Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 27701v1 Announce Type: cross Abstract: While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood.
arXiv:2602. 10238v2 Announce Type: replace-cross Abstract: The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache.
arXiv:2505. 22783v2 Announce Type: replace-cross Abstract: Reliable altitude estimation with frequency-modulated continuous wave (FMCW) radar altimeters is increasingly a challenge due to in-band interference from modern communication systems.
arXiv:2605. 06675v2 Announce Type: replace Abstract: Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving.
arXiv:2606. 28252v1 Announce Type: cross Abstract: Early detection of oral cancer markedly improves clinical outcomes, yet specialized diagnostic tools remain scarce in low-resource settings.
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
arXiv:2606. 27802v1 Announce Type: new Abstract: Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while sparse coding imposes parsimonious latent representations through explicit sparsity constraints.
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.
arXiv:2606. 28027v1 Announce Type: cross Abstract: Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost.
arXiv:2606. 27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored.
arXiv:2606. 27381v1 Announce Type: cross Abstract: Queue overflow, a severe consequence of urban traffic congestion, occurs when vehicle queues exceed intersection capacity, obstructing upstream traffic and triggering cascading gridlocks.
arXiv:2601. 16956v1 Announce Type: cross Abstract: The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now scaling to trillions of parameters, has necessitated training across thousands of GPUs using complex hybrid parallelism strategies (e.
arXiv:2606. 28070v1 Announce Type: new Abstract: JD.
arXiv:2606. 21257v2 Announce Type: replace-cross Abstract: OpenPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs has not been systematically characterized.
arXiv:2601. 22709v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss.
arXiv:2604. 00757v2 Announce Type: replace-cross Abstract: Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens.
arXiv:2606. 27884v1 Announce Type: cross Abstract: Mixed-precision computation has been introduced in deep neural networks (DNNs) as an effective approach to reduce latency, energy consumption, and memory footprint.
arXiv:2606. 27732v1 Announce Type: cross Abstract: Discrete diffusion language models (dLLMs) recover masked tokens in parallel, offering significant speedups over autoregressive (AR) generation.
arXiv:2606. 27797v1 Announce Type: cross Abstract: Knowledge Distillation (KD) enables training smaller student models under the guidance of larger teacher models, and the widely adopted TRL library implements it.