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。
897 篇论文 · 按点赞排序
Yuanyang Yin, Gongxuan Wang, Yifan Zhan +3 authors
Evoke is an interactive world model that uses external persistent memory and a redesigned long-horizon teacher to enable responsive, open-ended video generation with bounded context and low latency.
Guoxuan Chen, Chufeng Xiao, Haoran Yang +30 authors
Boogu-Image-0.1 is an open-source unified multimodal model family that achieves strong text-to-image generation, editing, and bilingual rendering with low training cost by improving multimodal understanding, data quality, and agentic inference scaling.
Ruofeng Yang, Yongcan Li, Shuai Li
ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers.
Aditi, Niket Agarwal, Arslan Ali +288 authors
Cosmos 3 is an omnimodal world model that processes and generates multiple data types through a unified mixture-of-transformers architecture, achieving state-of-the-art performance in various understanding and generation tasks.
Kangsheng Duan, Ziyang Xu, Wenyu Liu +3 authors
A lightweight image inpainting framework achieves high-fidelity results with significantly reduced parameters and inference time through novel local-global interaction blocks and adaptive distillation strategies.
Peng Xia, Jianwen Chen, Xinyu Yang +10 authors
A continual meta-learning framework for large language model agents that jointly evolves policies and reusable behavioral skills while minimizing downtime through opportunistic updates and skill-driven adaptation.
Songlin Yang, Xiaotong Zhao, Jiacheng Zhang +5 authors
Adaptive reward routing improves joint audio-video diffusion training by dynamically localizing updates and balancing competing rewards.
Hengyi Xie, Chenfei Yao, Xianjin Wu +7 authors
TurboVLA replaces the LLM-centric vision-language-action pipeline with direct vision-language interaction and a compact decoder to cut inference costs while maintaining high robotic manipulation performance.
Xiaomin Yu, Yi Xin, Wenjie Zhang +12 authors
Researchers address the modality gap in multimodal learning by proposing a fixed-frame theory and a training-free alignment method that enables efficient scaling of multimodal models using unpaired data.
Yanzhe Chen, Zechen Bai, Zhijun Cao +7 authors
Show-Harness links vision-language models to robot control via discrete semantic actions interpreted by embodiment-specific modules, enabling zero-shot and efficient fine-tuned deployment across robots and GUIs.
Renping Zhou, Zanlin Ni, Zihao Fan +8 authors
Simple-WAM predicts future video representations with a single forward pass to preserve generalization while avoiding costly denoising during inference.
Guochao Jiang, Jingyi Song, Guofeng Quan +3 authors
Dynamic Variance-adaptive Advantage Optimization (DVAO) addresses training instability in multi-reward reinforcement learning by adaptively weighting objectives based on empirical reward variance, maintaining bounded advantage magnitudes and improving multi-objective performance.
Yijiang Li, Bingyang Wang, Nuno Vasconcelos
ACT3D trains vision-language models via reinforcement learning to actively explore 3D environments from single first-person views, improving answer accuracy through adaptive, question-conditioned navigation without direct exploration supervision.
Bowen Ye, Lei Li, Shicheng Li +16 authors
CodeMidas converts existing source code into executable reinforcement learning tasks for training coding agents, improving performance across repair, construction, and terminal benchmarks.
Xiangyan Qu, Zhenlong Yuan, Jing Tang +9 authors
Image-CoT methods are extended to image editing with ADE-CoT, which improves efficiency and performance through adaptive resource allocation, edit-specific verification, and opportunistic stopping mechanisms.
Hejun Dong, Junbo Niu, Bin Wang +3 authors
MinerU-Diffusion is a diffusion-based framework that replaces autoregressive decoding with parallel diffusion denoising for document OCR, improving robustness and decoding speed.
Zhifei Xie, Kaiyu Pang, Haobin Zhang +4 authors
Mega-ASR framework improves robustness in real-world speech recognition through compound-data construction and progressive acoustic-to-semantic optimization techniques.
Qing Zong, Jiayu Liu, Junhao Shen +9 authors
Agentic systems can achieve open-ended improvement through multi-component co-evolution that progressively removes fixed human constraints across agents, environments, and evolution mechanisms.
Robbyant Team, Zelin Gao, Qiuyu Wang +21 authors
LingBot-World is an open-source world simulator with high-fidelity dynamics, long-term memory capabilities, and real-time interactivity for diverse environments.
Xin Gao, Yifan Yang, Xin Li +13 authors
AesCode improves code generation for visual artifacts by combining design graphs with cross-modal rewards guided by reference images, enhancing layout, aesthetics, and verifiable correctness.
Yu Wang, Rui Dai, Wei Chen +5 authors
Urbex reframes city-scale 3D grounding as an active search process using a vision-language agent with reinforcement learning, improving accuracy and speed without precomputed proposals.
Yang Xiao, Vidhyasaharan Sethu, Eun-Jung Holden +1 authors
VoxMem introduces a multi-session spoken memory benchmark spanning acoustic evidence types and reasoning operations, revealing that current audio-language models struggle with speaker, paralinguistic, and environmental memory.
Hongjin Qian, Chaofan Li, Kun Luo +11 authors
AREX-2 trains LLM agents on synthetic long-horizon improvement trajectories to enable iterative test-time refinement, yielding strong results across coding, research, and reasoning benchmarks.
Zihao Wu, Hongyao Tang, Yi Ma +9 authors
Off-policy reinforcement learning stabilizers vary with data availability, motivating regime-aware algorithms that adapt normalization and Q-function clipping to improve efficiency across CPU and GPU-parallel training.
Yicheng Zou, Dongsheng Zhu, Lin Zhu +171 authors
Intern-S1-Pro is a one-trillion-parameter scientific multimodal foundation model that enhances general and scientific capabilities through advanced agent functionalities and specialized task mastery across multiple scientific disciplines.
Zhiyu Li, Zeyu Zhang, Linyun Liu +71 authors
MemT-1.0 introduces a memory-native architecture that embeds continuous memory into foundation model computation, improving long-context efficiency and agentic task performance.
Yuxue Yang, Lue Fan, Ziqi Shi +3 authors
NeoVerse is a scalable 4D world model that enables pose-free reconstruction and novel-trajectory video generation from monocular videos with state-of-the-art performance.
Yiran Wang, Xingyilang Yin, Junfu Pu +12 authors
GameHorizon introduces a unified dataset and benchmark suite for evaluating AI gameplay capabilities across multiple temporal horizons using standardized offline and online tests.
Yongzhen Hu, Hao Yu, Jiawei Wang +7 authors
InfiniSplat v2 improves feed-forward 3D Gaussian reconstruction by decoupling geometry and attribute prediction, aligning Gaussians with ground-truth poses, and using large-angle supervision to enhance novel-view rendering quality.
Kevin Qinghong Lin, Batu EI, Yuhong Shi +3 authors
A multi-agent framework automates data journalism by generating evidence-grounded, multimodal news stories while maintaining transparency and verifiability.
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