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。
Ye Jin, Yangyang Xu, Jun Zhu +1 authors
MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool memory for reusable execution experiences to enable stable personalization and reliable local edits across multi-turn revisions.
50 篇论文 · 按点赞排序
Yuxin Zuo, Zikai Xiao, Li Sheng +30 authors
Language-based world models enable agentic environment simulation across multiple domains and enhance general agent performance through scalable simulation and improved downstream task performance.
Wei Zhou, Xuanhe Zhou, Shaokun Han +5 authors
Large language model agents' memory systems have evolved into complex data management frameworks requiring systematic evaluation across multiple modules and workloads to understand their performance characteristics and trade-offs.
Lianghua Huang, Zhifan Wu, Wei Wang +21 authors
Wan-Streamer is a unified, end-to-end multimodal model that enables real-time audio-visual interaction through causal attention mechanisms and integrated processing of visual, audio, and text modalities.
Jiayu Liu, Qihan Lin, Cheng Qian +8 authors
PlanBench-XL evaluates large language model agents' ability to plan and adapt in complex tool-rich environments with limited visibility and dynamic disruptions.
Youyang Yin, Huanhuan Liu, YY +14 authors
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.
Wei Zhou, Xiongwei Zhu, Zelin Xu +8 authors
A novel on-policy generative field distillation framework called DanceOPD is proposed to unify text-to-image generation, local editing, and global editing capabilities in flow-matching models through capability-specific routing and velocity-based training.
Jincheng Zhong, Weizhi Wang, Che Jiang +5 authors
EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single performance scores.
Vishesh Tripathi, Abhay Kumar
Grouped Query Experts (GQE) improves Transformer efficiency by selectively activating query heads based on token content while maintaining key-value cache benefits of grouped-query attention.
Fukang Wen, Zhijie Wang, Ruilin Xu
OpenRath introduces a PyTorch-like programming model for multi-agent systems using Session as a central runtime abstraction that enables explicit fork, merge, and replay operations while recording comprehensive execution state.
Cong Wan, Zeyu Guo, Zijian Cai +6 authors
Agentic Data Tailoring paradigm uses learnable data processing to structure high-entropy multimodal streams, with DataClaw_0-9B model achieving robust alignment through SFT and GRPO on a novel benchmark.
Nan Chen, Yiyang Cai, Rongchang Xie +7 authors
DomainShuttle enables open domain subject-driven text-to-video generation with high fidelity and flexibility across in-domain and cross-domain scenarios through domain-aware modeling and dual RoPE schemes.
Yuru Wang, Lejun Cheng, Yuxin Zuo +14 authors
NatureBench presents a cross-disciplinary benchmark of 90 scientific tasks derived from Nature publications to assess AI coding agents' ability to achieve discovery rather than just reproduction, revealing that current agents primarily rely on methodological translation rather than genuine scientific innovation.
Yueyi Sun, Yuhao Wang, Jason Li +8 authors
PerceptionDLM enables efficient parallel region perception in multimodal diffusion language models through structured attention masking and efficient prompting, achieving faster inference without sacrificing caption quality.
Siyin Wang, Junhao Shi, Senyu Fei +4 authors
ICWM enables robot policies to infer system variables from self-generated interactions, allowing adaptation to novel configurations without parameter updates by treating system identification as an in-context adaptation problem.
Qiuhong Shen, Shihua Zhang, Yue Liao +5 authors
World Action Models are predictive-action systems that generate future states for decision-making, with designs balancing representational richness against computational constraints.
Shuo Yang, Jinyang Wu, Zhengxi Lu +8 authors
On-policy skill distillation framework extracts dense hindsight supervision from completed trajectories to improve language agent training efficiency and performance.
Zekai Zhang, Jiahao Li, Jie Zhang +18 authors
A unified agentic framework called Qwen-Image-Agent is proposed to address the context gap in text-to-image generation by progressively constructing complete generation context through planning, reasoning, searching, and memory mechanisms.
Binghai Wang, Chenlong Zhang, Dayiheng Liu +9 authors
Verification challenges in AI agents arise from the difficulty of aligning proxy signals with human intent, requiring adaptive verification systems that evolve alongside generative capabilities.
Shiding Zhu, Yudi Qi, Yajie Wang +6 authors
EDV is a three-stage framework that uses multiple heterogeneous agents to collaboratively construct reliable experiences for LLM agents, preventing self-confirmatory errors through execute-distill-verify processes.
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47 authors
An open-source data curation pipeline for training agentic language models is presented, demonstrating superior performance through systematic experimentation and scalable training data.
Xinping Zhao, Jiaxin Xu, Ziqi Dai +7 authors
KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using encoder-decoder architecture with Matryoshka embedding pooling and cross-attention for efficient relevance modeling.
Shen Nie, Qiyang Min, Shaoxuan Xu +7 authors
Masked diffusion language models with fully bidirectional attention outperform autoregressive counterparts on various benchmarks while maintaining competitiveness with established models.
Jiayu Li, Yixiao Fang, Tianyu Hu +5 authors
Researchers developed a new benchmark and dataset for photography assistance, along with a unified multimodal model that provides both composition guidance and pose recommendations during image capture.
Guangyi Liu, Pengxiang Zhao, Gao Wu +8 authors
MobileForge enables efficient adaptation of mobile GUI agents through annotation-free learning by combining real app interaction grounding with hierarchical feedback-guided policy optimization.
Guangyi Liu, Gao Wu, Congxiao Liu +7 authors
MemGUI-Agent addresses long-horizon mobile GUI task limitations through proactive context management using Context-as-Action (ConAct) to maintain critical information across extended sequences.
Xuanle Zhao, Qiushi Sun, Jingyu Xiao +16 authors
This survey explores multimodal code intelligence systems that generate and reason with code based on visual inputs, categorizing approaches across GUI, scientific visualization, structured graphics, and emerging frameworks while identifying verification-centered research directions.
Xumin Yu, Zuyan Liu, Zhenyu Yang +5 authors
ViQ presents a visual quantization framework that balances semantic richness and detail preservation in discrete representations, enabling efficient multimodal training with native-resolution inputs.
Zhanbo Hua, Yifan Yao, Weihao Xie +14 authors
A principled synthesis engine generates high-quality terminal-agent tasks through multi-dimensional capability taxonomy and evidence-guided research, creating a distilled dataset that enables significant performance gains in LLM training.
JoungBin Lee, Jaewoo Jung, Jongmin Lee +8 authors
A novel-view video synthesis method that enhances motion-aware diffusion models through multi-view point tracking supervision to improve geometric consistency and motion fidelity.
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