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。
Zhongzhi Li, Yucheng Shi, Zongxia Li +8 authors
Recursive verified synthesis generates scalable long-horizon terminal-agent training data, substantially improving model performance on terminal benchmarks through supervised fine-tuning and reinforcement learning.
50 篇论文 · 按点赞排序
Ziyu Ma, Hailang Huang, Shun Zou +5 authors
LongHorizon-Harness improves long-horizon agent performance by explicitly tracking verified task states outside context via a manage-execute-audit loop.
Yu Zhang, Ruiqi Li, Changhao Pan +3 authors
SwanTale is a multi-speaker expressive speech and audio generation model that supports both instruction-based and zero-shot synthesis with high-quality multi-modality outputs.
Jianyu Wu, Yizhou Wang, Encheng Su +2 authors
Dual-Anchored Policy Distillation resolves privilege illusion in on-policy self-distillation by aligning matched-information paths and reducing reliance on privileged guidance, improving performance across model scales.
Zixuan Huang, Yang Zhou, Kaixuan Wang +6 authors
Proposed multiple-choice planning and deferred trajectory verification reduce reasoning bias and improve verifiable autonomous driving decisions.
Qiming Shi, Yulong Tao, Linbo Jin +10 authors
MerchantBench evaluates long-term coherence of LLM agents in a year-long e-commerce simulation requiring persistent decision-making across sourcing, pricing, and cash-flow management with mixed feedback delays.
Hao Fei, Yiran Zhao
Mental World Modeling integrates hidden mental states into predictive world models to improve action forecasting by jointly simulating physical scenes and agent beliefs.
Qinsi Wang, Jing Shi, Huazheng Wang +8 authors
RLSVR extends reinforcement learning with verifiable rewards to open-ended tasks by transforming them into self-verifiable proxy environments, demonstrated via a multi-agent spy game that yields automatic rewards for text generation and reasoning.
Yicheng Xiao, Wenxun Dai, Xinran Qin +22 authors
JoyAI-Video-Edit is a 16B-parameter autoregressive diffusion framework that enables real-time, open-ended video editing with high source fidelity and long-term temporal consistency on a single GPU.
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao +10 authors
AgentOPSD uses recursive Bayesian belief updates over turn-level log-probability gaps to assign credit in long-horizon agentic reinforcement learning without extra critics or rollouts.
Junliang Ye, Kenkun Liu, Guocun Wang +12 authors
Hunyuan3D-Buffalo 1.0 unifies 3D understanding, generation, editing, and part generation via a multimodal architecture trained on a large-scale 3D corpus, achieving leading benchmark results.
Chunchao Guo, Jinpeng Li, Yang Li +1 authors
WorldClaw is an agentic coarse-to-fine framework that generates large-scale editable 3D worlds from text by combining planning agents, semantic layouts, reusable assets, and render-based refinement.
Jiajun Liang, Yucheng Liao, Yukang Cao +12 authors
AURORA-LM is a continuous-latent diffusion language model that preserves high-capacity decodable text representations and uses a block-causal diffusion transformer with flow matching to generate text.
NeoteAI Team, Fudan TEAI Team
A vision-tactile-language-action model pretrained on large-scale tactile data achieves fine-grained contact-rich manipulation and improves via advantage-conditioned offline reinforcement learning.
Qiushi Sun, Kanzhi Cheng, Yian Wang +20 authors
Researchers introduce a benchmark and open reward models to evaluate and improve vision-language judges for computer-using agent trajectories, revealing systematic leniency biases and offering cost-effective alternatives.
Jiawei Wang, Hao Yu, Yongzhen Hu +7 authors
InfiniSplat improves single-image 3D Gaussian Splatting by aligning Gaussian primitives to scene surfaces via geometry-guided sampling and implicit decoding, yielding more coherent renderings under large viewpoint changes.
Ilia Semenkov, Daria Kleeva, Ivan Dakhtin +2 authors
Redesigning a MEG-to-audio retrieval model with spherical harmonics, source-space mapping, and input interventions reveals that narrative speech structure, acoustic onsets, and intensity drive retrieval while reducing parameters.
Yijun Lu, Rui Ye, Jiajun Wang +4 authors
Answer-Backtracked Credit Assignment improves long-horizon search agents by assigning dense step-level rewards via answer-backtracked clue recovery and clue-anchored scoring, yielding strong benchmark results with small models.
Junlin Han, Shengbang Tong, David Fan +4 authors
Systematic experiments reveal how unified multimodal pretraining transfers knowledge across vision and language, showing that early joint training, shared attention with modality-specific feed-forward layers, and low-compute recipes improve synergy and reduce vision laziness.
Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun +5 authors
ToolArtist is an agentic image generation model that unifies reasoning, tool use, and image synthesis under a single policy via supervised fine-tuning and reinforcement learning.
Jiale Xu, Rendong Liang, Yuhao Long +4 authors
Meshy T2 is a fast native mesh generation framework using flow matching and a vertex-set mesh VAE to produce high-fidelity, artist-style meshes with interactive speed and controllable complexity.
Junhao Shen, Zhanqiu Zhang, Yiwen Guo +1 authors
Skill-α uses reinforcement learning with rollback rewards to progressively generate agent skills by evaluating sequential edits against downstream task performance.
Zhen Fang, Yu Zeng, Wenxuan Huang +17 authors
Video-DeepResearch extends multimodal agents to continuous video via decoupled perception-exploration and GRPO training, achieving state-of-the-art results on a new video reasoning benchmark.
Tingyu Song, Mingxin Li, Yanzhao Zhang +5 authors
UEmbed is a decoder-only multimodal model that jointly produces dense and sparse embeddings in a single forward pass, extending sparse retrieval to unified text and multimodal inputs.
Zishan Xu, Zhiyuan Yao, Yuxin Chen +9 authors
EnvACE trains large language model agents via internal world rehearsal instead of external environments, improving long-horizon tool use through joint optimization of action and simulated response.
NeoteAI Team, Fudan TEAI Team
N0-TWAM is a large-scale tactile-native world-action model that predicts future vision, contact, and actions for contact-rich manipulation using a unified force-based tactile representation, contact events for task staging, and an asymmetric mixture-of-transformers architecture.
Qifeng Zhang, Kaixiang Huang, Heng Dong +6 authors
The study introduces a video benchmark requiring global spatial reasoning across long videos and reveals that vision-language models struggle to build consistent global scene representations despite strong local perception.
Kangning Zhang, Yixing Li, Shuai Shao +9 authors
Visual Attribution Distillation uses counterfactual reconstruction to isolate visually supported corrections from mixed teacher signals, improving multimodal on-policy distillation.
Soslan Kabisov, Gennadiy Savrasov, Maksim Elistratov +9 authors
CADENA reconstructs 3D meshes into parametric CAD programs step-by-step with intermediate geometry checks and introduces a benchmark for mechanical part reverse engineering.
Yushi Sun, Yanjie Zhang, Rui Sheng
Over-inference of unsupported user attributes is pervasive across personalized LLMs, with self-reported confidence inversely correlating with actual fabrication rates, underscoring the need for external verification.
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