activity
20242026
collaborators

11 papers

cs.AI2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.RO2026

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…

cs.CL2026

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…