REVIEW 29 cited by
Efficient Large Language Models: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Efficient Large Language Models: A Survey
read the original abstract
Large Language Models (LLMs) have demonstrated remarkable capabilities in important tasks such as natural language understanding and language generation, and thus have the potential to make a substantial impact on our society. Such capabilities, however, come with the considerable resources they demand, highlighting the strong need to develop effective techniques for addressing their efficiency challenges. In this survey, we provide a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from model-centric, data-centric, and framework-centric perspective, respectively. We have also created a GitHub repository where we organize the papers featured in this survey at https://github.com/AIoT-MLSys-Lab/Efficient-LLMs-Survey. We will actively maintain the repository and incorporate new research as it emerges. We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of efficient LLMs research and inspire them to contribute to this important and exciting field.
Forward citations
Cited by 29 Pith papers
-
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
OTora provides the first unified framework for reasoning-level denial-of-service attacks on LLM agents, achieving up to 10x more reasoning tokens and order-of-magnitude latency increases while preserving task accuracy...
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
GEMQ applies global LP-based expert importance estimation and router fine-tuning within progressive quantization to cut memory and speed inference in MoE LLMs with little accuracy loss.
-
EmbGen: Teaching with Reassembled Corpora
EmbGen creates synthetic QA data by entity decomposition, embedding-based reassembly into clusters, and multi-level sampling with cluster-specific prompts, yielding up to 88.9% higher Binary Accuracy than baselines on...
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance...
-
When is Warmstarting Effective for Scaling Language Models?
A 2x growth factor in model warmstarting yields reliable training speedups for language models under 20 tokens/parameter budgets, with an empirical upper bound on effective growth factors.
-
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
OTora is a two-stage framework that generates insertion-aware adversarial triggers and ICL-guided genetic payloads to induce reasoning-level denial-of-service in tool-augmented LLM agents across multiple backbones whi...
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing l...
-
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
OSAQ uses the low-rank structure of the Hessian to construct a closed-form additive weight transformation that suppresses outliers without changing task loss, enabling better low-bit LLM quantization.
-
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
OSAQ suppresses weight outliers in LLMs via a closed-form additive transformation from the Hessian's stable null space, improving 2-bit quantization perplexity by over 40% versus vanilla GPTQ with no inference overhead.
-
Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces
JACTUS unifies low-rank compression and task adaptation via a task-aware union of subspaces and global rank allocation by marginal gain, outperforming 100% PEFT methods like DoRA on ViT-Base (89.2% avg) and Llama2-7B ...
-
CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
CLIP-RD adds VRD for cross-modality distillation consistency and XRD for bidirectional cross-modal symmetry to align student embedding geometry more closely with the teacher, yielding a 0.8 percentage point gain over ...
-
DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving
DriveMoE applies scene-specialized Vision MoE and skill-specialized Action MoE to a VLA baseline to achieve SOTA closed-loop performance on Bench2Drive.
-
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
BlockPilot is an instance-adaptive policy that predicts optimal block size from the prefilling representation for diffusion speculative decoding, reporting 5.92 acceptance length and 4.20x speedup on Qwen3-4B.
-
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Iterative self-improving codebooks enhance safety in autoregressive multimodal models by self-identifying unsafe generations and updating the codebook to eliminate harmful visual token mappings without external feedback.
-
Recency/Frequency Adaptive KV Caching for Large Language Model Serving
Presents a recency/frequency adaptive KV caching approach that achieves up to 10.8% higher hit rate and 12.6% lower TTFT compared to vLLM on synthetic workloads.
-
Dynamic Linear Attention
DLA introduces adaptive state merging based on token information variation plus fixed-size memory management for linear attention, reporting better results than fixed-policy baselines on 16 datasets across three categories.
-
Latent Action Reparameterization for Efficient Agent Inference
LAR learns a compact latent action space from trajectories that shortens the effective decision horizon for LLM agents, reducing token count and inference time while preserving task success.
-
Triplet Feature Fusion for Equipment Anomaly Prediction : An Open-Source Methodology Using Small Foundation Models
Triplet fusion of 28 statistical features, 64-dim time-series embeddings from a 133K-param model, and 1024-dim text embeddings into LightGBM yields 0.992 precision and 0.998 AUC on 67k HVAC samples while cutting false...
-
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
Layer pruning preserves classification performance in LLMs but fundamentally limits recovery of generative reasoning capabilities even after extensive self-supervised finetuning.
-
Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment
The paper calls for life cycle assessment to capture embodied hardware costs and full pipeline operational costs in AI development and deployment.
-
Unified Deployment-Aware Evaluation of Open Reasoning Language Models
A controlled multi-model evaluation on shared data subsets shows that deployment metrics and prompting choices create important tradeoffs and alter model rankings beyond accuracy alone.
-
Unified Deployment-Aware Evaluation of Open Reasoning Language Models
Gemma-4-E4B with few-shot chain-of-thought reaches the highest weighted accuracy of 0.675 at 14.9 GB VRAM, while the larger Gemma-4-26B-A4B MoE model scores 0.663 but uses 48.1 GB.
-
From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap
A semi-structured thematic synthesis identifies core challenges in FM selection, alignment, prompting, orchestration, testing, deployment, and cross-cutting concerns like observability for production-ready FMware.
-
NeuronMLP: Efficient LLM Inference via Singular Value Decomposition Compression and Tiling on AWS Trainium
NeuronMLP applies SVD-based compression and Trainium-specific tiling and caching to MLP layers, delivering 1.35x kernel speedup and 1.21x end-to-end inference speedup at 0.05 compression ratio versus AWS NKI baseline.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
-
Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda
This research agenda argues that cloud-native architectures, microservices, autoscaling, and emerging trends like serverless inference and federated learning are required to make large language models efficient and scalable.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.