Together AI has released DeepSWE, a state-of-the-art, fully open-sourced software engineering agent that is trained entirely through reinforcement learning (RL).…
Lees meer
Shanghai Jiao Tong Researchers Propose OctoThinker for Reinforcement Learning-Scalable LLM Development
Introduction: Reinforcement Learning Progress through Chain-of-Thought Prompting LLMs have shown excellent progress in complex reasoning tasks through CoT prompting combined…
Lees meerReasonFlux-PRM: A Trajectory-Aware Reward Model Enhancing Chain-of-Thought Reasoning in LLMs
Understanding the Role of Chain-of-Thought in LLMs Large language models are increasingly being used to solve complex tasks such as…
Lees meerBaidu Researchers Propose AI Search Paradigm: A Multi-Agent Framework for Smarter Information Retrieval
The Need for Cognitive and Adaptive Search Engines Modern search systems are evolving rapidly as the demand for context-aware, adaptive…
Lees meerBaidu Open Sources ERNIE 4.5: LLM Series Scaling from 0.3B to 424B Parameters
Baidu has officially open-sourced its latest ERNIE 4.5 series, a powerful family of foundation models designed for enhanced language understanding,…
Lees meerOMEGA: A Structured Math Benchmark to Probe the Reasoning Limits of LLMs
Introduction to Generalization in Mathematical Reasoning Large-scale language models with long CoT reasoning, such as DeepSeek-R1, have shown good results…
Lees meerBuilding Advanced Multi-Agent AI Workflows by Leveraging AutoGen and Semantic Kernel
In this tutorial, we walk you through the seamless integration of AutoGen and Semantic Kernel with Google’s Gemini Flash model.…
Lees meerTabArena: Benchmarking Tabular Machine Learning with Reproducibility and Ensembling at Scale
Understanding the Importance of Benchmarking in Tabular ML Machine learning on tabular data focuses on building models that learn patterns…
Lees meerLongWriter-Zero: A Reinforcement Learning Framework for Ultra-Long Text Generation Without Synthetic Data
Introduction to Ultra-Long Text Generation Challenges Generating ultra-long texts that span thousands of words is becoming increasingly important for real-world…
Lees meerMDM-Prime: A generalized Masked Diffusion Models (MDMs) Framework that Enables Partially Unmasked Tokens during Sampling
Introduction to MDMs and Their Inefficiencies Masked Diffusion Models (MDMs) are powerful tools for generating discrete data, such as text…
Lees meer