Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.
Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking.
arXiv:2607. 19349v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as always-on online services, making efficient LLM serving a critical systems challenge.
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv:2607. 19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined.
arXiv:2607. 19426v1 Announce Type: cross Abstract: Single-cell datasets are increasingly costly to store, audit, and reuse for model training.
arXiv:2607. 19510v1 Announce Type: new Abstract: Modern LLM deployments use a number of implementation choices and inference optimizations (e.
arXiv:2607. 19957v1 Announce Type: cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).
arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.
arXiv:2607. 19528v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have triggered the development of end-to-end MLLMs for autonomous driving.
arXiv:2607. 19962v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps.
arXiv:2607. 19431v1 Announce Type: cross Abstract: Bit-serial accelerators exploit bit-level sparsity to reduce DNN inference cost, but existing designs exploit sparsity on only one operand, bounding the speedup.
arXiv:2607. 19395v1 Announce Type: cross Abstract: Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets.
arXiv:2607. 19421v1 Announce Type: cross Abstract: Silicon-photonic (SiPh) accelerators have emerged as a promising platform for Vision Transformer (ViT) inference by performing matrix multiplications on microring-resonator (MRR) banks with high throughput and energy efficiency.
arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.
arXiv:2607. 20153v1 Announce Type: new Abstract: We study Gaussian averaging as a smooth surrogate for quantized neural models.
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.
arXiv:2607. 19450v1 Announce Type: cross Abstract: Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in large language models (LLMs).
arXiv:2602. 17330v5 Announce Type: replace-cross Abstract: Comparative analysis of adaptive immune repertoires at population scale is hampered by two practical bottlenecks: the near-quadratic cost of pairwise affinity evaluations and dataset imbalances that obscure clinically important minority clonotypes.
arXiv:2605. 22069v3 Announce Type: replace-cross Abstract: Novel view synthesis from sparse-view inputs poses a significant challenge in 3D computer vision, particularly for achieving high-quality scene reconstructions with limited viewpoints.