AINeutralarXiv – CS AI · May 116/10
🧠A comprehensive academic survey examines edge deep learning—the integration of deep learning with edge computing—and its applications in computer vision and medical diagnostics. The paper categorizes hardware platforms, reviews model optimization techniques like compression and lightweight design, and identifies future challenges for deploying neural networks on resource-constrained devices.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce Amortized-Precision Quantization (APQ) and MAQEE, a framework that optimizes Vision Transformers for low-precision deployment with early-exit mechanisms. By jointly optimizing exit thresholds and bit-widths while accounting for quantization noise across layers, the approach achieves up to 95% reduction in computational operations while maintaining accuracy across vision tasks.
AINeutralarXiv – CS AI · May 116/10
🧠TopoPrune introduces a topology-based framework for data pruning that addresses instability issues in geometric methods by leveraging intrinsic data structure rather than extrinsic geometry. The approach combines manifold approximation with persistent homology to achieve high accuracy at extreme pruning rates (90%) while maintaining robustness across architectures and noise conditions.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers demonstrate that KV-cache offloading techniques, designed to reduce memory usage in large language models, significantly degrade performance on context-intensive tasks requiring extensive information extraction. The study introduces the Text2JSON benchmark and identifies low-rank projection and unreliable landmarks as key failure points, proposing improved alternatives.
🧠 Llama
AINeutralarXiv – CS AI · May 96/10
🧠Researchers propose using evolutionary strategies to fine-tune quantized deep learning models, improving accuracy beyond standard nearest-neighbor quantization techniques. The approach selectively adjusts weight values across iterations to find better quantization states, demonstrating effectiveness on VGG, ResNet, and autoencoder architectures for image classification and detection tasks.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers propose a novel knowledge distillation method for multi-modal AI systems that transfers modality relationship information from teacher to student networks by learning the teacher's Gram Matrix. This approach goes beyond existing methods that only focus on final output, enabling deeper knowledge transfer across different data modalities.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers have identified three fundamental dynamical principles—mutual alignment, unlocking, and racing—that explain how gradient descent training reduces neural network capacity to match task requirements. This theoretical advancement clarifies the mechanisms behind the lottery ticket hypothesis and why certain initial neuron conditions lead to higher weight norms, bridging a significant gap between empirical neural network success and theoretical understanding.
AINeutralarXiv – CS AI · May 96/10
🧠Researchers demonstrate that On-Policy Self-Distillation (OPSD) functions primarily as a compression mechanism rather than a correction tool for thinking-enabled mathematical reasoning models. They propose a revised training pipeline (SFT → RLVR → OPSD) that leverages OPSD's strengths in shortening responses while preserving accuracy on correct outputs.
AINeutralarXiv – CS AI · May 76/10
🧠Researchers introduce Budgeted LoRA, a distillation framework that compresses large language models by treating model compression as a structured compute allocation problem. The method achieves up to 4.05x speedup in inference through selective dense component removal and adaptive low-rank allocation, controlled by a single compute budget parameter.
🏢 Perplexity
AINeutralarXiv – CS AI · May 46/10
🧠Researchers demonstrate that quantization—reducing AI model precision to improve efficiency—paradoxically increases energy consumption and degrades reasoning accuracy in multi-hop reasoning tasks, contradicting established neural scaling laws. The study identifies hardware dequantization overhead as a critical bottleneck and proposes a Critical Model Scale metric to predict when quantization becomes counterproductive across different model sizes and hardware configurations.
AIBullisharXiv – CS AI · May 16/10
🧠BoostLoRA introduces a gradient-boosting framework that enables parameter-efficient fine-tuning adapters to grow their effective rank iteratively, allowing ultra-low-parameter models to match or exceed full fine-tuning performance across mathematical reasoning, code generation, and protein classification tasks. The method merges adapters with zero inference overhead while maintaining minimal per-round parameter costs.
AIBearisharXiv – CS AI · May 16/10
🧠Researchers challenge the conventional wisdom that large language models contain significant redundant parameters, demonstrating that small-magnitude weights encode crucial knowledge for difficult downstream tasks. The study reveals that pruning these weights causes irreversible performance degradation that cannot be recovered through continued training, with effects monotonically correlated to task difficulty.
AINeutralarXiv – CS AI · Apr 206/10
🧠Researchers introduce Self-Distillation Fine-Tuning (SDFT), a framework that recovers performance degradation in Large Language Models caused by compression, quantization, and catastrophic forgetting. Using Centered Kernel Alignment analysis, the study demonstrates that self-distillation works by aligning the student model's high-dimensional manifold with the teacher model's optimal representation structure.
AINeutralarXiv – CS AI · Apr 146/10
🧠ReSpinQuant introduces an efficient quantization framework for large language models that combines the expressivity of layer-wise adaptation with the computational efficiency of global rotation methods. By leveraging offline activation rotation fusion and residual subspace rotation matching, the approach achieves state-of-the-art performance on aggressive quantization schemes (W4A4, W3A3) without significant inference overhead.
AIBullisharXiv – CS AI · Apr 136/10
🧠Researchers demonstrate that HiFloat4, a 4-bit floating-point format, enables efficient large language model training on Huawei's Ascend NPUs with up to 4x improvements in compute throughput and memory efficiency. The study shows that specialized stabilization techniques can maintain accuracy within 1% of full-precision baselines while preserving computational gains across dense and mixture-of-experts architectures.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers provide the first rigorous theoretical analysis of OPTQ (GPTQ), a widely-used post-training quantization algorithm for neural networks and LLMs, establishing quantitative error bounds and validating practical design choices. The study extends theoretical guarantees to both deterministic and stochastic variants of OPTQ and the Qronos algorithm, offering guidance for regularization parameter selection and quantization alphabet sizing.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers introduce CoA-LoRA, a method that dynamically adapts LoRA fine-tuning to different quantization configurations without requiring separate retraining for each setting. The approach uses a configuration-aware model and Pareto-based search to optimize low-rank adjustments across heterogeneous edge devices, achieving comparable performance to traditional methods with zero additional computational cost.
AIBullisharXiv – CS AI · Apr 76/10
🧠Researchers propose REAM (Router-weighted Expert Activation Merging), a new method for compressing large language models that groups and merges expert weights instead of pruning them. The technique preserves model performance better than existing pruning methods while reducing memory requirements for deployment.
AIBullisharXiv – CS AI · Apr 76/10
🧠Researchers developed a new method to train transformer neural networks using discrete cosine transform (DCT) coefficients, achieving the same performance while using only 52% of the parameters. The technique requires no architectural changes and simply replaces standard linear layers with spectral layers that store DCT coefficients instead of full weight matrices.
🏢 Perplexity
AIBullisharXiv – CS AI · Apr 76/10
🧠Researchers have developed DP-OPD (Differentially Private On-Policy Distillation), a new framework for training privacy-preserving language models that significantly improves performance over existing methods. The approach simplifies the training pipeline by eliminating the need for DP teacher training and offline synthetic text generation while maintaining strong privacy guarantees.
🏢 Perplexity
AIBullisharXiv – CS AI · Apr 66/10
🧠Researchers developed QAPruner, a new framework that simultaneously optimizes vision token pruning and post-training quantization for Multimodal Large Language Models (MLLMs). The method addresses the problem where traditional token pruning can discard important activation outliers needed for quantization stability, achieving 2.24% accuracy improvement over baselines while retaining only 12.5% of visual tokens.
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers introduce GPrune-LLM, a new structured pruning framework that improves compression of large language models by addressing calibration bias and cross-task generalization issues. The method partitions neurons into behavior-consistent modules and uses adaptive metrics based on distribution sensitivity, showing consistent improvements in post-compression performance.
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers developed a resource-efficient framework for compressing large language models using knowledge distillation and chain-of-thought reinforcement learning. The method successfully compressed Qwen 3B to 0.5B while retaining 70-95% of performance across English, Spanish, and coding tasks, making AI models more suitable for resource-constrained deployments.
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers developed SimCert, a probabilistic certification framework that verifies behavioral similarity between compressed neural networks and their original versions. The framework addresses critical safety challenges in deploying compressed DNNs on resource-constrained systems by providing quantitative safety guarantees with adjustable confidence levels.
AINeutralarXiv – CS AI · Mar 176/10
🧠Researchers conducted the first systematic study on post-training quantization for diffusion large language models (dLLMs), identifying activation outliers as a key challenge for compression. The study evaluated state-of-the-art quantization methods across multiple dimensions to provide insights for efficient dLLM deployment on edge devices.
