A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Yue Wang, Qiuzhi Liu, Jiahao Xu, et al.
Identifies 'underthinking' in o1-like LLMs, where frequent thought switching harms reasoning, and proposes a decoding penalty (TIP) to improve accuracy on math problems.
Unknown
The paper explores whether protein language models (pLMs) can serve as a universal foundation for decoding protein sequences, potentially extending beyond traditional applications.
Unknown
This survey provides a comprehensive overview of speculative decoding and related techniques for accelerating autoregressive generation, including draft models and iterative refinement methods.
Unknown
This paper critically evaluates speculative decoding's real-world effectiveness, revealing that prior benchmarks overstate its speedups due to idealized conditions.
Unknown
This paper introduces a decoding-time debiasing method using process reward models to reduce social biases in LLM generation, from fill-in tasks to open-ended generation.
Unknown
This survey provides a comprehensive overview of techniques for making large language models more efficient, covering model compression, efficient decoding, and system-level optimizations.
Ruoyu Qin, Weiran He, Weixiao Huang, et al.
Seer is a context-learning RL system that reduces long-tail latency by 72-94% and improves rollout throughput by 2.04x through divided rollout, context-aware scheduling, and adaptive grouped speculative decoding.
Xiaoqiang Lin, Aritra Ghosh, K. H. Low, et al.
REFRAG exploits block-diagonal attention sparsity in RAG to skip unnecessary decoding computations, achieving 30.85x TTFT speedup and 16x context extension without accuracy loss.
Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, et al.
Proposes Lookback Lens, a simple hallucination detector using attention weight ratios, effective across tasks and models, and reduces hallucinations via classifier-guided decoding.
Siqi Kou, Lanxiang Hu, Zhe He, et al.
Consistency LLMs accelerate LLM inference by refining the model to consistently predict the fixed point from any state, achieving 2.4-3.4x speedup over autoregressive decoding.
Xun Liang, Hanyu Wang, Yezhaohui Wang, et al.
A systematic review of controllable text generation for LLMs, defining core concepts, categorizing tasks, and analyzing methods including model retraining, fine-tuning, and decoding-time intervention.
Unknown
Hyperfitting fine-tunes LLMs to near-zero loss on small data, sharpening predictions to improve greedy decoding for long text generation.