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。
50 篇论文 · 按点赞排序
Jaewon Chu, Jinwoo Seo, Jaewon Cho +4 authors
AgentGrad improves multi-agent prompt optimization by identifying target agents through sequential intervention and clustering gradients semantically to avoid mixing unrelated errors.
Youngrok Park, Sangmin Bae, Hojung Jung +6 authors
On-Policy Reverse Distillation enables stronger models to exceed weak supervisors by amplifying verifier-supported policy gradients along the teacher's shift direction, accelerating optimization without imposing capacity limits.
Sergii Kozyrev, Davyd Maiboroda
Fully quantizing hybrid LLMs—including recurrent Gated DeltaNet layers—to 4-bit NVFP4 preserves accuracy across long-context and reasoning benchmarks by localizing outliers and exploiting robust delta-rule dynamics.
Soohyun Ryu, Sohee Kim, Eunho Yang
Large vision-language models trained on synthetic block-manipulation tasks improve 3D spatial reasoning and generalize to real-world visual tasks.
Runpeng Dai, Kaili Huang, Changsung Kang +1 authors
CoGR trains LLMs to generate compact keywords for both queries and items, enabling direct inverted-index retrieval optimized via co-evolving reinforcement learning.
Namgyu Ho, Huzama Ahmad, Woosung Koh +3 authors
Declarative Attention lets language models declare relevant context regions during reasoning to skip most KV cache reads, reducing attended tokens with small accuracy trade-offs.
Guangting Zheng, Yiyuan Zhang, Tao Yang +4 authors
Direct end-to-end training of latent generative models avoids collapse via entropy preservation and asymmetric dynamics, using a generation-first strategy to achieve state-of-the-art image synthesis and unified multimodal generation.
Kang Liao, Yihang Luo, Xiao-Ming Wu +7 authors
Puffin-World is a unified multimodal framework that jointly models physics, geometry, and appearance for physically consistent 3D world generation, reconstruction, and closed-loop exploration.
Yuran Wang, Siqiao Huang, Mingleyang Li +21 authors
OpenWAM factorizes world-action pretraining into modular components to identify key design principles, yielding a scalable open model with strong simulation and real-robot performance.
Ziyuan Liu, Hengqi Liu, Zichuan Wang +6 authors
Two large-scale search agents are trained via a multi-stage pipeline combining supervised fine-tuning and reinforcement learning against live search, achieving state-of-the-art open-source results on complex web benchmarks through rigorous trajectory filtering and inference-time context management.
Venus Team, Zhuohan Cai, Haoxing Chen +28 authors
UI-Venus-2 is a general-purpose multimodal GUI agent that uses unified reasoning-action loops, expanded environment coverage, and robust verification to enable reliable real-world digital automation.
Zihan Qiu, Zekun Wang, Xiao Li +33 authors
Qwen3.8-Flash-Next is a sparse mixture-of-experts architecture combining hybrid gated delta-net and sparse attention layers, gated residual branches, and off-accelerator n-gram embeddings to improve efficiency, capability, and training stability.
Igor Pavlovic, Thiemo Wandel, Anton Obukhov +6 authors
Marigold V2 repurposes diffusion transformers for monocular depth estimation via single-step flow-matching inference, semantic alignment, and a Sinkhorn-based two-stage fine-tuning protocol, yielding sharper out-of-distribution depth maps and strong results on related dense regression tasks.
Hao He, Chengcheng Hu, Zirun Su +17 authors
DriveZero is an end-to-end autonomous driving system that combines a vision foundation model for perception with a closed-loop reinforcement learning action model to learn driving behaviors beyond human demonstrations.
RadixArk, Tom Chen, Mao Cheng +10 authors
Miles is an open-source, production-ready system for large-scale reinforcement learning and post-training that supports diverse backends, weight synchronization, LoRA, distillation, and diffusion models.
AgiBot Research Team, Renhang Liu, Wenzhi Zhao +42 authors
GE-Act 2.0 is a world-action model trained from scratch with a control-oriented autoencoder, single-step visual planner, and inverse dynamics model, using knowledge-aligned selective optimization to enable scalable zero-shot robot manipulation across diverse skills and conditions.
Jiale Kang, Ziyin Yue, Zheng Zhan +2 authors
Normalized Low-Rank Adaptation stabilizes LoRA training by normalizing down-projection matrices, accelerating convergence and improving performance without extra parameters or inference cost.
Xionghao Wu, Yijun Yang, Shiyang Zhou +17 authors
ZimaBlue learns generalizable world action models from large-scale egocentric video via a three-stage curriculum and a slow-fast architecture, substantially improving zero-shot robotic manipulation.
Danze Chen, Zeqing Wang, Ziyue Lin +2 authors
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become more capable, language is emerging as a natural interface for control. MiniMax-H3, for example, already supports zero-shot control of character behavior and camera motion through natural-language instructions. Building on this, H3-World turns this coarse language interface into precise, temporally grounded world control, without introducing dedicated action modules. Specifically, we represent each action as a structured combination of character and camera instructions, and align them with the corresponding temporal video latents. To make the control temporally precise, we further introduce temporal attention routing, which restricts each instruction to its intended time interval and reduces control leakage across actions. Importantly, H3-World directly reuses the semantic representations learned during large-scale video pretraining and requires only lightweight adaptation. With only 8,000 gameplay samples, 10,000 LoRA optimization steps, and 0.199% trainable parameters, H3-World achieves effective character and camera control while preserving strong generation quality. It also generalizes to unseen scenarios. These results show that the control capabilities emerging in large video generators can be efficiently transformed into interactive world control.
Junyao Yang, Yucheng Shi, Zhongzhi Li +4 authors
T1 is a 122B Mixture-of-Experts model trained with reinforcement learning to execute long-horizon terminal tasks in a cloud sandbox, achieving state-of-the-art results through stable actor-critic optimization and out-of-distribution training.
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