When fine-tuning language models on new tasks, catastrophic forgetting -- performance degradation on previously-learned tasks -- is a ubiquitous problem. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA address this through low-rank adapters, sparse adaptation offers an alternative that doesn't impose rank constraints. We introduce Random Initialization of Gated Sparse Adapters (RIGSA), which starts from randomly-initialized full-rank adapters, gates them with a ReZero analog, and sparsifies them with iterative magnitude pruning. We evaluate RIGSA on SmolLM2-1.7B-Instruct using a novel vision-in-text task (Textual MNIST) and measure forgetting on PIQA, HellaSwag, and GSM8k. SmolLM2-1.7B-Instruct initially performs around chance level on Textual MNIST, and is capable of learning the task through RIGSA, 4-bit QLoRA and random masking. In spite of having more trainable parameters than QLoRA, the RIGSA configurations that we studied displayed less forgetting than QLoRA, particularly on GSM8k, though it performs comparably to random masking.

Data scarcity remains a fundamental bottleneck for embodied intelligence. Existing approaches use large language models (LLMs) to automate gripper-based simulation generation, but they transfer poorly to dexterous manipulation, which demands more specialized environment design. Meanwhile, dexterous manipulation tasks are inherently more difficult due to their higher degrees of freedom. Massively generating feasible and trainable dexterous hand tasks remains an open challenge. To this end, we present GenDexHand, a generative simulation pipeline that autonomously produces diverse robotic tasks and environments for dexterous manipulation. GenDexHand introduces a closed-loop refinement process that adjusts object placements and scales based on vision-language model (VLM) feedback, substantially improving the average quality of generated environments. Each task is further decomposed into sub-tasks to enable sequential reinforcement learning, reducing training time and increasing success rates. Our work provides a viable path toward scalable training of diverse dexterous hand behaviors in embodied intelligence by offering a simulation-based solution to synthetic data generation. Our website: https://winniechen2002.github.io/GenDexHand/.

Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics. The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a response, making reinforcement learning (RL) post-training with rubric-based rewards difficult to scale. This problem is exacerbated by the fact that often the best way to combine these rubrics into one single reward is also highly prompt-specific. We propose Reinforcement Learning with Adversarial Critic (RLAC), a post-training approach that addresses these challenges via dynamic rubric verification. Our approach employs a large language model (LLM) as a critic that dynamically identifies only the most likely failure modes (e.g., a factual error or unhandled edge case), which are then verified by an external validator to optimize both generator and critic jointly. By training both the generator and the critic, this game enhances the critic's error detection and the generator's output quality while reducing required verifications. Our experiments demonstrate that RLAC improves factual accuracy in text generation and correctness in code generation, while also outperforming exhaustive verification and reward model methods. We show that dynamic critics are more effective than fixed critics, showcasing the potential of RLAC for scaling RL post-training to free-form generation tasks.

The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These all affect interaction quality, perceived intelligence, and alignment with both developer and user intentions. The shaping of this persona, known as character training, is a critical component of industry post-training, yet remains effectively unstudied in the academic literature. We introduce the first open implementation of character training, leveraging Constitutional AI and a new data pipeline using synthetic introspective data to shape the assistant persona in a more effective and controlled manner than alternatives such as constraining system prompts or activation steering. Specifically, we fine-tune three popular open-weights models using 11 example personas, such as humorous, deeply caring, or even malevolent. To track the effects of our approach, we introduce a method which analyzes revealed preferences, uncovering clear and holistic changes in character. We find these changes are more robust to adversarial prompting than the above two alternatives, while also leading to more coherent and realistic generations. Finally, we demonstrate this fine-tuning has little to no effect on general capabilities as measured by common benchmarks. We describe and open-source our full post-training method, the implementation of which can be found at https://github.com/maiush/OpenCharacterTraining.

Spin plays a fundamental role in understanding electronic structure, yet many real-space wavefunction methods fail to adequately consider it. We introduce the Spin-Adapted Antisymmetrization Method (SAAM), a general procedure that enforces exact total spin symmetry for antisymmetric many-electron wavefunctions in real space. In the context of neural network-based quantum Monte Carlo (NNQMC), SAAM leverages the expressiveness of deep neural networks to capture electron correlation while enforcing exact spin adaptation via group representation theory. This framework provides a principled route to embed physical priors into otherwise black-box neural network wavefunctions, yielding a compact representation of correlated system with neural network orbitals. Compared with existing treatments of spin in NNQMC, SAAM is more accurate and efficient, achieving exact spin purity without any additional tunable hyperparameters. To demonstrate its effectiveness, we apply SAAM to study the spin ladder of iron-sulfur clusters, a long-standing challenge for many-body methods due to their dense spectrum of nearly degenerate spin states. Our results reveal accurate resolution of low-lying spin states and spin gaps in [Fe$_2$S$_2$] and [Fe$_4$S$_4$] clusters, offering new insights into their electronic structures. In sum, these findings establish SAAM as a robust, hyperparameter-free standard for spin-adapted NNQMC, particularly for strongly correlated systems.

While generative models for music composition are increasingly capable, their adoption by musicians is hindered by text-prompting, an asynchronous workflow disconnected from the embodied, responsive nature of instrumental performance. To address this, we introduce Aria-Duet, an interactive system facilitating a real-time musical duet between a human pianist and Aria, a state-of-the-art generative model, using a Yamaha Disklavier as a shared physical interface. The framework enables a turn-taking collaboration: the user performs, signals a handover, and the model generates a coherent continuation performed acoustically on the piano. Beyond describing the technical architecture enabling this low-latency interaction, we analyze the system's output from a musicological perspective, finding the model can maintain stylistic semantics and develop coherent phrasal ideas, demonstrating that such embodied systems can engage in musically sophisticated dialogue and open a promising new path for human-AI co-creation.

ABSTRACT Design/methodology/approach This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge. The framework integrates Bloom's Taxonomy with Retrieval - Augmented Generation (RAG) to assess model perform ance across six hierarchical cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM - generated responses' sem antic accuracy and cultural relevance. Purpose This research evaluates how effectively LLMs represent and generate minority cultural knowledge, specifically Taiwanese Hakka culture. To address this, the study proposes a structured and replicable evaluation framework integrating Bloom's Taxonomy and RAG . The research is guided by the following questions: (1) How do LLMs perform across different cognitive domains when processing Hakka ...

In this work, we investigate the use of Large Language Models (LLMs) within a graph-based Retrieval Augmented Generation (RAG) architecture for Energy Efficiency (EE) Question Answering. First, the system automatically extracts a Knowledge Graph (KG) from guidance and regulatory documents in the energy field. Then, the generated graph is navigated and reasoned upon to provide users with accurate answers in multiple languages. We implement a human-based validation using the RAGAs framework properties, a validation dataset comprising 101 question-answer pairs, and domain experts. Results confirm the potential of this architecture and identify its strengths and weaknesses. Validation results show how the system correctly answers in about three out of four of the cases (75.2 +- 2.7%), with higher results on questions related to more general EE answers (up to 81.0 +- 4.1%), and featuring promising multilingual abilities (4.4% accuracy loss due to translation).

Global food trade plays a crucial role in ensuring food security and maintaining supply chain stability. However, its network structure evolves dynamically under the influence of geopolitical, economic, and environmental factors, making it challenging to model and predict future trade links. Effectively capturing temporal patterns in food trade networks is therefore essential for improving the accuracy and robustness of link prediction. This study introduces IVGAE-TAMA-BO, a novel dynamic graph neural network designed to model evolving trade structures and predict future links in global food trade networks. To the best of our knowledge, this is the first work to apply dynamic graph neural networks to this domain, significantly enhancing predictive performance. Building upon the original IVGAE framework, the proposed model incorporates a Trade-Aware Momentum Aggregator (TAMA) to capture the temporal evolution of trade networks, jointly modeling short-term fluctuations and long-term structural dependencies. A momentum-based structural memory mechanism further improves predictive stability and performance. In addition, Bayesian optimization is used to automatically tune key hyperparameters, enhancing generalization across diverse trade scenarios. Extensive experiments on five crop-specific datasets demonstrate that IVGAE-TAMA substantially outperforms the static IVGAE and other dynamic baselines by effectively modeling temporal dependencies, while Bayesian optimization further boosts performance in IVGAE-TAMA-BO. These results highlight the proposed framework as a robust and scalable solution for structural prediction in global trade networks, with strong potential for applications in food security monitoring and policy decision support.

Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT system co-designed with an optimized LLM serving architecture. GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption. To scale inference, we introduce a Graph-CoT-aware LLM inference mechanism with graph-specific KV-cache management, priority-based eviction, and pipelined execution to improve serving efficiency. Experiments demonstrate that GLM improves answer accuracy by up to 38%, reduces token cost by up to 95.7%, lowers inference latency by 90.3%, and achieves up to 15.1x higher throughput compared to state-of-the-art Graph-CoT baselines, enabling efficient adoption for complex real-world reasoning at scale.