Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?

This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. By leveraging large language models (LLMs) for neural architecture search (NAS), a vision transformer (ViT)-based knowledge distillation (KD) strategy, and an explainability module, the approach strikes an optimal balance between accuracy, computational efficiency, and memory usage. The LLM-guided search explores a hierarchical search space, refining candidate architectures through Pareto optimization based on accuracy, multiply-accumulate operations (MACs), and memory metrics. The best-performing architectures are further fine-tuned using logits-based KD with a pre-trained ViT-B/16 model, which enhances generalization without increasing model size. Evaluated on the CIFAR-100 dataset and deployed on an STM32H7 microcontroller (MCU), the three proposed models, LMaNet-Elite, LMaNet-Core, and QwNet-Core, achieve accuracy scores of 74.50%, 74.20% and 73.00%, respectively. All three models surpass current state-of-the-art (SOTA) models, such as MCUNet-in3/in4 (69.62% / 72.86%) and XiNet (72.27%), while maintaining a low computational cost of less than 100 million MACs and adhering to the stringent 320 KB static random-access memory (SRAM) constraint. These results demonstrate the efficiency and performance of the proposed framework for TinyML platforms, underscoring the potential of combining LLM-driven search, Pareto optimization, KD, and explainability to develop accurate, efficient, and interpretable models. This approach opens new possibilities in NAS, enabling the design of efficient architectures specifically suited for TinyML.

Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs

Sim-to-real reinforcement learning (RL) for humanoid robots with high-gear ratio actuators remains challenging due to complex actuator dynamics and the absence of torque sensors. To address this, we propose a novel RL framework leveraging foot-mounted inertial measurement units (IMUs). Instead of pursuing detailed actuator modeling and system identification, we utilize foot-mounted IMU measurements to enhance rapid stabilization capabilities over challenging terrains. Additionally, we propose symmetric data augmentation dedicated to the proposed observation space and random network distillation to enhance bipedal locomotion learning over rough terrain. We validate our approach through hardware experiments on a miniature-sized humanoid EVAL-03 over a variety of environments. The experimental results demonstrate that our method improves rapid stabilization capabilities over non-rigid surfaces and sudden environmental transitions.

Towards Better Sample Efficiency in Multi-Agent Reinforcement Learning via Exploration

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to train high-quality policies for a football environment. In this paper, we hypothesize that better exploration mechanisms can improve the sample efficiency of multi-agent methods. We propose two different approaches for better exploration in TiZero: a self-supervised intrinsic reward and a random network distillation bonus. Additionally, we introduce architectural modifications to the original algorithm to enhance TiZero's computational efficiency. We evaluate the sample efficiency of these approaches through extensive experiments. Our results show that random network distillation improves training sample efficiency by 18.8% compared to the original TiZero. Furthermore, we evaluate the qualitative behavior of the models produced by both variants against a heuristic AI, with the self-supervised reward encouraging possession and random network distillation leading to a more offensive performance. Our results highlights the applicability of our random network distillation variant in practical settings. Lastly, due to the nature of the proposed method, we acknowledge its use beyond football simulation, especially in environments with strong multi-agent and strategic aspects.

Sample-level Adaptive Knowledge Distillation for Action Recognition

Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours have been devoted to the image domain, while few works focus on video analysis which desires training much larger model making it be hardly deployed in resource-limited devices. However, traditional methods neglect two important problems, i.e., 1) Since the capacity gap between the teacher and the student exists, some knowledge w.r.t. difficult-to-transfer samples cannot be correctly transferred, or even badly affects the final performance of student, and 2) As training progresses, difficult-to-transfer samples may become easier to learn, and vice versa. To alleviate the two problems, we propose a Sample-level Adaptive Knowledge Distillation (SAKD) framework for action recognition. In particular, it mainly consists of the sample distillation difficulty evaluation module and the sample adaptive distillation module. The former applies the temporal interruption to frames, i.e., randomly dropout or shuffle the frames during training, which increases the learning difficulty of samples during distillation, so as to better discriminate their distillation difficulty. The latter module adaptively adjusts distillation ratio at sample level, such that KD loss dominates the training with easy-to-transfer samples while vanilla loss dominates that with difficult-to-transfer samples. More importantly, we only select those samples with both low distillation difficulty and high diversity to train the student model for reducing computational cost. Experimental results on two video benchmarks and one image benchmark demonstrate the superiority of the proposed method by striking a good balance between performance and efficiency.

Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability

One of the bottlenecks in robotic intelligence is the instability of neural network models, which, unlike control models, lack a well-defined convergence domain and stability. This leads to risks when applying intelligence in the physical world. Specifically, imitation policy based on neural network may generate hallucinations, leading to inaccurate behaviors that impact the safety of real-world applications. To address this issue, this paper proposes the Curiosity-Diffuser, aimed at guiding the conditional diffusion model to generate trajectories with lower curiosity, thereby improving the reliability of policy. The core idea is to use a Random Network Distillation (RND) curiosity module to assess whether the model's behavior aligns with the training data, and then minimize curiosity by classifier guidance diffusion to reduce overgeneralization during inference. Additionally, we propose a computationally efficient metric for evaluating the reliability of the policy, measuring the similarity between the generated behaviors and the training dataset, to facilitate research about reliability learning. Finally, simulation verify the effectiveness and applicability of the proposed method to a variety of scenarios, showing that Curiosity-Diffuser significantly improves task performance and produces behaviors that are more similar to the training data. The code for this work is available at: github.com/CarlDegio/Curiosity-Diffuser

Random Walk Guided Hyperbolic Graph Distillation

Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to generate condensed graphs, struggle to capture the inherent tree-like geometry of real-world networks, resulting in distilled graphs with limited task-specific information for downstream tasks. Furthermore, these methods often fail to extract dynamic properties from graphs, which are crucial for understanding information flow and facilitating graph continual learning. This paper presents the Hyperbolic Graph Distillation with Random Walks Optimization (HyDRO), a novel graph distillation approach that leverages hyperbolic embeddings to capture complex geometric patterns and optimize the spectral gap in hyperbolic space. Experiments show that HyDRO demonstrates strong task generalization, consistently outperforming state-of-the-art methods in both node classification and link prediction tasks. HyDRO also effectively preserves graph random walk properties, producing condensed graphs that achieve enhanced performance in continual graph learning. Additionally, HyDRO achieves competitive results on mainstream graph distillation benchmarks, while maintaining a strong balance between privacy and utility, and exhibiting robust resistance to noises.

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning

Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environments. However, the efficiency of these systems is often compromised by inadequate sample utilization and a lack of diversity in learning strategies. To enhance MARL performance, we introduce a novel sample reuse approach that dynamically adjusts policy updates based on observation novelty. Specifically, we employ a Random Network Distillation (RND) network to gauge the novelty of each agent's current state, assigning additional sample update opportunities based on the uniqueness of the data. We name our method Multi-Agent Novelty-GuidEd sample Reuse (MANGER). This method increases sample efficiency and promotes exploration and diverse agent behaviors. Our evaluations confirm substantial improvements in MARL effectiveness in complex cooperative scenarios such as Google Research Football and super-hard StarCraft II micromanagement tasks.

Modality-Invariant Bidirectional Temporal Representation Distillation Network for Missing Multimodal Sentiment Analysis

Multimodal Sentiment Analysis (MSA) integrates diverse modalities(text, audio, and video) to comprehensively analyze and understand individuals' emotional states. However, the real-world prevalence of incomplete data poses significant challenges to MSA, mainly due to the randomness of modality missing. Moreover, the heterogeneity issue in multimodal data has yet to be effectively addressed. To tackle these challenges, we introduce the Modality-Invariant Bidirectional Temporal Representation Distillation Network (MITR-DNet) for Missing Multimodal Sentiment Analysis. MITR-DNet employs a distillation approach, wherein a complete modality teacher model guides a missing modality student model, ensuring robustness in the presence of modality missing. Simultaneously, we developed the Modality-Invariant Bidirectional Temporal Representation Learning Module (MIB-TRL) to mitigate heterogeneity.

Multimodal Prescriptive Deep Learning

We introduce a multimodal deep learning framework, Prescriptive Neural Networks (PNNs), that combines ideas from optimization and machine learning, and is, to the best of our knowledge, the first prescriptive method to handle multimodal data. The PNN is a feedforward neural network trained on embeddings to output an outcome-optimizing prescription. In two real-world multimodal datasets, we demonstrate that PNNs prescribe treatments that are able to significantly improve estimated outcomes in transcatheter aortic valve replacement (TAVR) procedures by reducing estimated postoperative complication rates by 32% and in liver trauma injuries by reducing estimated mortality rates by over 40%. In four real-world, unimodal tabular datasets, we demonstrate that PNNs outperform or perform comparably to other well-known, state-of-the-art prescriptive models; importantly, on tabular datasets, we also recover interpretability through knowledge distillation, fitting interpretable Optimal Classification Tree models onto the PNN prescriptions as classification targets, which is critical for many real-world applications. Finally, we demonstrate that our multimodal PNN models achieve stability across randomized data splits comparable to other prescriptive methods and produce realistic prescriptions across the different datasets.

Efficient Active Imitation Learning with Random Network Distillation

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically, and there is no clear reward to evaluate them. While imitation learning has shown promise in such domains, these methods often fail when agents encounter out-of-distribution scenarios during deployment. Expanding the training dataset is a common solution, but it becomes impractical or costly when relying on human demonstrations. This article addresses active imitation learning, aiming to trigger expert intervention only when necessary, reducing the need for constant expert input along training. We introduce Random Network Distillation DAgger (RND-DAgger), a new active imitation learning method that limits expert querying by using a learned state-based out-of-distribution measure to trigger interventions. This approach avoids frequent expert-agent action comparisons, thus making the expert intervene only when it is useful. We evaluate RND-DAgger against traditional imitation learning and other active approaches in 3D video games (racing and third-person navigation) and in a robotic locomotion task and show that RND-DAgger surpasses previous methods by reducing expert queries. https://sites.google.com/view/rnd-dagger