S'MoRE: Structural Mixture of Residual Experts for LLM Fine-tuning

Fine-tuning pre-trained large language models (LLMs) presents a dual challenge of balancing parameter efficiency and model capacity. Existing methods like low-rank adaptations (LoRA) are efficient but lack flexibility, while Mixture-of-Experts (MoE) architectures enhance model capacity at the cost of more & under-utilized parameters. To address these limitations, we propose Structural Mixture of Residual Experts (S'MoRE), a novel framework that seamlessly integrates the efficiency of LoRA with the flexibility of MoE. Specifically, S'MoRE employs hierarchical low-rank decomposition of expert weights, yielding residuals of varying orders interconnected in a multi-layer structure. By routing input tokens through sub-trees of residuals, S'MoRE emulates the capacity of many experts by instantiating and assembling just a few low-rank matrices. We craft the inter-layer propagation of S'MoRE's residuals as a special type of Graph Neural Network (GNN), and prove that under similar parameter budget, S'MoRE improves "structural flexibility" of traditional MoE (or Mixture-of-LoRA) by exponential order. Comprehensive theoretical analysis and empirical results demonstrate that S'MoRE achieves superior fine-tuning performance, offering a transformative approach for efficient LLM adaptation.

ERPO: Advancing Safety Alignment via Ex-Ante Reasoning Preference Optimization

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. In this work, we propose Ex-Ante Reasoning Preference Optimization (ERPO), a novel safety alignment framework that equips LLMs with explicit preemptive reasoning through Chain-of-Thought and provides clear evidence for safety judgments by embedding predefined safety rules. Specifically, our approach consists of three stages: first, equipping the model with Ex-Ante reasoning through supervised fine-tuning (SFT) using a constructed reasoning module; second, enhancing safety, usefulness, and efficiency via Direct Preference Optimization (DPO); and third, mitigating inference latency with a length-controlled iterative preference optimization strategy. Experiments on multiple open-source LLMs demonstrate that ERPO significantly enhances safety performance while maintaining response efficiency.

Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal

High-fidelity imaging is crucial for the successful safety supervision and intelligent deployment of vision-based measurement systems (VBMS). It ensures high-quality imaging in VBMS, which is fundamental for reliable visual measurement and analysis. However, imaging quality can be significantly impaired by adverse weather conditions, particularly rain, leading to blurred images and reduced contrast. Such impairments increase the risk of inaccurate evaluations and misinterpretations in VBMS. To address these limitations, we propose an Expectation Maximization Reconstruction Transformer (EMResformer) for single image rain streak removal. The EMResformer retains the key self-attention values for feature aggregation, enhancing local features to produce superior image reconstruction. Specifically, we propose an Expectation Maximization Block seamlessly integrated into the single image rain streak removal network, enhancing its ability to eliminate superfluous information and restore a cleaner background image. Additionally, to further enhance local information for improved detail rendition, we introduce a Local Model Residual Block, which integrates two local model blocks along with a sequence of convolutions and activation functions. This integration synergistically facilitates the extraction of more pertinent features for enhanced single image rain streak removal. Extensive experiments validate that our proposed EMResformer surpasses current state-of-the-art single image rain streak removal methods on both synthetic and real-world datasets, achieving an improved balance between model complexity and single image deraining performance. Furthermore, we evaluate the effectiveness of our method in VBMS scenarios, demonstrating that high-quality imaging significantly improves the accuracy and reliability of VBMS tasks.

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition

Diffusion Policy (DP) has attracted significant attention as an effective method for policy representation due to its capacity to model multi-distribution dynamics. However, current DPs are often based on a single visual modality (e.g., RGB or point cloud), limiting their accuracy and generalization potential. Although training a generalized DP capable of handling heterogeneous multimodal data would enhance performance, it entails substantial computational and data-related costs. To address these challenges, we propose a novel policy composition method: by leveraging multiple pre-trained DPs based on individual visual modalities, we can combine their distributional scores to form a more expressive Modality-Composable Diffusion Policy (MCDP), without the need for additional training. Through extensive empirical experiments on the RoboTwin dataset, we demonstrate the potential of MCDP to improve both adaptability and performance. This exploration aims to provide valuable insights into the flexible composition of existing DPs, facilitating the development of generalizable cross-modality, cross-domain, and even cross-embodiment policies. Our code is open-sourced at https://github.com/AndyCao1125/MCDP.

EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks

While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex long-horizon tasks. To address this gap, we propose EmbodiedVSR (Embodied Visual Spatial Reasoning), a novel framework that integrates dynamic scene graph-guided Chain-of-Thought (CoT) reasoning to enhance spatial understanding for embodied agents. By explicitly constructing structured knowledge representations through dynamic scene graphs, our method enables zero-shot spatial reasoning without task-specific fine-tuning. This approach not only disentangles intricate spatial relationships but also aligns reasoning steps with actionable environmental dynamics. To rigorously evaluate performance, we introduce the eSpatial-Benchmark, a comprehensive dataset including real-world embodied scenarios with fine-grained spatial annotations and adaptive task difficulty levels. Experiments demonstrate that our framework significantly outperforms existing MLLM-based methods in accuracy and reasoning coherence, particularly in long-horizon tasks requiring iterative environment interaction. The results reveal the untapped potential of MLLMs for embodied intelligence when equipped with structured, explainable reasoning mechanisms, paving the way for more reliable deployment in real-world spatial applications. The codes and datasets will be released soon.

HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots

The perceptual system design for humanoid robots poses unique challenges due to inherent structural constraints that cause severe self-occlusion and limited field-of-view (FOV). We present HumanoidPano, a novel hybrid cross-modal perception framework that synergistically integrates panoramic vision and LiDAR sensing to overcome these limitations. Unlike conventional robot perception systems that rely on monocular cameras or standard multi-sensor configurations, our method establishes geometrically-aware modality alignment through a spherical vision transformer, enabling seamless fusion of 360 visual context with LiDAR's precise depth measurements. First, Spherical Geometry-aware Constraints (SGC) leverage panoramic camera ray properties to guide distortion-regularized sampling offsets for geometric alignment. Second, Spatial Deformable Attention (SDA) aggregates hierarchical 3D features via spherical offsets, enabling efficient 360{\deg}-to-BEV fusion with geometrically complete object representations. Third, Panoramic Augmentation (AUG) combines cross-view transformations and semantic alignment to enhance BEV-panoramic feature consistency during data augmentation. Extensive evaluations demonstrate state-of-the-art performance on the 360BEV-Matterport benchmark. Real-world deployment on humanoid platforms validates the system's capability to generate accurate BEV segmentation maps through panoramic-LiDAR co-perception, directly enabling downstream navigation tasks in complex environments. Our work establishes a new paradigm for embodied perception in humanoid robotics.

ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network

In recent years, quadruped robotics has advanced significantly, particularly in perception and motion control via reinforcement learning, enabling complex motions in challenging environments. Visual sensors like depth cameras enhance stability and robustness but face limitations, such as low operating frequencies relative to joint control and sensitivity to lighting, which hinder outdoor deployment. Additionally, deep neural networks in sensor and control systems increase computational demands. To address these issues, we introduce spiking neural networks (SNNs) and event cameras to perform a challenging quadruped parkour task. Event cameras capture dynamic visual data, while SNNs efficiently process spike sequences, mimicking biological perception. Experimental results demonstrate that this approach significantly outperforms traditional models, achieving excellent parkour performance with just 11.7% of the energy consumption of an artificial neural network (ANN)-based model, yielding an 88.3% energy reduction. By integrating event cameras with SNNs, our work advances robotic reinforcement learning and opens new possibilities for applications in demanding environments.

LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures

In recent years, research on humanoid robots has garnered significant attention, particularly in reinforcement learning based control algorithms, which have achieved major breakthroughs. Compared to traditional model-based control algorithms, reinforcement learning based algorithms demonstrate substantial advantages in handling complex tasks. Leveraging the large-scale parallel computing capabilities of GPUs, contemporary humanoid robots can undergo extensive parallel training in simulated environments. A physical simulation platform capable of large-scale parallel training is crucial for the development of humanoid robots. As one of the most complex robot forms, humanoid robots typically possess intricate mechanical structures, encompassing numerous series and parallel mechanisms. However, many reinforcement learning based humanoid robot control algorithms currently employ open-loop topologies during training, deferring the conversion to series-parallel structures until the sim2real phase. This approach is primarily due to the limitations of physics engines, as current GPU-based physics engines often only support open-loop topologies or have limited capabilities in simulating multi-rigid-body closed-loop topologies. For enabling reinforcement learning-based humanoid robot control algorithms to train in large-scale parallel environments, we propose a novel training method LiPS. By incorporating multi-rigid-body dynamics modeling in the simulation environment, we significantly reduce the sim2real gap and the difficulty of converting to parallel structures during model deployment, thereby robustly supporting large-scale reinforcement learning for humanoid robots.

Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion

In recent years, humanoid robots have garnered significant attention from both academia and industry due to their high adaptability to environments and human-like characteristics. With the rapid advancement of reinforcement learning, substantial progress has been made in the walking control of humanoid robots. However, existing methods still face challenges when dealing with complex environments and irregular terrains. In the field of perceptive locomotion, existing approaches are generally divided into two-stage methods and end-to-end methods. Two-stage methods first train a teacher policy in a simulated environment and then use distillation techniques, such as DAgger, to transfer the privileged information learned as latent features or actions to the student policy. End-to-end methods, on the other hand, forgo the learning of privileged information and directly learn policies from a partially observable Markov decision process (POMDP) through reinforcement learning. However, due to the lack of supervision from a teacher policy, end-to-end methods often face difficulties in training and exhibit unstable performance in real-world applications. This paper proposes an innovative two-stage perceptive locomotion framework that combines the advantages of teacher policies learned in a fully observable Markov decision process (MDP) to regularize and supervise the student policy. At the same time, it leverages the characteristics of reinforcement learning to ensure that the student policy can continue to learn in a POMDP, thereby enhancing the model's upper bound. Our experimental results demonstrate that our two-stage training framework achieves higher training efficiency and stability in simulated environments, while also exhibiting better robustness and generalization capabilities in real-world applications.

Trinity: A Modular Humanoid Robot AI System

In recent years, research on humanoid robots has garnered increasing attention. With breakthroughs in various types of artificial intelligence algorithms, embodied intelligence, exemplified by humanoid robots, has been highly anticipated. The advancements in reinforcement learning (RL) algorithms have significantly improved the motion control and generalization capabilities of humanoid robots. Simultaneously, the groundbreaking progress in large language models (LLM) and visual language models (VLM) has brought more possibilities and imagination to humanoid robots. LLM enables humanoid robots to understand complex tasks from language instructions and perform long-term task planning, while VLM greatly enhances the robots' understanding and interaction with their environment. This paper introduces \textcolor{magenta}{Trinity}, a novel AI system for humanoid robots that integrates RL, LLM, and VLM. By combining these technologies, Trinity enables efficient control of humanoid robots in complex environments. This innovative approach not only enhances the capabilities but also opens new avenues for future research and applications of humanoid robotics.