Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention mechanisms effectively capture dynamic contextual dependencies, but their reliance on learned weight distributions limits the preservation of long-range hierarchical structures in generated sequences. Dependency-aware token encoding introduces a structured approach to embedding initialization, ensuring that relational constraints are embedded within token representations rather than inferred solely through attention dynamics. The proposed encoding mechanism refines token interactions through dependency-weighted attention computations, ensuring that syntactic and semantic dependencies are retained across multiple processing layers. Empirical evaluations indicate reductions in perplexity across diverse linguistic benchmarks, suggesting improvements in contextual coherence and predictive consistency in autoregressive text generation. Computational efficiency assessments reveal a moderate increase in memory consumption and training time, attributed to additional matrix computations within the encoding module, yet scalability remains feasible within conventional transformer architectures. Structured encoding enhances lexical variation and dependency retention, reinforcing linguistic coherence without requiring external syntactic annotations or auxiliary training objectives. Statistical comparisons highlight improvements in dependency alignment, particularly in longer sequences where conventional self-attention models exhibit degradation in hierarchical consistency. Sentence length distributions indicate a reduction in abrupt phrase transitions, further supporting the hypothesis that explicit dependency encoding facilitates more structured phrase generation.

We investigate whether artificial intelligence can address the peer review crisis in economics by analyzing 27,090 evaluations of 9,030 unique submissions using a large language model (LLM). The experiment systematically varies author characteristics (e.g., affiliation, reputation, gender) and publication quality (e.g., top-tier, mid-tier, low-tier, AI generated papers). The results indicate that LLMs effectively distinguish paper quality but exhibit biases favoring prominent institutions, male authors, and renowned economists. Additionally, LLMs struggle to differentiate high-quality AI-generated papers from genuine top-tier submissions. While LLMs offer efficiency gains, their susceptibility to bias necessitates cautious integration and hybrid peer review models to balance equity and accuracy.

Recent advancements in the reasoning skills of Large Language Models (LLMs) demonstrate an increase in the ability of LLMs to solve simple planning tasks. However, as long as the driving force behind improved reasoning capability is the size and complexity of the model, the financial and computational costs associated with running them will also increase. This trend raises questions about continued accessibility and whether these improvements will increase at the same pace as models continue to grow in size and expense. We propose two approaches to enhance the reasoning ability of less resource-intensive LLMs. (1) Provide them with a generalised strategy for solving tasks within a given domain, generated by a more resource-intensive LLM. (2) Exploit their cost-effectiveness by iteratively prompting these models to correct errors in their proposed solutions. Our empirical results from planning and mathematical reasoning tasks demonstrate that these methods improve the performance of less resource-intensive LLMs to levels comparable with their more resource-intensive counterparts, at a fraction of the cost. Additionally, we show that the utilisation of generalised strategies in our experiments reduced the cost of the less resource-intensive model by nearly 30 percent on average.

Object rearrangement is a significant task for collaborative robots, where they are directed to manipulate objects into a specified goal state. Determining the placement of objects is a major challenge that influences the efficiency of the rearrangement process. Most current methods heavily rely on pre-collected datasets to train the model for predicting the goal position and are restricted to specific instructions, which limits their broader applicability and effectiveness.In this paper, we propose a framework of language-conditioned object rearrangement based on the Large Language Model (LLM). Particularly, our approach mimics human reasoning by using past successful experiences as a reference to infer the desired goal position. Based on LLM's strong natural language comprehension and inference ability, our method can generalise to handle various everyday objects and free-form language instructions in a zero-shot manner. Experimental results demonstrate that our methods can effectively execute the robotic rearrangement tasks, even those involving long sequential orders.

Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning using Evolution for Accurate Recognition (CLEAR), which uses a combination of LLMs and evolutionary computation to generate and optimize cues such that recognition of specialized features in images is improved. It achieves this by auto-generating a novel domain-specific representation and then using it to optimize suitable textual cues with a genetic algorithm. We apply CLEAR to the real-world task of identifying sustainability data from interior and exterior images of buildings. We investigate the effects of using a variable-length representation compared to fixed-length and show how LLM consistency can be improved by refactoring from categorical to real-valued estimates. We show that CLEAR enables higher accuracy compared to expert human recognition and human-authored prompts in every task with error rates improved by up to two orders of magnitude and an ablation study evincing solution concision.

With recent advancements in the capabilities of Text-to-Image (T2I) AI models, product designers have begun experimenting with them in their work. However, T2I models struggle to interpret abstract language and the current user experience of T2I tools can induce design fixation rather than a more iterative, exploratory process. To address these challenges, we developed Inkspire, a sketch-driven tool that supports designers in prototyping product design concepts with analogical inspirations and a complete sketch-to-design-to-sketch feedback loop. To inform the design of Inkspire, we conducted an exchange session with designers and distilled design goals for improving T2I interactions. In a within-subjects study comparing Inkspire to ControlNet, we found that Inkspire supported designers with more inspiration and exploration of design ideas, and improved aspects of the co-creative process by allowing designers to effectively grasp the current state of the AI to guide it towards novel design intentions.

This paper considers the sample-efficiency of preference learning, which models and predicts human choices based on comparative judgments. The minimax optimal estimation rate $\Theta(d/n)$ in traditional estimation theory requires that the number of samples $n$ scales linearly with the dimensionality of the feature space $d$. However, the high dimensionality of the feature space and the high cost of collecting human-annotated data challenge the efficiency of traditional estimation methods. To remedy this, we leverage sparsity in the preference model and establish sharp estimation rates. We show that under the sparse random utility model, where the parameter of the reward function is $k$-sparse, the minimax optimal rate can be reduced to $\Theta(k/n \log(d/k))$. Furthermore, we analyze the $\ell_{1}$-regularized estimator and show that it achieves near-optimal rate under mild assumptions on the Gram matrix. Experiments on synthetic data and LLM alignment data validate our theoretical findings, showing that sparsity-aware methods significantly reduce sample complexity and improve prediction accuracy.

The recent advancements in visual reasoning capabilities of large multimodal models (LMMs) and the semantic enrichment of 3D feature fields have expanded the horizons of robotic capabilities. These developments hold significant potential for bridging the gap between high-level reasoning from LMMs and low-level control policies utilizing 3D feature fields. In this work, we introduce LMM-3DP, a framework that can integrate LMM planners and 3D skill Policies. Our approach consists of three key perspectives: high-level planning, low-level control, and effective integration. For high-level planning, LMM-3DP supports dynamic scene understanding for environment disturbances, a critic agent with self-feedback, history policy memorization, and reattempts after failures. For low-level control, LMM-3DP utilizes a semantic-aware 3D feature field for accurate manipulation. In aligning high-level and low-level control for robot actions, language embeddings representing the high-level policy are jointly attended with the 3D feature field in the 3D transformer for seamless integration. We extensively evaluate our approach across multiple skills and long-horizon tasks in a real-world kitchen environment. Our results show a significant 1.45x success rate increase in low-level control and an approximate 1.5x improvement in high-level planning accuracy compared to LLM-based baselines. Demo videos and an overview of LMM-3DP are available at https://lmm-3dp-release.github.io.

Training of large language models (LLMs) is typically distributed across a large number of accelerators to reduce training time. Since internal states and parameter gradients need to be exchanged at each and every single gradient step, all devices need to be co-located using low-latency high-bandwidth communication links to support the required high volume of exchanged bits. Recently, distributed algorithms like DiLoCo have relaxed such co-location constraint: accelerators can be grouped into ``workers'', where synchronizations between workers only occur infrequently. This in turn means that workers can afford being connected by lower bandwidth communication links without affecting learning quality. However, in these methods, communication across workers still requires the same peak bandwidth as before, as the synchronizations require all parameters to be exchanged across all workers. In this paper, we improve DiLoCo in three ways. First, we synchronize only subsets of parameters in sequence, rather than all at once, which greatly reduces peak bandwidth. Second, we allow workers to continue training while synchronizing, which decreases wall clock time. Third, we quantize the data exchanged by workers, which further reduces bandwidth across workers. By properly combining these modifications, we show experimentally that we can distribute training of billion-scale parameters and reach similar quality as before, but reducing required bandwidth by two orders of magnitude.

Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action evaluation while preserving the stability of value function-based learning. Unlike DeepSeek GRPO, which eliminates the value function in favor of purely empirical reward estimation, Hybrid GRPO introduces a structured advantage computation method that balances empirical action sampling with bootstrapped value estimation. This approach enhances sample efficiency, improves learning stability, and mitigates variance amplification observed in purely empirical methods. A detailed mathematical comparison between PPO, DeepSeek GRPO, and Hybrid GRPO is presented, highlighting key differences in advantage estimation and policy updates. Experimental validation in a controlled reinforcement learning environment demonstrates that Hybrid GRPO achieves superior convergence speed, more stable policy updates, and improved sample efficiency compared to existing methods. Several extensions to Hybrid GRPO are explored, including entropy-regularized sampling, hierarchical multi-step sub-sampling, adaptive reward normalization, and value-based action selection. Beyond reinforcement learning in simulated environments, Hybrid GRPO provides a scalable framework for bridging the gap between large language models (LLMs) and real-world agent-based decision-making. By integrating structured empirical sampling with reinforcement learning stability mechanisms, Hybrid GRPO has potential applications in autonomous robotics, financial modeling, and AI-driven control systems. These findings suggest that Hybrid GRPO serves as a robust and adaptable reinforcement learning methodology, paving the way for further advancements in policy optimization.