Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
Paper • 2504.06261 • Published • 110
Cool-Research-Mad
-
-
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 183 -
AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference
Paper • 2502.04077 • Published • 2 -
An Embarrassingly Simple Approach for Wafer Feature Extraction and Defect Pattern Recognition
Paper • 2303.11632 • Published • 1 -
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 94 -
Large Language Models are Pattern Matchers: Editing Semi-Structured and Structured Documents with ChatGPT
Paper • 2409.07732 • Published -
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation
Paper • 2112.05364 • Published • 1 -
ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
Paper • 2503.12918 • Published -
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Paper • 2601.08763 • Published • 150 -
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Paper • 2505.10554 • Published • 119 -
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
Paper • 2607.07976 • Published -
Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
Paper • 2606.12689 • Published • 2 -
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 331 -
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
Paper • 2608.02703 • Published • 6