会员服务
KLong: Training LLM Agent for Extremely Long-horizon Tasks
KLong: Training LLM Agent for Extremely Long-horizon Tasks
Arxiv
0+阅读 · 2月19日
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
Arxiv
0+阅读 · 2月17日
Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
Arxiv
0+阅读 · 2月12日
Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
Arxiv
0+阅读 · 2月10日
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Arxiv
0+阅读 · 2月11日
Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority
Arxiv
0+阅读 · 2月9日
SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
Arxiv
0+阅读 · 2月7日
Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
Arxiv
0+阅读 · 2月16日
Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
Arxiv
0+阅读 · 2月16日
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Arxiv
0+阅读 · 2月8日
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
Arxiv
0+阅读 · 2月3日
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Arxiv
0+阅读 · 2月2日
Exploring Fine-Tuning for Tabular Foundation Models
Arxiv
0+阅读 · 1月14日
Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation
Arxiv
0+阅读 · 1月16日
Mechanisms are Transferable: Data-Efficient Low-Resource Adaptation via Circuit-Targeted Supervised Fine-Tuning
Arxiv
0+阅读 · 1月19日
参考链接
微信扫码咨询专知VIP会员
Top