11 papers
TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models
Yidong Wang, Yan Zhan, Ziteng Feng +16
Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-spe…
Toward Native Multimodal Modeling: A Roadmap
Siyu An, Junru Lu, Junnan Dong +18
Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders…
Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
Junxiang Wu, Zhiqiang Kou, Hongwei Zeng +7
Label Distribution Learning (LDL) models supervision as an instance-wise probability distribution, enabling fine-grained learning under inherent ambiguity, but its success relies o…
Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment
Wenzhe Xu, Biao Liu, Yiyang Sun +2
Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing meth…
Seed2Scale: A Self-Evolving Data Engine for Embodied AI via Small to Large Model Synergy and Multimodal Evaluation
Cong Tai, Zhaoyu Zheng, Haixu Long +12
Existing data generation methods suffer from exploration limits, embodiment gaps, and low signal-to-noise ratios, leading to performance degradation during self-iteration. To addre…
Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
Junming Yang, Ning Xu, Biao Liu +2
Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch…