Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
Jian Yang, Xianglong Liu, Weifeng Lv +68 authors
A comprehensive guide to code LLMs, covering their lifecycle from data curation to deployment, including techniques, trade-offs, and research-practice gaps.
50 篇论文 · 按点赞排序
DeepSeek-AI, Aixin Liu, Aoxue Mei +261 authors
DeepSeek-V3.2 introduces DeepSeek Sparse Attention and a scalable reinforcement learning framework, achieving superior reasoning and performance compared to GPT-5 and Gemini-3.0-Pro in complex reasoning tasks.
Z-Image Team, Huanqia Cai, Sihan Cao +18 authors
Z-Image, a 6B-parameter Scalable Single-Stream Diffusion Transformer (S3-DiT) model, achieves high-performance image generation with reduced computational cost, offering sub-second inference and compatibility with consumer hardware.
Hao Liang, Xiaochen Ma, Zhou Liu +32 authors
DataFlow is an LLM-driven data preparation framework that enhances data quality and reproducibility for various tasks, improving LLM performance with automatically generated pipelines.
Zuhao Yang, Sudong Wang, Kaichen Zhang +7 authors
LongVT, an end-to-end framework, enhances long video reasoning by interleaving global and local analysis using multimodal tools, outperforming existing methods on challenging benchmarks.
Yubo Huang, Hailong Guo, Fangtai Wu +8 authors
Live Avatar uses a 14-billion-parameter diffusion model with Timestep-forcing Pipeline Parallelism and Rolling Sink Frame Mechanism to achieve real-time, high-fidelity avatar generation.
Kling Team, Jialu Chen, Yuanzheng Ci +65 authors
Kling-Omni is an end-to-end generative framework that unifies video generation, editing, and reasoning from multimodal inputs to produce high-fidelity video content.
Shuai Bai, Yuxuan Cai, Ruizhe Chen +61 authors
Qwen3-VL, a vision-language model, excels in text and multimodal understanding through advanced architectures and larger contexts, achieving superior performance across benchmarks.
Yuyang Hu, Shichun Liu, Yanwei Yue +44 authors
This survey provides an updated overview of agent memory research, distinguishing its forms, functions, and dynamics, and highlights emerging research directions.
Fangyu Lei, Jinxiang Meng, Yiming Huang +14 authors
DAComp is a benchmark of 210 tasks that evaluates the capabilities of agents in real-world data engineering and data analysis workflows, revealing significant deficiencies in both areas.
Haolong Yan, Jia Wang, Xin Huang +94 authors
A self-evolving training pipeline with the Calibrated Step Reward System and GUI-MCP protocol improve GUI automation efficiency, accuracy, and privacy in real-world scenarios.
Ruihang Chu, Yefei He, Zhekai Chen +10 authors
Wan-Move enhances motion control in video generative models by integrating motion-aware features into latent space, enabling high-quality and scalable video synthesis.
Hongjin Su, Shizhe Diao, Ximing Lu +13 authors
A small orchestrator using ToolOrchestra method coordinates various intelligent tools with reinforcement learning, achieving higher accuracy and efficiency in solving complex tasks like Humanity's Last Exam compared to larger models.
Taewoong Kang, Kinam Kim, Dohyeon Kim +3 authors
EgoX framework generates egocentric videos from exocentric inputs using video diffusion models with LoRA adaptation, unified conditioning, and geometry-guided self-attention for coherence and visual fidelity.
Wanghan Xu, Yuhao Zhou, Yifan Zhou +104 authors
A framework for Scientific General Intelligence (SGI) is presented, evaluated using SGI-Bench, and improved with Test-Time Reinforcement Learning, highlighting gaps in existing models' scientific capabilities.
Zefan Cai, Haoyi Qiu, Tianyi Ma +9 authors
MMGR evaluates video and image models across reasoning abilities in multiple domains, revealing performance gaps and highlighting limitations in perceptual data and causal correctness.
Dmitrii Stoianov, Danil Taranets, Olga Tsymboi +12 authors
T-pro 2.0 is an open-weight Russian LLM for hybrid reasoning and efficient inference, using a Cyrillic-dense tokenizer and EAGLE speculative-decoding pipeline.
Yuqing Li, Jiangnan Li, Zheng Lin +5 authors
MiA-RAG enhances long-context reasoning in LLM-based RAG systems by incorporating hierarchical summarization to create global semantic representations that guide both retrieval and generation processes.
Weizhou Shen, Ziyi Yang, Chenliang Li +11 authors
QwenLong-L1.5 enhances long-context reasoning through data synthesis, stabilized reinforcement learning, and memory-augmented architecture, achieving superior performance on benchmarks and general domains.
Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi +31 authors
This paper presents a framework for agent and tool adaptation in agentic AI systems, clarifying design strategies and identifying open challenges for improving AI capabilities.
Chujie Zheng, Kai Dang, Bowen Yu +7 authors
The paper provides a theoretical foundation for optimizing sequence-level rewards in reinforcement learning using token-level objectives, highlighting the importance of techniques like importance sampling correction, clipping, and Routing Replay for stabilizing training, especially with large language models.
Jingfeng Yao, Yuda Song, Yucong Zhou +1 authors
A unified visual tokenizer pre-training framework (VTP) improves generative performance by optimizing image-text contrastive, self-supervised, and reconstruction losses, leading to better scaling properties and higher zero-shot accuracy and faster convergence.
Ang Lv, Jin Ma, Yiyuan Ma +1 authors
An expert-router coupling (ERC) loss aligns router decisions with expert capabilities in Mixture-of-Experts (MoE) models by enforcing constraints on internal activations, improving performance and computational efficiency.
Hoiyeong Jin, Hyojin Jang, Jeongho Kim +6 authors
InsertAnywhere framework enhances video object insertion by generating geometrically consistent and visually coherent scenarios through 4D aware mask generation and diffusion-based synthesis.
Jintao Zhang, Kaiwen Zheng, Kai Jiang +5 authors
TurboDiffusion accelerates video generation by 100-200x using attention acceleration, step distillation, and quantization, while maintaining video quality.
Zhihong Shao, Yuxiang Luo, Chengda Lu +6 authors
A self-verifying large language model for theorem proving improves mathematical reasoning by incentivizing rigorous step-by-step derivations and achieves high scores in international competitions.
Jianhong Bai, Xiaoshi Wu, Xintao Wang +9 authors
SemanticGen addresses slow convergence and computational costs in video generation by using a two-stage diffusion model approach that first generates semantic features and then VAE latents, leading to faster convergence and high-quality results.
Juanxi Tian, Siyuan Li, Conghui He +2 authors
A benchmark for chained text-to-multi-image generation assesses models' ability to model dynamic causal processes and world knowledge, revealing that unified multimodal models outperform specialized ones but still struggle with spatiotemporal consistency.
Jia-Nan Li, Jian Guan, Wei Wu +1 authors
ReFusion, a novel masked diffusion model, improves performance and efficiency by using slot-based parallel decoding, achieving superior results compared to autoregressive models and traditional masked diffusion models.
Sihan Xu, Ziqiao Ma, Wenhao Chai +5 authors
Generative pretraining using next embedding prediction outperforms traditional self-supervised methods in visual learning tasks, achieving high accuracy on ImageNet and effective transfer to semantic segmentation.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号