conftrace_

inference efficiency

248 papers

Explore in graph

Co-occurring keywords

model compression (3302) large language model (13587) knowledge distillation (3725) inference optimization (219) kv cache (74) efficient computing (781) language model (4599) inference acceleration (244) attention mechanism (4001) neural network (6616)

Papers

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint EMNLP 2025
Thought calibration: Efficient and confident test-time scaling EMNLP 2025
zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025
Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025
Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025
500xCompressor: Generalized Prompt Compression for Large Language Models ACL 2025
Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025
ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models ICCV 2025
Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection IJCAI 2025
Parallel Continuous Chain-of-Thought with Jacobi Iteration EMNLP 2025
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute CVPR 2025
RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations IJCAI 2025
SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching IJCNLP 2025
Scaling Laws and Efficient Inference for Ternary Language Models ACL 2025
PrAd: Prompt Adaptive Tuning for Decoder-only Language Models EMNLP 2025
From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025
VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models COLING 2025
Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models EMNLP 2025
Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models NAACL 2025
TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models AAAI 2025
MoDification: Mixture of Depths Made Easy NAACL 2025
Generative Prompt Internalization NAACL 2025
TableKV: KV Cache Compression for In-Context Table Processing ACL 2025