会员服务
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
Arxiv
0+阅读 · 10月31日
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
Arxiv
0+阅读 · 10月31日
CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
Arxiv
0+阅读 · 10月31日
ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning
ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learning
Arxiv
0+阅读 · 10月31日
Who Made This? Fake Detection and Source Attribution with Diffusion Features
Who Made This? Fake Detection and Source Attribution with Diffusion Features
Arxiv
0+阅读 · 10月31日
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
Arxiv
0+阅读 · 10月31日
HyperClick: Advancing Reliable GUI Grounding via Uncertainty Calibration
HyperClick: Advancing Reliable GUI Grounding via Uncertainty Calibration
Arxiv
0+阅读 · 10月31日
Supervised Quadratic Feature Analysis: Information Geometry Approach for Dimensionality Reduction
Arxiv
0+阅读 · 10月31日
MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
Arxiv
0+阅读 · 10月30日
Language-guided Open-world Video Anomaly Detection under Weak Supervision
Arxiv
0+阅读 · 10月30日
Similarity-Distance-Magnitude Language Models
Arxiv
0+阅读 · 10月30日
Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality
Arxiv
0+阅读 · 10月30日
KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA
Arxiv
0+阅读 · 10月29日
Zero Reinforcement Learning Towards General Domains
Arxiv
0+阅读 · 10月29日
Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks
Arxiv
0+阅读 · 10月29日
参考链接
微信扫码咨询专知VIP会员
Top