Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 00651v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to relevant experts, yet introduce a critical vulnerability: Safety Sparsity, where safety capabilities concentrate in few experts, making them susceptible to adversarial bypassing.
arXiv:2606. 00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with a small number of shared transformer blocks.
arXiv:2606. 01352v1 Announce Type: new Abstract: Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems.
arXiv:2606. 02355v1 Announce Type: new Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency.
arXiv:2603. 08026v2 Announce Type: replace-cross Abstract: Masked diffusion language models enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation.
arXiv:2602. 10623v2 Announce Type: replace-cross Abstract: Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet they are often vulnerable to reward hacking due to noisy annotations and systematic biases such as response length or style.
arXiv:2606. 00079v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.
arXiv:2606. 00129v1 Announce Type: cross Abstract: Large language models (LLMs) have emerged as powerful representation learners whose internal features increasingly align with human cognition.
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:2606. 00120v1 Announce Type: cross Abstract: This paper proposes SpikeWFM, a novel hybrid architecture that integrates spiking neural networks (SNNs) with conventional artificial neural network (ANN)-based transformers for wireless foundation models (WFMs).
arXiv:2606. 00144v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel.
arXiv:2606. 00282v1 Announce Type: cross Abstract: Large-scale recommendation systems operate across diverse domains, yet they face the challenges of data sparsity and noisy implicit feedback.
arXiv:2606. 00561v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to deploy on constrained hardware, and opaque to operators.
arXiv:2606. 00703v1 Announce Type: cross Abstract: Low-precision pretraining (FP8, MXFP4, NVFP4) is now standard for frontier language models, yet the literature is almost entirely achievability -- algorithms and empirical scaling laws -- with no matching characterization of what is information-theoretically possible.
arXiv:2601. 19919v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is one of the most effective paradigms for compressing large-scale foundation models into deployable architectures.
arXiv:2606. 01023v1 Announce Type: cross Abstract: Visual inspection remains the dominant quality-control practice in woven and tufted carpet production, yet it is slow, subjective, and inconsistent at the line speeds and widths of modern looms.
arXiv:2606. 01065v1 Announce Type: cross Abstract: Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only eviction are correct by construction.
arXiv:2606. 01117v1 Announce Type: cross Abstract: Extreme multi-label classification (XMC) involves learning models over large output spaces with millions of labels, making the output layer a memory-compute bottleneck.
arXiv:2606. 01607v1 Announce Type: cross Abstract: Federated learning (FL) is a decentralized approach that enables collaborative model training without exposing raw data.
arXiv:2606. 01689v1 Announce Type: cross Abstract: The detection and segmentation of infrared small targets have important application significance in the fields of surveillance and security, maritime rescue and so on.