7 papers
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation
Yutong Hu, Fengjiao Chen, Xuezhi Cao +1
Long-horizon robot manipulation requires memory, but not necessarily inside the action policy. To address such tasks, current agentic systems often combine VLAs with planners and g…
Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
Jiacheng Xu, Feng Chen, Xiuneng Xu +1
Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down…
Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations
Jie Zhu, Huaixia Dou, Junhui Li +5
Emotional Support Conversation (ESC) aims to assist individuals experiencing distress by generating empathetic and supportive dialogue. While prior work typically assumes that each…
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
Dujun Nie, Fengjiao Chen, Qi Lv +4
While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source. A critical challenge in utili…
AgentOCR: Reimagining Agent History via Optical Self-Compression
Lang Feng, Fuchao Yang, Feng Chen +5
Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction, but practical deployment is bottlenecke…
Training Diffusion Policies via Prior-Mapping Co-Evolution
Chubin Zhang, Zhenglin Wan, Feng Chen +7
Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions…