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。
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22 authors
DataFlex is a unified framework for dynamic data-centric training of large language models that supports sample selection, domain mixture adjustment, and sample reweighting while maintaining compatibility with standard training workflows and enabling efficient large-scale deployment.
50 篇论文 · 按点赞排序
Chiyu Ma, Shuo Yang, Kexin Huang +7 authors
FIPO enhances reinforcement learning for language models by using discounted future-KL divergence to improve credit assignment and extend reasoning chains, achieving better mathematical problem-solving performance.
Tianle Zeng, Hanxuan Chen, Yanci Wen +1 authors
CARLA-Air integrates high-fidelity driving and multirotor flight simulation within a unified Unreal Engine framework, supporting joint air-ground agent modeling with photorealistic environments and multi-modal sensing capabilities.
Kaijin Chen, Dingkang Liang, Xin Zhou +4 authors
Hybrid Memory enables video world models to maintain consistent tracking of dynamic subjects during occlusion by combining archival storage for static backgrounds with active tracking for moving objects, using a specialized architecture with tokenized memory and spatiotemporal retrieval mechanisms.
Yawen Luo, Xiaoyu Shi, Junhao Zhuang +5 authors
ShotStream enables real-time interactive multi-shot video generation through causal architecture design, dual-cache memory mechanisms, and two-stage distillation to maintain visual consistency and reduce latency.
Xinlei Yu, Zhangquan Chen, Yongbo He +34 authors
Latent space is emerging as a fundamental computational substrate for language-based models, offering advantages over explicit token-level approaches through continuous representation that mitigates linguistic redundancy and sequential inefficiency.
Meituan LongCat Team, Bin Xiao, Chao Wang +86 authors
Discrete Native Autoregressive framework enables unified multimodal processing by representing diverse modalities in a shared discrete space through a novel visual transformer architecture.
Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna +2 authors
Speculative decoding effectiveness depends on draft model training data alignment with downstream tasks, with specialized drafters performing better when combined through confidence-based routing rather than simple averaging.
Zheng-Hui Huang, Zhixiang Wang, Jiaming Tan +6 authors
A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel VLM-based evaluation method that correlates well with human judgment.
Zhengxi Lu, Zhiyuan Yao, Jinyang Wu +7 authors
SKILL0 enables LLM agents to internalize skills during training, allowing zero-shot autonomous behavior through a dynamic curriculum that reduces contextual overhead while improving task performance.
Patrice Bechard, Orlando Marquez Ayala, Emily Chen +5 authors
Simple terminal-based coding agents using programmatic interfaces and foundation models can effectively perform enterprise tasks comparable to or better than complex tool-augmented agents.
Hongtao Wu, Boyun Zheng, Dingjie Song +5 authors
Medical AI Scientist represents the first autonomous research framework designed for clinical applications, enabling evidence-based hypothesis generation and manuscript drafting through clinician-engineer collaboration across three research modes.
Zefeng He, Siyuan Huang, Xiaoye Qu +4 authors
GEMS is an agent-native multimodal generation framework that enhances model capabilities through structured multi-agent optimization, persistent memory, and domain-specific skills across general and downstream tasks.
Han Zhang, Guo-Hua Yuan, Chaohao Yuan +6 authors
Lingshu-Cell is a masked discrete diffusion model that learns transcriptomic state distributions and enables conditional simulation of cellular perturbations across diverse tissues and species.
Fangda Ye, Yuxin Hu, Pengxiang Zhu +19 authors
MiroEval addresses limitations of existing deep research system benchmarks by introducing a comprehensive evaluation framework that assesses adaptive synthesis, agentic factuality verification, and process-centric auditing across real-user tasks.
Zhongying Deng, Cheng Tang, Ziyan Huang +124 authors
Medical imaging datasets remain fragmented and limited in scale, but a metadata-driven fusion paradigm enables integration of scattered resources to support development of more robust foundation models.
Xinyu Tian, Shu Zou, Zhaoyuan Yang +3 authors
Reinforcement Learning enhances Vision-Language Model reasoning but suffers from diversity collapse; a new Multi-Group Policy Optimization method is proposed to encourage diverse thinking patterns.
Zhaochong An, Orest Kupyn, Théo Uscidda +5 authors
VGGRPO enhances video diffusion models with latent geometry guidance to improve geometric consistency and camera stability while avoiding expensive VAE decoding.
Jona Ruthardt, Manu Gaur, Deva Ramanan +2 authors
Steerable Visual Representations enable language-guided focus on specific image elements while maintaining representation quality through early fusion of text and visual features.
Kaituo Feng, Manyuan Zhang, Shuang Chen +7 authors
A search-augmented image generation agent is presented that performs multi-hop reasoning and search to collect textual knowledge and reference images for grounded generation, trained with supervised fine-tuning and agentic reinforcement learning with dual reward feedback.
Saman Motamed, William Harvey, Benjamin Klein +3 authors
VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning.
Ruixiang Zhang, Richard He Bai, Huangjie Zheng +3 authors
Simple self-distillation improves code generation in large language models by fine-tuning on model-generated samples, effectively addressing precision-exploration trade-offs in decoding.
Jingwei Ni, Yihao Liu, Xinpeng Liu +6 authors
Trace2Skill enables scalable skill generation for LLM agents by analyzing diverse execution traces in parallel and consolidating them into transferable, declarative skills without parameter updates or external modules.
Ao Qu, Han Zheng, Zijian Zhou +14 authors
Autonomous multi-agent evolution framework enables open-ended discovery through persistent memory, asynchronous execution, and collaborative problem-solving, achieving superior performance on mathematical and optimization tasks.
Xiaofeng Mao, Shaohao Rui, Kaining Ying +4 authors
PackForcing enables efficient long-video generation through hierarchical KV-cache management and spatiotemporal compression while maintaining temporal consistency and reducing memory usage.
Yue Huang, Yu Jiang, Wenjie Wang +12 authors
Multi-agent systems with large generative models exhibit emergent collective behaviors and risks that mirror human societal pathologies without explicit instruction.
Shifang Zhao, Yihan Hu, Ying Shan +2 authors
CutClaw is an autonomous multi-agent framework that uses multimodal language models to automatically edit long video footage into rhythmic, narratively consistent short videos with synchronized audio and visual elements.
Shuang Chen, Quanxin Shou, Hangting Chen +16 authors
Unify-Agent integrates agent-based modeling with multimodal understanding to enhance image synthesis through reasoning, searching, and generation processes grounded in external knowledge.
Huacan Wang, Chaofa Yuan, Xialie Zhuang +15 authors
General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to organize production and coordination. We believe AI agents are approaching a similar inflection point: as foundation models make broad task execution and tool use increasingly accessible, the binding constraint shifts from raw capability to how work is delegated, verified, and rewarded at scale. We introduce EpochX, a credits-native marketplace infrastructure for human-agent production networks. EpochX treats humans and agents as peer participants who can post tasks or claim them. Claimed tasks can be decomposed into subtasks and executed through an explicit delivery workflow with verification and acceptance. Crucially, EpochX is designed so that each completed transaction can produce reusable ecosystem assets, including skills, workflows, execution traces, and distilled experience. These assets are stored with explicit dependency structure, enabling retrieval, composition, and cumulative improvement over time. EpochX also introduces a native credit mechanism to make participation economically viable under real compute costs. Credits lock task bounties, budget delegation, settle rewards upon acceptance, and compensate creators when verified assets are reused. By formalizing the end-to-end transaction model together with its asset and incentive layers, EpochX reframes agentic AI as an organizational design problem: building infrastructures where verifiable work leaves persistent, reusable artifacts, and where value flows support durable human-agent collaboration.
Zehai He, Wenyi Hong, Zhen Yang +4 authors
Vision2Web presents a comprehensive benchmark for visual website development tasks and evaluates coding agents across static UI generation, interactive frontend reproduction, and full-stack development with varying complexity levels.
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