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

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025
Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025
Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling EMNLP 2025
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers ICCV 2025
Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks CVPR 2025
StitchLLM: Serving LLMs, One Block at a Time ACL 2025
Faster and Better LLMs via Latency-Aware Test-Time Scaling EMNLP 2025
SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching IJCNLP 2025
Generative Prompt Internalization NAACL 2025
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models AAAI 2025
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models ICCV 2025
Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack ACL 2025
ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models ICCV 2025
Thought calibration: Efficient and confident test-time scaling EMNLP 2025
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025
Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling EMNLP 2025
Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models ACL 2025
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute CVPR 2025
Scaling Laws and Efficient Inference for Ternary Language Models ACL 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
Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025
TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models AAAI 2025
MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling ICCV 2025
500xCompressor: Generalized Prompt Compression for Large Language Models ACL 2025