A.1 Proof of Proposition 12 Proposition 1 The historical contrastive instance discrimination (HCID) can be modelled as a3 maximum likelihood problem optimized via Expectation Maximization.4 Maximum likelihood (ML) is a concept to describe the theoretic insights of clustering algorithms.6 PN n=1 Z(kn) = 1), and the last step of derivation13 employs Jensen's inequality [6, 7, 4]. Z(kn) log p(xq,kn; θE) (5) Expectation step focuses on estimating the posterior probability p(kn; xq,θE). We first gener-17 ate keys by a historical encoder: kt mn = Et m(xt), and xt Xtgt. Then, We calculate18 p(kn; xq,θE) = p(kt mn; xq,θE) = 1 (xq,kt mn), where 1 (xq,kt mn) = 1 if both belong to the19 positive pair; otherwise, 1 (xq,kt mn) = 0.20 Please note the notation "t m" shows that the k is encoded by a historical encoder.21

Presenting users with diverse responses from foundation models is crucial for enhancing user experience and accommodating varying preferences. However, generating multiple high-quality and diverse responses without sacrificing accuracy remains a challenge, especially when using greedy sampling. In this work, we propose a novel framework, Synthesize-Partition-Adapt (SP A), that leverages the abundant synthetic data available in many domains to elicit diverse responses from foundation models. By leveraging signal provided by data attribution methods such as influence function, SP A partitions data into subsets, each targeting unique aspects of the data, and trains multiple model adaptations optimized for these subsets. Experimental results demonstrate the effectiveness of our approach in diversifying foundation model responses while maintaining high quality, showcased through the HumanEval and MBPP tasks in the code generation domain and several tasks in the natural language understanding domain, highlighting its potential to enrich user experience across various applications.

In recent years, model-free reinforcement learning (MFRL) has achieved tremendous success on a wide range of simulated domains, e .

Q1: ...the claim that the algorithm really manages to align the latent distributions of real and simulated data... We will revise the inappropriate statements in the final version. Q2: In the model adaptation phase, are state-action pairs simply sampled randomly from their respective buffers? Do you have results for a single, monolithic model? Q4: Did you investigate the reasons for the slow learning in the 500 steps on InvertedPendulum compared to PETS? Q1: The experiments shown in Figure 2 do not outperform MBPO beyond the confidence bounds.

Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled target domain, but it requires to access the source data which often raises concerns in data privacy, data portability and data transmission efficiency. We study unsupervised model adaptation (UMA), or called Unsupervised Domain Adaptation without Source Data, an alternative setting that aims to adapt source-trained models towards target distributions without accessing source data. To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA. HCL addresses the UMA challenge from two perspectives. First, it introduces historical contrastive instance discrimination (HCID) that learns from target samples by contrasting their embeddings which are generated by the currently adapted model and the historical models. With the historical models, HCID encourages UMA to learn instance-discriminative target representations while preserving the source hypothesis. Second, it introduces historical contrastive category discrimination (HCCD) that pseudo-labels target samples to learn category-discriminative target representations.

Organizations are rapidly adopting Large Language Models (LLMs) to transform their operations, yet they lack clear guidance on key decisions for adoption and implementation. While LLMs offer powerful capabilities in content generation, assisted coding, and process automation, businesses face critical challenges in data security, LLM solution development approach, infrastructure requirements, and deployment strategies. Healthcare providers must protect patient data while leveraging LLMs for medical analysis, financial institutions need to balance automated customer service with regulatory compliance, and software companies seek to enhance development productivity while maintaining code security. This article presents a systematic six-step decision framework for LLM adoption, helping organizations navigate from initial application selection to final deployment. Based on extensive interviews and analysis of successful and failed implementations, our framework provides practical guidance for business leaders to align technological capabilities with business objectives. Through key decision points and real-world examples from both B2B and B2C contexts, organizations can make informed decisions about LLM adoption while ensuring secure and efficient integration across various use cases, from customer service automation to content creation and advanced analytics.

Planetary exploration missions require robots capable of navigating extreme and unknown environments. While wheeled rovers have dominated past missions, their mobility is limited to traversable surfaces. Legged robots, especially quadrupeds, can overcome these limitations by handling uneven, obstacle-rich, and deformable terrains. However, deploying such robots in unknown conditions is challenging due to the need for environment-specific control, which is infeasible when terrain and robot parameters are uncertain. This work presents a modular control framework that combines model-based dynamic control with online model adaptation and adaptive footstep planning to address uncertainties in both robot and terrain properties. The framework includes state estimation for quadrupeds with and without contact sensing, supports runtime reconfiguration, and is integrated into ROS 2 with open-source availability. Its performance was validated on two quadruped platforms, multiple hardware architectures, and in a volcano field test, where the robot walked over 700 m.

Presenting users with diverse responses from foundation models is crucial for enhancing user experience and accommodating varying preferences. However, generating multiple high-quality and diverse responses without sacrificing accuracy remains a challenge, especially when using greedy sampling. In this work, we propose a novel framework, Synthesize-Partition-Adapt (SP A), that leverages the abundant synthetic data available in many domains to elicit diverse responses from foundation models. By leveraging signal provided by data attribution methods such as influence function, SP A partitions data into subsets, each targeting unique aspects of the data, and trains multiple model adaptations optimized for these subsets. Experimental results demonstrate the effectiveness of our approach in diversifying foundation model responses while maintaining high quality, showcased through the HumanEval and MBPP tasks in the code generation domain and several tasks in the natural language understanding domain, highlighting its potential to enrich user experience across various applications.