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。
Ming Qian, Tianjian Ouyang, Mingchao Sun +25 authors
ABot-Earth 0.5 generates realistic 3D environments from satellite imagery using 3D Gaussian Splatting representation, enabling fast synthesis and real-time visualization for Embodied AI applications.
50 篇论文 · 按点赞排序
Yiyou Sun, Xinyang Han, Weichen Zhang +305 authors
Agents' Last Exam (ALE) is a benchmark for evaluating AI agents on long-term, economically valuable real-world tasks across 13 industry clusters with 1K+ tasks, revealing significant gaps between benchmark performance and practical deployment.
Kwai Keye Team, Bin Wen, Changyi Liu +50 authors
Kwai Keye-VL-2.0-30B-A3B is an open-source Mixture-of-Experts multimodal foundation model that enables long-video understanding and agentic intelligence through DeepSeek Sparse Attention and specialized training infrastructure.
Yifu Yuan, Yaoting Huang, Xianze Yao +20 authors
Embodied-R1.5 is a unified embodied foundation model that integrates embodied reasoning capabilities and achieves state-of-the-art performance on embodied vision-language benchmarks through a multi-task balanced reinforcement learning approach.
Xunhao Lai, Weiqi Xu, Yufeng Yang +8 authors
MiniMax Sparse Attention enables efficient processing of ultra-long contexts in large language models through blockwise sparsity and optimized GPU execution, achieving significant speedups while maintaining performance.
Jundong Xu, Qingchuan Li, Jiaying Wu +11 authors
EvoArena benchmark and EvoMem memory paradigm address the challenge of dynamic environments in LLM agents by modeling progressive updates and structured memory evolution, showing improved performance on evolving tasks.
Jiajie Jin, Yuyang Hu, Kai Qiu +15 authors
An AI framework called Arbor enables autonomous scientific research by combining strategic coordination, isolated hypothesis testing, and a persistent knowledge tree to iteratively improve research outcomes across multiple domains.
Mahtab Bigverdi, Linjie Li, Weikai Huang +8 authors
Imaginative Perception Tokens (IPT) enhance vision-language models' spatial reasoning by providing intermediate perceptual representations that externalize what the model would perceive from alternative viewpoints, outperforming traditional text-based reasoning methods.
Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8 authors
SWE-Explore introduces a benchmark for evaluating coding agents' repository exploration capabilities by requiring ranked lists of relevant code regions within line budgets, demonstrating that agentic exploration outperforms traditional retrieval methods.
Seokju Cho, Ryo Hachiuma, Abhishek Badki +8 authors
SpatialClaw is a training-free framework that uses code as an action interface to enable flexible, stateful spatial reasoning in vision-language models, achieving superior performance across diverse 3D/4D spatial reasoning tasks.
Wanli Li, Bowen Zhou, Yunyao Yu +4 authors
WeaveBench presents a comprehensive benchmark for evaluating computer-use agents across multiple interfaces, revealing significant challenges in long-horizon task orchestration and highlighting the limitations of traditional performance assessment methods.
Wanghan Xu, Shuo Li, Tianlin Ye +47 authors
ResearchClawBench evaluates autonomous scientific research capabilities across 40 tasks from 10 domains using expert-curated criteria and reveals current limitations in re-discovery accuracy among AI agents and LLMs.
Songhao Wu, Zhongxin Chen, Yuxuan Liu +3 authors
Text embeddings from large language models are enhanced by EmbedFilter, a linear transformation that reduces the influence of high-frequency tokens and improves semantic representations while enabling dimensionality reduction.
Jiacheng Chen, Xinyu Zhang, Shunkai Zhang +20 authors
MaxProof is a test-time scaling framework that enhances mathematical proof generation by combining multiple proof-oriented capabilities and using population-level search with tournament selection to achieve competitive performance on high-level mathematical competitions.
Songhao Wu, Ang Lv, Ruobing Xie +1 authors
Researchers propose a novel router redesign for Mixture-of-Experts models that aligns router rows with the principal singular directions of expert matrices using Manifold Power Iteration to improve model effectiveness.
Dian Zheng, Harry Lee, Manyuan Zhang +4 authors
InterleaveThinker enables interleaved generation capabilities for image generators through a multi-agent pipeline with planner and critic agents, achieving performance comparable to state-of-the-art models while enhancing reasoning benchmarks.
Jiaqi Tang, Jianmin Chen, Youyang Zhai +6 authors
Robust-U1 enhances multimodal large language models' robustness against visual corruptions through self-recovery capabilities that improve both visual quality and reasoning performance.
Jia Deng, Yimeng Chen, Xiaoqing Xiang +9 authors
A framework for creating shortcut-resistant training data for deep search agents by identifying and mitigating four shortcut risks in data synthesis processes.
Xucong Wang, Ziyu Ma, Shidong Yang +4 authors
Role-Agent framework enables LLM agents to function as both agent and environment through bootstrapped co-evolution, improving performance via environment-aware reasoning and targeted practice.
Zhennan Shen, Yanshu Li, Qingyu Yin +6 authors
On-policy distillation exhibits distinct parameter space dynamics characterized by relaxed off-principal updates and subspace locking, forming a unique geometric pattern separate from supervised fine-tuning and reinforcement learning with verifiable rewards.
Jiachun Li, Zhuoran Jin, Tianyi Men +12 authors
Large language model agents require specialized environments for training and evaluation, which can be categorized by their engineering lifecycle stages and evolved through various paradigms including neural and symbolic approaches.
Mengyu Zheng, Kai Han, Boxun Li +13 authors
A new benchmark and adapter protocol called Claw-SWE-Bench enables fair comparison of diverse coding agents by standardizing evaluation conditions and revealing the importance of adapter design for effective code generation.
Wenbo Pan, Shujie Liu, Chin-Yew Lin +5 authors
Retrospective Harness Optimization (RHO) is a self-supervised method that improves AI agent performance by optimizing agent harness using only past trajectories through diverse task selection, parallel re-solving, and self-validation techniques.
Weijie Wang, Haoyu Zhao, Yifan Yang +7 authors
Latent spatial memory for video world models stores 3D scene information directly in diffusion latent space, eliminating pixel-space reconstruction overhead and achieving faster generation with reduced memory usage.
Yan Wang, Qifan Zhang, Jiachen Yu +10 authors
Lookahead Sparse Attention with Neural Memory Indexer reduces GPU memory usage for long-context LLM inference while maintaining accuracy through proactive KV cache management and decoupled training.
Aofan Yu, Chenyu Zhou, Tianyi Xu +8 authors
LatentSkill enables efficient deployment of textual skills in agent systems by converting them into LoRA adapters stored in weight space, reducing context overhead while maintaining modularity and composability.
Xin Jin, Huanqia Cai, Zhen Li +8 authors
A teacher-student framework decouples complex reasoning from efficient reward deployment in text-to-image training, achieving superior preference accuracy and optimization performance.
Baochang Ren, Xinjie Liu, Xi Chen +15 authors
LabVLA, a vision-language-action model trained with a two-stage approach combining action token pretraining and flow matching, demonstrates superior performance on laboratory automation tasks through simulated data generation and robot-specific learning.
Pu Ning, Quan Chen, Kun Tao +7 authors
A large language model trained on synthesized delegation intelligence achieves superior performance on long-horizon research tasks through task decomposition and subagent coordination.
Taewon Yun, Hyeonseong Park, Jeonghwan Choi +3 authors
SoCRATES presents a realistic multi-domain benchmark for evaluating proactive LLM mediators across various socio-cognitive adaptation axes, demonstrating that even top-performing models only resolve about one-third of the consensus gap in conflict resolution.
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