Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2602. 08585v2 Announce Type: replace-cross Abstract: Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference.
arXiv:2606. 00312v1 Announce Type: cross Abstract: Over the past half-dozen years, stochastic rounding (SR) has regained significant attention as a quantization scheme for low-precision floating-point arithmetic, with applications spanning numerical analysis and modern machine learning systems.
arXiv:2606. 01227v1 Announce Type: new Abstract: Many networks not only support but also rely on transient non-normal amplification, an orders-of-magnitude increase in the activity of an otherwise stable system.
arXiv:2605. 26089v2 Announce Type: replace-cross Abstract: We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens.
arXiv:2606. 00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it after task one and foreclose cross-task refinement.
arXiv:2602. 10056v2 Announce Type: replace Abstract: We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks.
arXiv:2411. 09816v5 Announce Type: replace Abstract: Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices.
arXiv:2605. 27835v2 Announce Type: replace Abstract: We introduce CAREF, a parameter-efficient fine-tuning framework that jointly optimizes predictive accuracy and explanation faithfulness via calibration-aware regularization.
arXiv:2601. 00672v2 Announce Type: replace-cross Abstract: In this paper, we study the finite element operator network (FEONet), an operator-learning method for parametric problems, originally introduced in J.
arXiv:2606. 01101v1 Announce Type: cross Abstract: The quadratic complexity of self-attention remains a bottleneck for Large Language Models (LLMs) processing ultra-long contexts.
arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
arXiv:2605. 26632v2 Announce Type: replace Abstract: Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs.
arXiv:2606. 02455v1 Announce Type: new Abstract: Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems.
arXiv:2509. 25837v3 Announce Type: replace-cross Abstract: Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference.
arXiv:2605. 17839v3 Announce Type: replace-cross Abstract: Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses.
arXiv:2507. 09029v5 Announce Type: replace-cross Abstract: Pre-training large neural networks at scale imposes heavy memory demands on accelerators and often requires costly communication.
arXiv:2512. 00956v3 Announce Type: replace Abstract: Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors.
Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency.
Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count.
Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training.