conftrace_

memory optimization

114 papers

Explore in graph

Co-occurring keywords

model compression (3302) large language model (13587) memory efficiency (261) kv cache (74) inference optimization (219) inference efficiency (248) efficient inference (233) edge computing (210) deep neural network (1803) efficient computing (781)

Papers

Thesis Proposal: Efficient KV Cache Reuse for Multi-Document Retrieval-Augmented Generation EACL 2026
EHL*: Memory-Budgeted Indexing for Ultrafast Optimal Euclidean Pathfinding AAAI 2026
Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction AAAI 2026
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference EACL 2026
CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints AAAI 2026
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026
MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks CVPR 2025
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation ACL 2025
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression EMNLP 2025
500xCompressor: Generalized Prompt Compression for Large Language Models ACL 2025
QSpec: Speculative Decoding with Complementary Quantization Schemes EMNLP 2025
Efficient Training of Neural Fractional-Order Differential Equation via Adjoint Backpropagation AAAI 2025
Cost-Effective On-Device Sequential Recommendation with Spiking Neural Networks IJCAI 2025
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization EMNLP 2025
Q-MiniSAM2: A Quantization-based Benchmark for Resource-Efficient Video Segmentation IJCAI 2025
Attractor-based Closed List Search: Sparsifying the Closed List for Efficient Memory-Constrained Planning IJCAI 2025
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding EMNLP 2025
LightThinker: Thinking Step-by-Step Compression EMNLP 2025
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025
Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis ACL 2025
Practical Offloading for Fine-Tuning LLM on Commodity GPU via Learned Sparse Projectors AAAI 2025
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead AAAI 2025
Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025
AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints AAAI 2025
Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models NAACL 2025