language model inference

iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference AAAI 2026 Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs EACL 2026 Steering Pretrained Drafters During Speculative Decoding AAAI 2026 CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation AAAI 2025 Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025 Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree AAAI 2025 Improving Consistency in LLM Inference using Probabilistic Tokenization NAACL 2025 Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025 Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits ICLR 2025 Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025 Surprising Effectiveness of pretraining Ternary Language Model at Scale ICLR 2025 An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference EMNLP 2024 BASS: Batched Attention-optimized Speculative Sampling ACL 2024 Efficient LLM Scheduling by Learning to Rank NeurIPS 2024 Loki: Low-rank Keys for Efficient Sparse Attention NeurIPS 2024 Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024 Speculative Contrastive Decoding ACL 2024 The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics NAACL 2024 An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models NAACL 2021 SyntaxGym: An Online Platform for Targeted Evaluation of Language Models ACL 2020