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。
Xuyang Liu, Shihao Wang, Xinyu Wei +5 authors
OmniCompass is a holistic benchmark for omni-modal video grounding and understanding that evaluates vision-language and audio-visual reasoning through temporal grounding, spatial grounding, and question answering tasks.
50 篇论文 · 按点赞排序
Haotian Ma, Ruqi Yang, Philip Townsend
Spectral-Spatial Interpretation assigns localized channel importance at each spatial position via conditional Shapley values, yielding full spectral-spatial attribution matrices that outperform existing methods on multispectral image tasks.
StreamEval Team
StreamEval benchmarks interactive streaming video generation across five tasks, revealing that reliable request execution and sustained state consistency remain major challenges despite high visual quality.
Enhan Zhao, Yongqi Tong, Xuejun Yu +6 authors
BizBench evaluates long-horizon business agents on intermediate execution validity using real-world payment procedures, revealing that frontier models frequently violate constraints despite achieving partial goal success.
SenseNova, Joint Research Team, Zhongang Cai +59 authors
GPT-6-Astra achieves high performance across diverse robotic tasks via in-context learning, yet real-world deployment reveals gaps in demonstration cost, execution time, and practical embodied intelligence.
Qi Li, Xinchao Wang
Jeva is a decision-native architecture that jointly enforces null-awareness, permutation invariance, option scalability, and cross-request caching for structured decision-making.
Zhe Qian, Ziyang Gong, Zhongxing Xu +9 authors
LoopVL extends Loop Transformers to vision-language modeling by iteratively updating a shared multimodal state, improving reasoning and revealing dynamic visual attention shifts.
Luozheng Qin, Yuhan Zhu, Changhai Zhou +9 authors
MJev-Spatial is a fast multimodal decision model that unifies spatial reasoning tasks into a single-pass classification framework, improving speed and accuracy over autoregressive vision-language models.
Weijie Wang, Haomin Zhang, Ye Li +7 authors
ATAS improves long-form video consistency by compiling screenplays into referenced shot requests, retrieving spatial and temporal evidence from scene and event memories, and conditionally updating memory after generation.
Mingyu Ouyang, Yiran Wang, Siyuan Hu +9 authors
Player-1 improves game control by combining supervised fine-tuning on gameplay trajectories with reinforcement learning across synthetic environments, achieving substantial gains over demonstration-only baselines.
Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15 authors
VideoJev converts video observations into structured decisions by scoring temporal intervals and text options, enabling efficient reusable inference for visual agents.
Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang +6 authors
DiffusionART improves reinforcement learning fine-tuning of diffusion models by removing hidden consistency forces and enabling stable, efficient training without EMA tuning or differentiable rewards.
Jiawei Chi, Shangchen Miao, Zhiyuan Shi +11 authors
AgentGarten couples simulators with a shared neural renderer to build real-time interactive virtual worlds, enabling agents to learn efficiently through inherited experience and adversarially distilled visual observations.
Arman Behnam, Sunglyoung Kim, Liangwei Yang
A benchmark of ten real long-term AI companion relationships reveals that past context is rarely needed, memory detectors fail on real messages, and persona reconstruction costs vary widely.
Zhiyuan Shi, Xiang Li, Xingzhuo Guo +8 authors
Multimodal language models use an intrinsic linear subspace called S-Space to encode object coordinates, supporting spatial perception, reasoning, and response generation, while also revealing bottlenecks in viewpoint transformation.
Zhuofan Josh Ying, Guanglong Sun, Nolan Ho +6 authors
Parameter-efficient fine-tuning with low-rank adapters enables efficient adaptation of very large multimodal backbones for brain encoding, improving performance and interpretability while reducing computational cost.
Dianqiao Lei, Kevin Qinghong Lin, Pan Lu +2 authors
Researchers propose multi-level metrics to evaluate LLM no-thinking behavior, finding that explicit reasoning persists despite controls and varies with task openness, establishing no-thinking as a distinct capability requiring systematic assessment.
Tianming Liang, Junyi Pan, Yuxi Li +5 authors
WeVisOne-VL unifies object-level and pixel-level visual perception via structured token prediction, supporting detection, localization, counting, OCR, segmentation, and matting with a lightweight pixel decoder and multi-stage training.
Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang +21 authors
OneStreamer uses proactive generation to build reusable video memory and respond promptly, achieving top performance on streaming video benchmarks.
Meijia Chen, Hao Li, Zheng Lu +12 authors
CrossFit mitigates co-cheating in self-evolving search agents by cross-fitting proposal scoring across partitioned sources, substantially reducing false agreement and improving benchmark performance.
Fang Wu, Da Xing, Yanjie Huang +16 authors
UniEvo-VL enables multimodal models to self-improve during inference by using internal critiques to guide diffusion-based generation without external teachers.
Xi Xiao, Tianchen Zhao, Youngeun Kim +10 authors
ReaLVR improves latent visual reasoning by supervising latent tokens with visual evidence and answer contrast, scaling robustly to 235B parameters.
Bingxi Hou, Guochao Jiang, Guofeng Quan +4 authors
Waypoint-OPD improves policy-shift distillation by gating endpoint shifts using directional agreement between early and late teacher policy changes, boosting reasoning performance with minimal overhead.
Guanting Dong, Xinyu Yang, Jiajie Jin +9 authors
Agent-Reflex trains interactive agents to reflect and recover from noisy tool feedback and user corrections through skill discovery, supervised fine-tuning, and on-policy optimization.
Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar
In controlled distillation experiments, rollout policy has limited impact compared to token-level KL direction and learning rate, with on-policy benefits depending on objective and hyperparameters.
Deyuan Liu, Yihao Hu, Jingxuan Zhang +13 authors
UltraText Bench evaluates dense visual text generation across bilingual scenes using structured references and a vision-language judge, revealing trade-offs between clarity, fidelity, and workload difficulty.
Jihai Zhang, Runjia Qian, Kaiqin Kong +15 authors
Matrix-Game 4.0 separates game logic from visual synthesis via an executable engine and autoregressive video renderer, achieving real-time interactive gameplay with low latency.
Xinhao Ji, Hui En Pang, Hao Li +12 authors
EgoXperience introduces a unified framework for joint reconstruction of camera motion, scene geometry, hands, and objects from egocentric video using automatically annotated large-scale data and a single-pass model.
Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi +9 authors
Prospective learning via Self-Retrospection Distillation uses hindsight experience to train foresight predictions, improving reinforcement learning when outcome rewards are uniform.
Jiaming Zhang, Xuan Wang, Fuyao Zhang +3 authors
A decoder-free, action-conditioned world model predicts next-screen representations to verify GUI transitions and detect hijacked screens with high accuracy and low latency.
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