Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 21257v4 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:2504. 17584v2 Announce Type: replace-cross Abstract: Attention-FC Disaggregated (AFD) LLM inference systems offload memory-bound Attention operations to memory-rich accelerators (e.
arXiv:2608. 07193v1 Announce Type: new Abstract: Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet existing methods largely rely on fixed, handcrafted heuristics and costly expert trial and error.
arXiv:2608. 07106v1 Announce Type: new Abstract: Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the resource-intensive distance sorting algorithms often used before neural network inference.
arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
arXiv:2608. 07226v1 Announce Type: cross Abstract: Compact AI systems make local language-model experimentation increasingly accessible, yet practical evidence for multi-node training on desktop-class accelerators remains limited.
arXiv:2608. 07066v1 Announce Type: new Abstract: Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization.
arXiv:2608. 06912v1 Announce Type: new Abstract: The top-$k$ operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning.
arXiv:2608. 07192v1 Announce Type: new Abstract: Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems.
arXiv:2608. 07001v1 Announce Type: new Abstract: As large language models (LLMs) process increasingly long contexts, KV cache storage and repeated access have become a major bottleneck.
arXiv:2608. 07151v1 Announce Type: cross Abstract: Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness.
arXiv:2608. 06447v1 Announce Type: cross Abstract: In modern distributed network environments, particularly in Internet of Things infrastructures and 5G networks, stringent privacy preservation and scalability requirements have created significant challenges for intrusion detection systems.
arXiv:2606. 05597v3 Announce Type: replace Abstract: Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more steps and tokens than necessary.
arXiv:2608. 07405v1 Announce Type: cross Abstract: Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation.
arXiv:2605. 28803v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single policy, yet their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive.
arXiv:2608. 06650v1 Announce Type: cross Abstract: Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-robot control.
arXiv:2608. 06723v1 Announce Type: cross Abstract: The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design.
arXiv:2608. 06763v1 Announce Type: new Abstract: Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU execution.
arXiv:2608. 01035v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.
arXiv:2511. 01592v2 Announce Type: replace Abstract: Energy estimation is critical to impact identification on aerospace composites, where low-velocity impacts can induce internal damage that is undetectable at the surface.