How LongCat‑Flash‑Thinking‑2601 Achieves Real‑World Generalization for Agents

LongCat‑Flash‑Thinking‑2601, a 560‑billion‑parameter MoE model, combines environment expansion, multi‑environment RL, systematic noise training, a heavy‑thinking reasoning mode, and Zigzag sparse attention to deliver strong benchmark performance and robust real‑world agent capabilities.

Environment ExpansionLarge Language ModelOpen Source

0 likes · 14 min read

How LongCat‑Flash‑Thinking‑2601 Achieves Real‑World Generalization for Agents

Network Intelligence Research Center (NIRC)

Jan 4, 2026 · Artificial Intelligence

How UniCodebook’s Unified 2D‑3D Discrete Priors Boost Noise‑Robust, Calibration‑Free 3D Human Pose Estimation

UniCodebook introduces a unified 2D‑3D discrete prior that combines continuous and discrete representations, enabling calibration‑free multiview 3D human pose estimation with superior noise robustness and higher accuracy, as demonstrated by state‑of‑the‑art results on Human3.6M and MPI‑INF‑3DHP.

3D pose estimationNeurIPS 2025Transformer

0 likes · 8 min read

How UniCodebook’s Unified 2D‑3D Discrete Priors Boost Noise‑Robust, Calibration‑Free 3D Human Pose Estimation

NewBeeNLP

Mar 13, 2024 · Artificial Intelligence

Can LLMs Clean Noisy Graphs? Introducing GraphEdit for Robust Structure Learning

GraphEdit leverages large language models and a lightweight edge predictor to remove noisy connections and uncover hidden node dependencies, achieving state‑of‑the‑art performance on benchmark graph datasets such as Cora, Citeseer, and PubMed, while demonstrating strong robustness to noise and limited supervision.

Edge PredictionGraph Structure Learningbenchmark datasets

0 likes · 17 min read

Can LLMs Clean Noisy Graphs? Introducing GraphEdit for Robust Structure Learning