We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration efficiency. Additionally, we introduce an adaptive-length Chain-of-Thought distillation approach for reasoning data generation. This approach dynamically optimizes reasoning chain lengths, thereby enhancing inference efficiency and preventing excessive reasoning overthinking. Empirical evaluations demonstrate that Skywork R1V, with only 38B parameters, delivers competitive performance, achieving a score of 69.0 on the MMMU benchmark and 67.5 on MathVista. Meanwhile, it maintains robust textual reasoning performance, evidenced by impressive scores of 72.0 on AIME and 94.0 on MATH500. The Skywork R1V model weights have been publicly released to promote openness and reproducibility.

Several papers have delved into the challenges of human-AI-robot co-learning and co-adaptation. It has been noted that the terminology used to describe this collaborative relationship in existing studies needs to be more consistent. For example, the prefix "co" is used interchangeably to represent both "collaborative" and "mutual," and the terms "co-learning" and "co-adaptation" are sometimes used interchangeably. However, they can reflect subtle differences in the focus of the studies. The current scoping review's primary research question (RQ1) aims to gather existing papers discussing this collaboration pattern and examine the terms researchers use to describe this human-agent relationship. Given the relative newness of this area of study, we are also keen on exploring the specific types of intelligent agents and task domains that have been considered in existing research (RQ2). This exploration is significant as it can shed light on the diversity of human-agent interactions, from one-time to continuous learning/adaptation scenarios. It can also help us understand the dynamics of human-agent interactions in different task domains, guiding our expectations towards research situated in dynamic, complex domains. Our third objective (RQ3) is to investigate the cognitive theories and frameworks that have been utilized in existing studies to measure human-agent co-learning and co-adaptation. This investigation is crucial as it can help us understand the theoretical underpinnings of human-agent collaboration and adaptation, and it can also guide us in identifying any new frameworks proposed specifically for this type of relationship.

Big Chinese tech companies appear to have turned off some AI functions to prevent cheating during the country's highly competitive university entrance exams. More than 13.3 million students are sitting the four-day gaokao exams, which began on Saturday and determine if and where students can secure a limited place at university. This year, students hoping to get some assistance from increasingly advanced AI tools have been stymied. In screenshots shared online, one Chinese user posted a photo of an exam question to Doubao, owned by TikTok's parent company, ByteDance. The app responded: "During the college entrance examination, according to relevant requirements, the question answering service will be suspended".

This work studies and develop projection-free algorithms for online learning with linear optimization oracles (a.k.a. Frank-Wolfe) for handling the constraint set. More precisely, this work (i) provides an improved (optimized) variant of an online Frank-Wolfe algorithm along with its conceptually simple potential-based proof, and (ii) shows how to leverage semidefinite programming to jointly design and analyze online Frank-Wolfe-type algorithms numerically in a variety of settings-that include the design of the variant (i). Based on the semidefinite technique, we conclude with strong numerical evidence suggesting that no pure online Frank-Wolfe algorithm within our model class can have a regret guarantee better than O(T^3/4) (T is the time horizon) without additional assumptions, that the current algorithms do not have optimal constants, that the algorithm benefits from similar anytime properties O(t^3/4) not requiring to know T in advance, and that multiple linear optimization rounds do not generally help to obtain better regret bounds.

Conformal prediction is widely used to equip black-box machine learning models with uncertainty quantification enjoying formal coverage guarantees. However, these guarantees typically break down in the presence of distribution shifts, where the data distribution at test time differs from the training (or calibration-time) distribution. In this work, we address subpopulation shifts, where the test environment exhibits an unknown and differing mixture of subpopulations compared to the calibration data. We propose new methods that provably adapt conformal prediction to such shifts, ensuring valid coverage without requiring explicit knowledge of subpopulation structure. Our algorithms scale to high-dimensional settings and perform effectively in realistic machine learning tasks. Extensive experiments on vision (with vision transformers) and language (with large language models) benchmarks demonstrate that our methods reliably maintain coverage and controls risk in scenarios where standard conformal prediction fails.

Although deep learning has demonstrated remarkable capabilities in learning from unstructured data, modern tree-based ensemble models remain superior in extracting relevant information and learning from structured datasets. While several efforts have been made to accelerate tree-based models, the inherent characteristics of the models pose significant challenges for conventional accelerators. Recent research leveraging content-addressable memory (CAM) offers a promising solution for accelerating tree-based models, yet existing designs suffer from excessive memory consumption and low utilization. This work addresses these challenges by introducing RETENTION, an end-to-end framework that significantly reduces CAM capacity requirement for tree-based model inference. We propose an iterative pruning algorithm with a novel pruning criterion tailored for bagging-based models (e.g., Random Forest), which minimizes model complexity while ensuring controlled accuracy degradation. Additionally, we present a tree mapping scheme that incorporates two innovative data placement strategies to alleviate the memory redundancy caused by the widespread use of don't care states in CAM. Experimental results show that implementing the tree mapping scheme alone achieves $1.46\times$ to $21.30 \times$ better space efficiency, while the full RETENTION framework yields $4.35\times$ to $207.12\times$ improvement with less than 3% accuracy loss. These results demonstrate that RETENTION is highly effective in reducing CAM capacity requirement, providing a resource-efficient direction for tree-based model acceleration.

Equilibrium Propagation (EP) is a learning algorithm for training Energy-based Models (EBMs) on static inputs which leverages the variational description of their fixed points. Extending EP to time-varying inputs is a challenging problem, as the variational description must apply to the entire system trajectory rather than just fixed points, and careful consideration of boundary conditions becomes essential. In this work, we present Generalized Lagrangian Equilibrium Propagation (GLEP), which extends the variational formulation of EP to time-varying inputs. We demonstrate that GLEP yields different learning algorithms depending on the boundary conditions of the system, many of which are impractical for implementation. We then show that Hamiltonian Echo Learning (HEL) -- which includes the recently proposed Recurrent HEL (RHEL) and the earlier known Hamiltonian Echo Backpropagation (HEB) algorithms -- can be derived as a special case of GLEP. Notably, HEL is the only instance of GLEP we found that inherits the properties that make EP a desirable alternative to backpropagation for hardware implementations: it operates in a "forward-only" manner (i.e. using the same system for both inference and learning), it scales efficiently (requiring only two or more passes through the system regardless of model size), and enables local learning.

Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear instructions, puzzlehunts require models to discover the underlying problem structure from multimodal evidence and iterative reasoning, mirroring real-world domains such as scientific discovery, exploratory data analysis, or investigative problem-solving. Despite recent progress in foundation models, their performance on such open-ended settings remains largely untested. In this paper, we introduce PuzzleWorld, a large-scale benchmark of 667 puzzlehunt-style problems designed to assess step-by-step, open-ended, and creative multimodal reasoning. Each puzzle is annotated with the final solution, detailed reasoning traces, and cognitive skill labels, enabling holistic benchmarking and fine-grained diagnostic analysis. Most state-of-the-art models achieve only 1-2% final answer accuracy, with the best model solving only 14% of puzzles and reaching 40% stepwise accuracy. To demonstrate the value of our reasoning annotations, we show that fine-tuning a small model on reasoning traces improves stepwise reasoning from 4% to 11%, while training on final answers alone degrades performance to near zero. Our error analysis reveals that current models exhibit myopic reasoning, are bottlenecked by the limitations of language-based inference, and lack sketching capabilities crucial for visual and spatial reasoning. We release PuzzleWorld at https://github.com/MIT-MI/PuzzleWorld to support future work on building more general, open-ended, and creative reasoning systems.

While the complexity of 21st-century demands has promoted pedagogical approaches to foster complex competencies, a persistent gap remains between in-class learning activities and individualized learning or assessment practices. To address this, studies have explored the use of AI-generated characters in learning and assessment. One attempt is scenario-based assessment (SBA), a technique that not only measures but also fosters the development of competencies throughout the assessment process. SBA introduces simulated agents to provide an authentic social-interactional context, allowing for the assessment of competency-based constructs while mitigating the unpredictability of real-life interactions. Recent advancements in multimodal AI, such as text-to-video technology, allow these agents to be enhanced into AI-generated characters. This mixed-method study investigates how learners perceive AI characters taking the role of mentor and teammates in an SBA mirroring the context of a collaborative science investigation. Specifically, we examined the Likert scale responses of 56 high schoolers regarding trust, social presence, and effectiveness. We analyzed the relationships between these factors and their impact on the intention to adopt AI characters through PLS-SEM. Our findings indicated that learners' trust shaped their sense of social presence with the AI characters, enhancing perceived effectiveness. Qualitative analysis further highlighted factors that foster trust, such as material credibility and alignment with learning goals, as well as the pivotal role of social presence in creating a collaborative context. This paper was accepted as an full paper for AIED 2025.

In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we tune a model by having it interact with a database engine? We frame this problem as a reinforcement learning problem where the model receives execution-based feedback from the environment in the form of scalar rewards. These rewards penalize execution failures and assign positive values when a query returns a correct answer. We use the rewards within the Group Relative Policy Optimization (GRPO) framework. We use a tabular reasoning benchmark to test and evaluate our findings. We find that with only weak supervision in the form of question-answer pairs, RL-tuning improves the accuracy of model generated SQL code from 31.49 to 49.83 while reducing error percentage from 25.43% to 14.71%. This improvement allowed the model nearly match the performance performance to the larger SQLCoder-70B model. Our work demonstrates the potential of using execution-based feedback to improve symbolic reasoning capabilities of LLMs.