Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs).However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently diverse and heterogeneous human preferences.Hence, such oversimplification limits LLMs from supporting personalization and pluralistic alignment.Theoretically, we show that when human preferences follow a mixture distribution of diverse subgroups, a single BT model has an irreducible error.While existing solutions, such as multi-objective learning with finegrained annotations, help address this issue, they are costly and constrained by predefined attributes, failing to fully capture the richness of human values.In this work, we introduce MiCRo, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations.In the first stage, MiCRo introduces context-aware mixture modeling approach to capture diverse human preferences.In the second stage, Mi-CRo integrates an online routing strategy that dynamically adapts mixture weights based on specific context to resolve ambiguity, allowing for efficient and scalable preference adaptation with minimal additional supervision.Experiments on multiple preference datasets demonstrate that MiCRo effectively captures diverse human preferences and significantly improves downstream personalization.

Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or humans often contains noise and errors, posing a significant challenge for existing offline RL methods, particularly when the real-world data is limited. Our study reveals that prior research focusing on adapting predominant offline RL methods based on temporal difference learning still falls short under data corruption when the dataset is limited. In contrast, we discover that vanilla sequence modeling methods, such as Decision Transformer, exhibit robustness against data corruption, even without specialized modifications. To unlock the full potential of sequence modeling, we propose **R**obust **D**ecision **T**ransformer (**RDT**) by incorporating three simple yet effective robust techniques: embedding dropout to improve the model's robustness against erroneous inputs, Gaussian weighted learning to mitigate the effects of corrupted labels, and iterative data correction to eliminate corrupted data from the source. Extensive experiments on MuJoCo, Kitchen, and Adroit tasks demonstrate RDT's superior performance under various data corruption scenarios compared to prior methods. Furthermore, RDT exhibits remarkable robustness in a more challenging setting that combines training-time data corruption with test-time observation perturbations. These results highlight the potential of sequence modeling for learning from noisy or corrupted offline datasets, thereby promoting the reliable application of offline RL in real-world scenarios. Our code is available at https://github.com/jiawei415/RobustDecisionTransformer。

We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation models using reinforcement learning (RL), and the multi-dimensionality, heterogeneity, and conflicting nature of human preferences further complicate the alignment process. In this paper, we introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context and applies supervised fine-tuning for alignment. The salient features of RiC are simplicity and adaptivity, as it only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time. Inspired by the analytical solution of an abstracted convex optimization problem, our dynamic inference-time adjustment method approaches the Pareto-optimal solution for multiple objectives. Empirical evidence demonstrates the efficacy of our method in aligning both Large Language Models (LLMs) and diffusion models to accommodate diverse rewards with only around 10% GPU hours compared with multi-objective RL baseline.

In multi-goal reinforcement learning (RL), efficient learning from sparse rewards remains a major challenge. One of the most successful solutions to the challenge is Hindsight Experience Replay (HER), a model-free algorithm that relabels desired goals with achieved goals. However, HER and its previous variants are still limited in efficiency and require millions of samples for training. In this paper, leveraging the power of a learned dynamics model, we propose Hindsight Experience Replay with Model-based Prediction (HERO) to further improve the sample efficiency of HER. The core technique of HERO is a two-stage value estimation algorithm combining hindsight relabeled rewards and model-based predictive rewards. To effectively model complex dynamics of robot manipulation tasks, we introduce the goal-enhanced predictive model (GPM) and the achieved-goal variance prioritization (AVP). GPM pays more attention to predicting the achieved goal in the next state, while AVP prioritizes trajectories based on the variance of achieved goals in each trajectory. In our experiments, we evaluate HERO on a set of challenging robot manipulation tasks. Empirical results demonstrate that HERO achieves significantly higher sample efficiency than previous multi-goal RL algorithms.

Boundary-based instance segmentation has drawn much attention since of its attractive efficiency. However, existing methods suffer from the difficulty in long-distance regression. In this paper, we propose a coarse-to-fine module to address the problem. Approximate boundary points are generated at the coarse stage and then features of these points are sampled and fed to a refined regressor for fine prediction. It is end-to-end trainable since differential sampling operation is well supported in the module. Furthermore, we design a holistic boundary-aware branch and introduce instance-agnostic supervision to assist regression. Equipped with ResNet-101, our approach achieves 31.7% mask AP on COCO dataset with single-scale training and testing, outperforming the baseline 1.3% mask AP with less than 1% additional parameters and GFLOPs. Experiments also show that our proposed method achieves competitive performance compared to existing boundary-based methods with a lightweight design and a simple pipeline.