Providing students with detailed and timely grading feedback is essential for self-learning. While existing LLM-based grading systems are promising, most of them rely on one single model, which limits their performance. To address this, we propose Ensemble Tree-of-Thought (ToT), a framework that enhances LLM outputs by integrating multiple models. Using this framework, we develop a grading system. Ensemble ToT follows three steps: (1) analyzing LLM performance, (2) generating candidate answers, and (3) refining them into a final result. Based on this, our grading system first evaluates the grading tendencies of LLMs, then generates multiple results, and finally integrates them via a simulated debate. Experimental results demonstrate our approach's ability to provide accurate and explainable grading by effectively coordinating multiple LLMs.

-- As robots are increasingly deployed in diverse application domains, generalizable cross-embodiment mobility policies are increasingly essential. While classical mobility stacks have proven effective on specific robot platforms, they pose significant challenges when scaling to new embodiments. Learning-based methods, such as imitation learning (IL) and reinforcement learning (RL), offer alternative solutions but suffer from covariate shift, sparse sampling in large environments, and embodiment-specific constraints. This paper introduces COMPASS, a novel workflow for developing cross-embodiment mobility policies by integrating IL, residual RL, and policy distillation. We begin with IL on a mobile robot, leveraging easily accessible teacher policies to train a foundational model that combines a world model with a mobility policy. Building on this base, we employ residual RL to fine-tune embodiment-specific policies, exploiting pre-trained representations to improve sampling efficiency in handling various physical constraints and sensor modalities. We empirically demonstrate that COMPASS scales effectively across diverse robot platforms while maintaining adaptability to various environment configurations, achieving a generalist policy with a success rate approximately 5X higher than the pre-trained IL policy. The resulting framework offers an efficient, scalable solution for cross-embodiment mobility, enabling robots with different designs to navigate safely and efficiently in complex scenarios.

Large Language Models (LLMs) are revolutionizing information retrieval, with chatbots becoming an important source for answering user queries. As by their design, LLMs prioritize generating correct answers, the value of highly plausible yet incorrect answers (candidate answers) tends to be overlooked. However, such answers can still prove useful, for example, they can play a crucial role in tasks like Multiple-Choice Question Answering (MCQA) and QA Robustness Assessment (QARA). Existing QA datasets primarily focus on correct answers without explicit consideration of the plausibility of other candidate answers, limiting opportunity for more nuanced evaluations of models. To address this gap, we introduce PlausibleQA, a large-scale dataset comprising 10,000 questions and 100,000 candidate answers, each annotated with plausibility scores and justifications for their selection. Additionally, the dataset includes 900,000 justifications for pairwise comparisons between candidate answers, further refining plausibility assessments. We evaluate PlausibleQA through human assessments and empirical experiments, demonstrating its utility in MCQA and QARA analysis. Our findings show that plausibility-aware approaches are effective for MCQA distractor generation and QARA. We release PlausibleQA as a resource for advancing QA research and enhancing LLM performance in distinguishing plausible distractors from correct answers.

To compare autoregressive language models at scale, we propose using log-likelihood vectors computed on a predefined text set as model features. This approach has a solid theoretical basis: when treated as model coordinates, their squared Euclidean distance approximates the Kullback-Leibler divergence of text-generation probabilities. Our method is highly scalable, with computational cost growing linearly in both the number of models and text samples, and is easy to implement as the required features are derived from cross-entropy loss. Applying this method to over 1,000 language models, we constructed a "model map," providing a new perspective on large-scale model analysis.

Target tracking entails the estimation of the evolution of the target state over time, namely the target trajectory. Different from the classical state space model, our series of studies, including this paper, model the collection of the target state as a stochastic process (SP) that is further decomposed into a deterministic part which represents the trend of the trajectory and a residual SP representing the residual fitting error. Subsequently, the tracking problem is formulated as a learning problem regarding the trajectory SP for which a key part is to estimate a trajectory FoT (T-FoT) best fitting the measurements in time series. For this purpose, we consider the polynomial T-FoT and address the regularized polynomial T-FoT optimization employing two distinct regularization strategies seeking trade-off between the accuracy and simplicity. One limits the order of the polynomial and then the best choice is determined by grid searching in a narrow, bounded range while the other adopts $\ell_0$ norm regularization for which the hybrid Newton solver is employed. Simulation results obtained in both single and multiple maneuvering target scenarios demonstrate the effectiveness of our approaches.

-- The complex structure of musculoskeletal humanoids makes it difficult to model them, and the inter-body interference and high internal muscle force are unavoidable. Although various safety mechanisms have been developed to solve this problem, it is important not only to deal with the dangers when they occur but also to prevent them from happening. In this study, we propose a method to learn a network outputting danger probability corresponding to the muscle length online so that the robot can gradually prevent dangers from occurring. Applications of this network for control are also described. The method is applied to the musculoskeletal humanoid, Musashi, and its effectiveness is verified. I. INTRODUCTION The musculoskeletal humanoid [1]-[4] has various biomimetic advantages such as variable stiffness using redundant muscles, spherical joints without singular points, underactuated and flexible fingers, etc. At the same time, its complex musculoskeletal structure is difficult to model and various learning control methods have been developed [5]- [8].

A major step toward Artificial General Intelligence (AGI) and Super Intelligence is AI's ability to autonomously conduct research - what we term Artificial Research Intelligence (ARI). If machines could generate hypotheses, conduct experiments, and write research papers without human intervention, it would transform science. Sakana recently introduced the 'AI Scientist', claiming to conduct research autonomously, i.e. they imply to have achieved what we term Artificial Research Intelligence (ARI). The AI Scientist gained much attention, but a thorough independent evaluation has yet to be conducted. Our evaluation of the AI Scientist reveals critical shortcomings. The system's literature reviews produced poor novelty assessments, often misclassifying established concepts (e.g., micro-batching for stochastic gradient descent) as novel. It also struggles with experiment execution: 42% of experiments failed due to coding errors, while others produced flawed or misleading results. Code modifications were minimal, averaging 8% more characters per iteration, suggesting limited adaptability. Generated manuscripts were poorly substantiated, with a median of five citations, most outdated (only five of 34 from 2020 or later). Structural errors were frequent, including missing figures, repeated sections, and placeholder text like 'Conclusions Here'. Some papers contained hallucinated numerical results. Despite these flaws, the AI Scientist represents a leap forward in research automation. It generates full research manuscripts with minimal human input, challenging expectations of AI-driven science. Many reviewers might struggle to distinguish its work from human researchers. While its quality resembles a rushed undergraduate paper, its speed and cost efficiency are unprecedented, producing a full paper for USD 6 to 15 with 3.5 hours of human involvement, far outpacing traditional researchers.

Online learning is a model of machine learning where the learner is trained on sequential feedback. We investigate worst-case error for the online learning of real functions that have certain smoothness constraints. Suppose that $\mathcal{F}_q$ is the class of all absolutely continuous functions $f: [0, 1] \rightarrow \mathbb{R}$ such that $\|f'\|_q \le 1$, and $\operatorname{opt}_p(\mathcal{F}_q)$ is the best possible upper bound on the sum of the $p^{\text{th}}$ powers of absolute prediction errors for any number of trials guaranteed by any learner. We show that for any $\delta, \epsilon \in (0, 1)$, $\operatorname{opt}_{1+\delta} (\mathcal{F}_{1+\epsilon}) = O(\min(\delta, \epsilon)^{-1})$. Combined with the previous results of Kimber and Long (1995) and Geneson and Zhou (2023), we achieve a complete characterization of the values of $p, q \ge 1$ that result in $\operatorname{opt}_p(\mathcal{F}_q)$ being finite, a problem open for nearly 30 years. We study the learning scenarios of smooth functions that also belong to certain special families of functions, such as polynomials. We prove a conjecture by Geneson and Zhou (2023) that it is not any easier to learn a polynomial in $\mathcal{F}_q$ than it is to learn any general function in $\mathcal{F}_q$. We also define a noisy model for the online learning of smooth functions, where the learner may receive incorrect feedback up to $\eta \ge 1$ times, denoting the worst-case error bound as $\operatorname{opt}^{\text{nf}}_{p, \eta} (\mathcal{F}_q)$. We prove that $\operatorname{opt}^{\text{nf}}_{p, \eta} (\mathcal{F}_q)$ is finite if and only if $\operatorname{opt}_p(\mathcal{F}_q)$ is. Moreover, we prove for all $p, q \ge 2$ and $\eta \ge 1$ that $\operatorname{opt}^{\text{nf}}_{p, \eta} (\mathcal{F}_q) = \Theta (\eta)$.

We revisit the problem of fair representation learning by proposing Fair Partial Least Squares (PLS) components. PLS is widely used in statistics to efficiently reduce the dimension of the data by providing representation tailored for the prediction. We propose a novel method to incorporate fairness constraints in the construction of PLS components. This new algorithm provides a feasible way to construct such features both in the linear and the non linear case using kernel embeddings. The efficiency of our method is evaluated on different datasets, and we prove its superiority with respect to standard fair PCA method.

The California Legislative Black Caucus on Thursday proposed a package of reparations for the descendants of African Americans who were enslaved in the United States, proposals that include preferences for public university admissions and financial assistance for first-time home buyers. The package contains 15 bills in what caucus members said will be a multiyear effort to repair the generational harms and discrimination suffered by the descendants of slaves in California. In 2020, Gov. Gavin Newsom and California lawmakers formed a "first in the nation" state task force to study and propose remedies for the legacy of slavery. During the end of the legislative session last year, reform advocates were frustrated that the legislature, which was limited by a tight state budget and a high-stakes election year, passed only 10 of the 14 bills prioritized by the Legislative Black Caucus. "We are picking up where we left off last year," said Assemblymember Lori Wilson (D-Suisun City) at a press conference Thursday morning.