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。
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28 authors
Looped World Models introduce iterative latent state refinement through shared transformer blocks, achieving 100x parameter efficiency while adapting computational depth to prediction complexity.
50 篇论文 · 按点赞排序
Dingyu Yao, Junhao Zhou, Chenxu Yang +12 authors
A vision-language model operates continuously in real-time, making autonomous decisions about when to respond or delegate, enabling interactive systems that perceive and act upon environmental changes without user prompting.
Jian Yang, Shawn Guo, Wei Zhang +16 authors
Parallel loop Transformers achieve better code generation performance with two loops due to refined representations, while additional loops cause diminishing returns and increased positional mismatch costs.
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.
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.
Sen Xu, Shixi Liu, Wei Wang +6 authors
VibeThinker-3B demonstrates that compact models can achieve state-of-the-art performance on verifiable reasoning tasks through specialized training techniques, challenging conventional scaling assumptions.
Jisang Han, Seonghu Jeon, Jaewoo Jung +7 authors
A geometric action model leverages pretrained geometric foundation models to enable language-conditioned manipulation policies with improved accuracy, robustness, and efficiency in 3D physical environments.
Yongheng Zhang, Ziang Liu, Jiaxuan Zhu +17 authors
Large Language Models are evolving from conversational systems to integrated AI colleagues with enhanced reasoning capabilities and persistent work environments.
DreamX Team, Yancheng Bai, Rui Chen +20 authors
DreamX-World 1.0 is a interactive text/image-to-video model that generates long-horizon content with camera control and scene persistence using specialized encoding, training techniques, and optimization methods.
Jiwen Liu, Shujuan Li, Zhixue Fang +8 authors
A unified framework for camera motion cloning that uses grid motion videos as representation and integrates multimodal diffusion transformers for enhanced video generation control.
Shaoqiu Zhang, Maoquan Wang, Yuling Shi +5 authors
FastContext separates repository exploration from code solving in LLM agents using specialized exploration models that reduce token consumption and improve resolution rates.
Ang Li, Ben Liu, Bin Han +215 authors
Ling-2.6 and Ring-2.6 models are presented as scalable solutions for agentic intelligence, featuring architectural upgrades and specialized training methods to balance fast response times with advanced reasoning capabilities.
Xucong Wang, Ziyu Ma, Yong Wang +5 authors
Agentic Reinforcement Learning method that improves multi-turn tool-use capabilities by refining branching decisions and credit assignment through fine-grained decision points and procedure-level advantage scaling.
Shuo Ji, Yibo Li, Bryan Hooi
MRAgent combines associative memory graphs with active reconstruction to enable dynamic memory access during reasoning, improving long-horizon memory reasoning while reducing computational costs.
Yifu Luo, Zeyu Chen, Haoyu Wang +4 authors
d-OPSD introduces a novel on-policy self-distillation framework for diffusion language models by adapting self-teacher construction and supervision mechanisms to match the non-autoregressive nature of diffusion models.
Tianshan Zhang, Yijia Duan, Yanjun Li +2 authors
DragMesh-2 enables dexterous hand-object interaction through contact-driven manipulation, with PICA enhancing robustness under varying contact loads without tactile feedback.
Byung-Kwan Lee, Ximing Lu, Shizhe Diao +8 authors
Zone of Proximal Policy Optimization (ZPPO) improves knowledge distillation by using reformulated prompts that help students learn from both correct and incorrect responses, enhancing performance especially at smaller model sizes.
Maria Ivanova, Pavel Zadorozhny, Rodion Levichev +5 authors
Multi-LCB addresses the limitation of LiveCodeBench by providing a multi-language benchmark for evaluating LLMs across twelve programming languages while maintaining contamination controls and evaluation protocols.
Tongxu Luo, Rongsheng Wang, Jiaxi Bi +22 authors
End-to-end game generation presents significant challenges for coding agents, requiring them to create complete playable games from natural language descriptions while meeting specific evaluation criteria for engine grounding, artifact completeness, and interactive verification.
Hongjian Zhou, Xinyu Zou, Jinge Wu +19 authors
Large language models demonstrate reduced medical reasoning accuracy when exposed to misleading context, highlighting a critical gap in current evaluation methods that fails to assess epistemic resilience under adversarial conditions.
Hao Li, Ganlong Zhao, Yufei Liu +8 authors
A unified Vision-Language-Action pretraining framework leverages heterogeneous data sources including human egocentric videos and robot trajectories through a reliability-aware training approach that improves performance on embodied AI tasks.
Jianing Zhang, Chenhao Zheng, Yajun Yang +10 authors
3D point motion forecasting model predicts object trajectories from visual history and language goals, demonstrating superior performance on benchmarks and transferring effectively to robot manipulation and video generation tasks.
Shengyuan Ding, Xilin Wei, Xinyu Fang +4 authors
A new benchmark suite called RNG-Bench is introduced to evaluate multimodal foundation models' ability to reconstruct past observations and use them for decision-making in multi-step interactions, featuring two games with controlled difficulty parameters and a memory gap metric to distinguish forgetting from poor decision-making.
Tingyang Chen, Shuo Lu, Kang Zhao +11 authors
HarnessX enables adaptive and evolvable AI agent runtime interfaces through compositional primitives, trace-driven evolution, and feedback loops that improve both harness design and model training.
Junyi Zhang, Jiaxin Ge, Hanjun Yoo +17 authors
Embodied robots learn reusable skills through self-directed play and exploration, then apply these skills to improve performance on downstream tasks without additional training.
Fan Zhang, Vireo Zhang, Shengju Qian +8 authors
An omnimodal agent orchestration framework is presented that enables efficient collaboration across multiple modalities through unified task decomposition and specialized sub-agent execution, achieving superior performance on complex multimodal benchmarks.
Jie Zhang, Xiaoyue Chen, Anzhe Chen +35 authors
Qwen-RobotWorld is a language-conditioned video world model that predicts future visual trajectories across multiple robotic domains using a double-stream diffusion transformer and embodied world knowledge corpus.
Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin +58 authors
Aggregate-score leaderboards in agent benchmarks fail to capture deployment-relevant dimensions and show rank instability, necessitating new evaluation frameworks based on predictive validity and out-of-distribution criteria.
Kairos Team, Fei Wang, Shan You +21 authors
Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications.
Yalun Dai, Hao Li, Shulin Tian +10 authors
S-Agent is a spatial reasoning framework that enhances visual language models with temporal memory and hierarchical spatial tools to enable continuous 3D world understanding from multi-view imagery.
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