CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks Paper • 2507.23751 • Published 26 days ago • 4
EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes Paper • 2507.11407 • Published Jul 15 • 56
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning Paper • 2508.10419 • Published 12 days ago • 70
Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge Paper • 2508.08777 • Published 14 days ago • 14
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers Paper • 2508.14704 • Published 6 days ago • 34
NVIDIA Nemotron Collection Open, Production-ready Enterprise Models. Nvidia Open Model license. • 3 items • Updated 3 days ago • 48
view article Article Training and Finetuning Embedding Models with Sentence Transformers v3 By tomaarsen • May 28, 2024 • 244
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning Paper • 2507.16784 • Published Jul 22 • 118
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models Paper • 2507.14241 • Published Jul 17 • 17
DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts Paper • 2507.18464 • Published Jul 24 • 11
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm Paper • 2507.18553 • Published Jul 24 • 39
Diversity-Enhanced Reasoning for Subjective Questions Paper • 2507.20187 • Published 30 days ago • 23
SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment Paper • 2507.20984 • Published 29 days ago • 54
A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence Paper • 2507.21046 • Published 29 days ago • 79