会员服务
VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
Arxiv
0+阅读 · 4月21日
Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning
Arxiv
0+阅读 · 4月6日
RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
Arxiv
0+阅读 · 5月4日
Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval
Arxiv
0+阅读 · 4月1日
SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression
Arxiv
0+阅读 · 4月20日
Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
Arxiv
0+阅读 · 4月2日
Hydra: Unifying Document Retrieval and Generation in a Single Vision-Language Model
Arxiv
0+阅读 · 4月19日
How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
Arxiv
0+阅读 · 4月30日
Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Arxiv
0+阅读 · 4月13日
EngGPT2: Sovereign, Efficient and Open Intelligence
Arxiv
0+阅读 · 3月17日
SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans
Arxiv
0+阅读 · 3月9日
On-Policy Self-Distillation for Reasoning Compression
Arxiv
0+阅读 · 3月5日
Naver Labs Europe @ WSDM CUP | Multilingual Retrieval
Arxiv
0+阅读 · 2月24日
DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning
Arxiv
0+阅读 · 2月11日
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
Arxiv
0+阅读 · 2月8日
参考链接
微信扫码咨询专知VIP会员
Top