Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization

Recently, reinforcement learning~(RL) has become an important approach for improving the capabilities of large language models~(LLMs). In particular, reinforcement learning from verifiable rewards~(RLVR) has emerged as a promising paradigm for reasoning tasks. However, existing RL-based training still remains only a rough approximation to human learning. Human learners leverage both external and internal experience to guide exploration and gradually internalize useful trajectories into stable knowledge. Motivated by this gap, we ask: how can LLMs better utilize and internalize experience during RLVR training? To answer this question, we propose \textbf{D}ual \textbf{G}uidance \textbf{O}ptimization~(\textbf{DGO}), a unified framework that leverages \emph{external} and \emph{internal experience} to improve training effectiveness. Specifically, DGO first constructs an experience bank from previously explored trajectories. The policy then performs exploration under the joint guidance of the experience bank and the model's internal knowledge. The resulting trajectories are further used to refine the experience bank and optimize model parameters, forming a closed loop of experience utilization and internalization. Experiments show that DGO consistently outperforms baseline methods, suggesting that better utilization and internalization of experience lead to more effective reasoning.

Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning

Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, despite being a critical real-world modality, remains relatively underexplored in multimodal learning. In this paper, we focus on the task of Tabular-Vision Multi-Modal Understanding (TVMU) and identify three core challenges: (1) high structural variability and data incompleteness in tables, (2) implicit and complex feature dependencies, and (3) significant heterogeneity in problem-solving pipelines across downstream tasks. To address these issues, we propose Thinking with Tables (TWT). TWT employs a program-aided code-based neuro-symbolic reasoning mechanism that facilitates key operations, such as information extraction and element modeling, by interacting with external environments. We evaluate TWT on eight representative datasets. Experimental results demonstrate that TWT consistently outperforms existing baselines by an average of 10\% in accuracy, achieving performance comparable to, or even surpassing, proprietary commercial SOTA LLMs on TVMU tasks. Models and codes are available at https://github.com/kunyang-YU/Thinking-with-Tables

NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing

Remote sensing underpins crucial applications such as disaster relief and ecological field surveys, where systems must understand complex scenes and constraints and make reliable decisions. Current remote-sensing benchmarks mainly focus on evaluating perception and reasoning capabilities of multimodal large language models (MLLMs). They fail to assess planning capability, stemming either from the difficulty of curating and validating planning tasks at scale or from evaluation protocols that are inaccurate and inadequate. To address these limitations, we introduce NeSy-Route, a large-scale neuro-symbolic benchmark for constrained route planning in remote sensing. Within this benchmark, we introduce an automated data-generation framework that integrates high-fidelity semantic masks with heuristic search to produce diverse route-planning tasks with provably optimal solutions. This allows NeSy-Route to comprehensively evaluate planning across 10,821 route-planning samples, nearly 10 times larger than the largest prior benchmark. Furthermore, a three-level hierarchical neuro-symbolic evaluation protocol is developed to enable accurate assessment and support fine-grained analysis on perception, reasoning, and planning simultaneously. Our comprehensive evaluation of various state-of-the-art MLLMs demonstrates that existing MLLMs show significant deficiencies in perception and planning capabilities. We hope NeSy-Route can support further research and development of more powerful MLLMs for remote sensing.

RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Driving

Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and lighting conditions, limiting their robustness and large-scale deployment in intelligent transportation systems. Radar-vision fusion provides a promising alternative by combining the environmental robustness and cost efficiency of millimeter-wave (mmWave) radar with the rich semantic information captured by cameras. Nevertheless, conventional 3D radar measurements lack height resolution and remain highly sparse, while emerging 4D mmWave radar introduces elevation information but also brings challenges such as signal noise and large data volume. To address these issues, this paper proposes RadarXFormer, a 3D object detection framework that enables efficient cross-modal fusion between 4D radar spectra and RGB images. Instead of relying on sparse radar point clouds, RadarXFormer directly leverages raw radar spectra and constructs an efficient 3D representation that reduces data volume while preserving complete 3D spatial information. The "X" highlights the proposed cross-dimension (3D-2D) fusion mechanism, in which multi-scale 3D spherical radar feature cubes are fused with complementary 2D image feature maps. Experiments on the K-Radar dataset demonstrate improved detection accuracy and robustness under challenging conditions while maintaining real-time inference capability.

General Humanoid Whole-Body Control via Pretraining and Fast Adaptation

Learning a general whole-body controller for humanoid robots remains challenging due to the diversity of motion distributions, the difficulty of fast adaptation, and the need for robust balance in high-dynamic scenarios. Existing approaches often require task-specific training or suffer from performance degradation when adapting to new motions. In this paper, we present FAST, a general humanoid whole-body control framework that enables Fast Adaptation and Stable Motion Tracking. FAST introduces Parseval-Guided Residual Policy Adaptation, which learns a lightweight delta action policy under orthogonality and KL constraints, enabling efficient adaptation to out-of-distribution motions while mitigating catastrophic forgetting. To further improve physical robustness, we propose Center-of-Mass-Aware Control, which incorporates CoM-related observations and objectives to enhance balance when tracking challenging reference motions. Extensive experiments in simulation and real-world deployment demonstrate that FAST consistently outperforms state-of-the-art baselines in robustness, adaptation efficiency, and generalization.

Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models

Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference. In this work, we embrace the idea of looping back to move forward: reusing model parameters through recursive refinement to extract stronger multimodal representations without increasing model size. We propose RecursiveVLM, a recursive Transformer architecture tailored for LMMs. Two key innovations enable effective looping: (i) a Recursive Connector that aligns features across recursion steps by fusing intermediate-layer hidden states and applying modality-specific projections, respecting the distinct statistical structures of vision and language tokens; (ii) a Monotonic Recursion Loss that supervises every step and guarantees performance improves monotonically with recursion depth. This design transforms recursion into an on-demand refinement mechanism: delivering strong results with few loops on resource-constrained devices and progressively improving outputs when more computation resources are available. Experiments show consistent gains of +3% over standard Transformers and +7% over vanilla recursive baselines, demonstrating that strategic looping is a powerful path toward efficient, deployment-adaptive LMMs.

FlattenGPT: Depth Compression for Transformer with Layer Flattening

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues learned in those blocks, leading to substantial performance degradation. As another line of model compression, channel pruning can better preserve performance, while it cannot reduce model depth and is challenged by inconsistent pruning ratios for individual layers. To pursue better model compression and acceleration, this paper proposes \textbf{FlattenGPT}, a novel way to detect and reduce depth-wise redundancies. By flatting two adjacent blocks into one, it compresses the network depth, meanwhile enables more effective parameter redundancy detection and removal. FlattenGPT allows to preserve the knowledge learned in all blocks, and remains consistent with the original transformer architecture. Extensive experiments demonstrate that FlattenGPT enhances model efficiency with a decent trade-off to performance. It outperforms existing pruning methods in both zero-shot accuracies and WikiText-2 perplexity across various model types and parameter sizes. On LLaMA-2/3 and Qwen-1.5 models, FlattenGPT retains 90-96\% of zero-shot performance with a compression ratio of 20\%. It also outperforms other pruning methods in accelerating LLM inference, making it promising for enhancing the efficiency of transformers.

Zero-Shot UAV Navigation in Forests via Relightable 3D Gaussian Splatting

UAV navigation in unstructured outdoor environments using passive monocular vision is hindered by the substantial visual domain gap between simulation and reality. While 3D Gaussian Splatting enables photorealistic scene reconstruction from real-world data, existing methods inherently couple static lighting with geometry, severely limiting policy generalization to dynamic real-world illumination. In this paper, we propose a novel end-to-end reinforcement learning framework designed for effective zero-shot transfer to unstructured outdoors. Within a high-fidelity simulation grounded in real-world data, our policy is trained to map raw monocular RGB observations directly to continuous control commands. To overcome photometric limitations, we introduce Relightable 3D Gaussian Splatting, which decomposes scene components to enable explicit, physically grounded editing of environmental lighting within the neural representation. By augmenting training with diverse synthesized lighting conditions ranging from strong directional sunlight to diffuse overcast skies, we compel the policy to learn robust, illumination-invariant visual features. Extensive real-world experiments demonstrate that a lightweight quadrotor achieves robust, collision-free navigation in complex forest environments at speeds up to 10 m/s, exhibiting significant resilience to drastic lighting variations without fine-tuning.

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization

Multi-turn tool-integrated reasoning enables Large Language Models (LLMs) to solve complex tasks through iterative information retrieval. However, current reinforcement learning (RL) frameworks for search-augmented reasoning predominantly rely on sparse outcome-level rewards, leading to a "Double Homogenization Dilemma." This manifests as (1) Process homogenization, where the thinking, reasoning, and tooling involved in generation are ignored. (2) Intra-group homogenization, coarse-grained outcome rewards often lead to inefficiencies in intra-group advantage estimation with methods like Group Relative Policy Optimization (GRPO) during sampling. To address this, we propose Turn-level Stage-aware Policy Optimization (TSPO). TSPO introduces the First-Occurrence Latent Reward (FOLR) mechanism, allocating partial rewards to the step where the ground-truth answer first appears, thereby preserving process-level signals and increasing reward variance within groups without requiring external reward models or any annotations. Extensive experiments demonstrate that TSPO significantly outperforms state-of-the-art baselines, achieving average performance gains of 24% and 13.6% on Qwen2.5-3B and 7B models, respectively.

Learning Diffusion Policy from Primitive Skills for Robot Manipulation

Diffusion policies (DP) have recently shown great promise for generating actions in robotic manipulation. However, existing approaches often rely on global instructions to produce short-term control signals, which can result in misalignment in action generation. We conjecture that the primitive skills, referred to as fine-grained, short-horizon manipulations, such as ``move up'' and ``open the gripper'', provide a more intuitive and effective interface for robot learning. To bridge this gap, we propose SDP, a skill-conditioned DP that integrates interpretable skill learning with conditional action planning. SDP abstracts eight reusable primitive skills across tasks and employs a vision-language model to extract discrete representations from visual observations and language instructions. Based on them, a lightweight router network is designed to assign a desired primitive skill for each state, which helps construct a single-skill policy to generate skill-aligned actions. By decomposing complex tasks into a sequence of primitive skills and selecting a single-skill policy, SDP ensures skill-consistent behavior across diverse tasks. Extensive experiments on two challenging simulation benchmarks and real-world robot deployments demonstrate that SDP consistently outperforms SOTA methods, providing a new paradigm for skill-based robot learning with diffusion policies.