogeneity across client data (non-IID), system heterogeneity in device capabilities, and communication efficiency. Existing FL approaches mitigate these challenges through improved aggregation, personalization, or knowledge distillation, but they almost universally assume a fixed client architecture, limiting adaptability to heterogeneous data complexity and hardware constraints. This architectural constraint often leads to suboptimal trade-offs between accuracy and efficiency in real-world FL systems. This work introduces FedKDNAS, a distillation-driven FL framework that combines client-side neural architecture selection with distillation of server-coordinated knowledge. Each client autonomously selects a lightweight model under accuracy-resource constraints. It then trains it locally using a hybrid objective combining supervised learning and knowledge distillation and shares only predictions on a public reference set. The server then aggregates and smooths these predictions, optionally combining them with a teacher model, to produce stable distillation targets for the next round. Extensive evaluation on six datasets against six representative FL baselines (FedAvg, Ditto, FedMD, FedDF, FedDistill, Local-KD) demonstrates that FedKDNAS consistently achieves superior Pareto efficiency, improving accuracy by up to 15\% under non-IID conditions, reducing client CPU usage by approximately 28\%, and decreasing communication overhead by up to 44 times while maintaining lightweight logit-based communication.

Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency

While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment challenges on resource-constrained edge devices. Current parameter reduction techniques primarily involve training LVLMs from small language models, but these methods offer limited flexibility and remain computationally intensive. We study a complementary route: compressing existing LVLMs by applying structured pruning to the language model backbone, followed by lightweight recovery training. Specifically, we investigate two structural pruning paradigms: layerwise and widthwise pruning, and pair them with supervised finetuning and knowledge distillation on logits and hidden states. Additionally, we assess the feasibility of conducting recovery training with only a small fraction of the available data. Our results show that widthwise pruning generally maintains better performance in low-resource scenarios, where computational resources are limited or there is insufficient finetuning data. As for the recovery training, finetuning only the multimodal projector is sufficient at small compression levels. Furthermore, a combination of supervised finetuning and hidden-state distillation yields optimal recovery across various pruning levels. Notably, effective recovery can be achieved using just 5% of the original data, while retaining over 95% of the original performance. Through empirical study on three representative LVLM families ranging from 3B to 7B parameters, this study offers actionable insights for practitioners to compress LVLMs without extensive computation resources or sufficient data. The code base is available at https://github.com/YiranHuangIrene/VLMCompression.git.