LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
Paper
•
2407.14057
•
Published
•
46
nlp
-
-
OpenThoughts: Data Recipes for Reasoning Models
Paper • 2506.04178 • Published • 48 -
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
Paper • 2506.03610 • Published • 9 -
Vision Language Models are Biased
Paper • 2505.23941 • Published • 23 -
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
Paper • 2507.05687 • Published • 27 -
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
Paper • 2508.10419 • Published • 73 -
TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling
Paper • 2510.01698 • Published • 4 -
KORMo: Korean Open Reasoning Model for Everyone
Paper • 2510.09426 • Published • 62 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 401