热点
"空间推理" 相关文章
SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
cs.AI updates on arXiv.org 2025-11-05T05:17:11.000000Z
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
cs.AI updates on arXiv.org 2025-11-05T05:14:24.000000Z
GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation
cs.AI updates on arXiv.org 2025-10-28T04:13:44.000000Z
Mitigating Coordinate Prediction Bias from Positional Encoding Failures
cs.AI updates on arXiv.org 2025-10-28T04:12:48.000000Z
Stuck in the Matrix: Probing Spatial Reasoning in Large Language Models
cs.AI updates on arXiv.org 2025-10-24T04:23:49.000000Z
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
机器之心 2025-10-21T08:56:11.000000Z
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
机器之心 2025-10-21T06:37:48.000000Z
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
机器之心 2025-10-21T06:37:48.000000Z
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
机器之心 2025-10-21T06:37:48.000000Z
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
机器之心 2025-10-21T06:37:48.000000Z
From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
cs.AI updates on arXiv.org 2025-10-21T04:28:24.000000Z
Pursuing Minimal Sufficiency in Spatial Reasoning
cs.AI updates on arXiv.org 2025-10-21T04:26:58.000000Z
Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models
cs.AI updates on arXiv.org 2025-10-20T04:10:18.000000Z
Agentic Design of Compositional Machines
cs.AI updates on arXiv.org 2025-10-17T04:11:14.000000Z
Agentic Design of Compositional Machines
cs.AI updates on arXiv.org 2025-10-17T04:11:14.000000Z
景不动人动，MLLM如何面对「移步换景」的真实世界？OST-Bench揭示多模态大模型在线时空理解短板
机器之心 2025-10-14T06:54:22.000000Z
景不动人动，MLLM如何面对「移步换景」的真实世界？OST-Bench揭示多模态大模型在线时空理解短板
机器之心 2025-10-14T06:54:22.000000Z
永别了，人类冠军！AI横扫天文奥赛，GPT-5得分远超金牌选手2.7倍
智源社区 2025-10-13T10:14:01.000000Z
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
cs.AI updates on arXiv.org 2025-10-10T04:19:16.000000Z
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
cs.AI updates on arXiv.org 2025-10-10T04:19:16.000000Z