Author: insights

1. Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance 🔑 Keywords: Motion Control, Video Generative Models, Dense Point Trajectories, Latent Space, Motion […]

1. Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning 🔑 Keywords: NPR, Large Language Models, self-distilled training, Parallel-Aware Policy Optimization, […]

1. TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows 🔑 Keywords: TwinFlow, inference efficiency, generative models, text-to-image tasks 💡 Category: […]

1. DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle 🔑 Keywords: DAComp, Data Engineering, Data Analysis, Autonomous Data Agents, SQL […]

1. Qwen3-VL Technical Report 🔑 Keywords: Qwen3-VL, vision-language model, interleaved contexts, enhanced interleaved-MRoPE, DeepStack integration 💡 Category: Multi-Modal Learning 🌟 Research Objective: […]

1. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models 🔑 Keywords: DeepSeek-V3.2, DeepSeek Sparse Attention, scalable reinforcement learning, reasoning proficiency 💡 […]

1. From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence 🔑 Keywords: AI Native, Large Language Models, […]

1. Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer 🔑 Keywords: Z-Image, Scalable Single-Stream Diffusion Transformer, photorealistic image generation, […]

1. Video Generation Models Are Good Latent Reward Models 🔑 Keywords: PRFL, latent space, video generation, human preferences, gradient backpropagation 💡 Category: […]

1. Multimodal Evaluation of Russian-language Architectures 🔑 Keywords: Mera Multi, Multimodal Evaluation Framework, Russian Language, AI-Generated Summary, Benchmark Leakage 💡 Category: Multi-Modal […]

1. GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms 🔑 Keywords: GigaEvo, LLM-guided evolutionary computation, AlphaEvolve, open-source framework, […]

1. General Agentic Memory Via Deep Research 🔑 Keywords: JIT compilation, Reinforcement Learning, light-weight memorizer, AI-generated summary, large language models 💡 Category: […]