Large Language Models (LLMs) show strong performance in RTL generation, but different models excel on different tasks because of architecture and training differences. Prior work mainly prompts or finetunes a single model. What remains not well studied is how to coordinate multiple different LLMs so they jointly improve RTL quality while also reducing cost, instead of running all models and choosing the best output. We define this as the multi-LLM RTL generation problem. We propose VeriDispatcher, a multi-LLM RTL generation framework that dispatches each RTL task to suitable LLMs based on pre-inference difficulty prediction. For each model, we train a compact classifier over semantic embeddings of task descriptions, using difficulty scores derived from benchmark variants that combine syntax, structural similarity, and functional correctness. At inference, VeriDispatcher uses these predictors to route tasks to a selected subset of LLMs. Across 10 diverse LLMs on RTLLM and VerilogEval, VeriDispatcher achieves up to 18% accuracy improvement on RTLLM using only 40% of commercial calls, and on VerilogEval maintains accuracy while reducing commercial usage by 25%, enabling cost-effective, high-quality LLM deployment in hardware design automation.

Recent progress in legged locomotion has allowed highly dynamic and parkour-like behaviors for robots, similar to their biological counterparts. Yet, these methods mostly rely on egocentric (first-person) perception, limiting their performance, especially when the viewpoint of the robot is occluded. A promising solution would be to enhance the robot's environmental awareness by using complementary viewpoints, such as multiple actors exchanging perceptual information. Inspired by this idea, this work proposes a multi-view depth-based locomotion framework that combines egocentric and exocentric observations to provide richer environmental context during agile locomotion. Using a teacher-student distillation approach, the student policy learns to fuse proprioception with dual depth streams while remaining robust to real-world sensing imperfections. To further improve robustness, we introduce extensive domain randomization, including stochastic remote-camera dropouts and 3D positional perturbations that emulate aerial-ground cooperative sensing. Simulation results show that multi-viewpoints policies outperform single-viewpoint baseline in gap crossing, step descent, and other dynamic maneuvers, while maintaining stability when the exocentric camera is partially or completely unavailable. Additional experiments show that moderate viewpoint misalignment is well tolerated when incorporated during training. This study demonstrates that heterogeneous visual feedback improves robustness and agility in quadrupedal locomotion. Furthermore, to support reproducibility, the implementation accompanying this work is publicly available at https://anonymous.4open.science/r/multiview-parkour-6FB8

Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and Materials Science. However, large tool outputs can overflow the LLMs' context window, preventing task completion. Existing solutions such as truncation or summarization fail to preserve complete outputs, making them unsuitable for workflows requiring the full data. This work introduces a method that enables LLMs to process and utilize tool responses of arbitrary length without loss of information. By shifting the model's interaction from raw data to memory pointers, the method preserves tool functionality, allows seamless integration into agentic workflows, and reduces token usage and execution time. The proposed method is validated on a real-world Materials Science application that cannot be executed with conventional workflows, and its effectiveness is demonstrated via a comparative analysis where both methods succeed. In this experiment, the proposed approach consumed approximately seven times fewer tokens than the traditional workflow.

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA). However, even state-of-the-art MLLMs struggle with domain-specific or knowledge-intensive queries, where relevant information is underrepresented in pre-training data. Knowledge-based VQA (KB-VQA) addresses this by retrieving external documents to condition answer generation, but current retrieval-augmented approaches suffer from low precision, noisy passages, and limited reasoning. To address this, we propose ReAG, a novel Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages, ensuring high-quality additional context. The model follows a multi-stage training strategy leveraging reinforcement learning to enhance reasoning over retrieved content, while supervised fine-tuning serves only as a cold start. Extensive experiments on Encyclopedic-VQA and InfoSeek demonstrate that ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence. Our source code is publicly available at: https://github.com/aimagelab/ReAG.

In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific items. However, existing generative recommenders overlook this natural refinement process. Generative recommendation formulates next-item prediction as autoregressive generation over tokenized user histories, where each item is represented as a sequence of discrete tokens. Prior models typically fuse heterogeneous attributes such as ID, category, title, and description into a single embedding before quantization, which flattens the inherent semantic hierarchy of items and fails to capture the gradual evolution of user intent during web interactions. To address this limitation, we propose CoFiRec, a novel generative recommendation framework that explicitly incorporates the Coarse-to-Fine nature of item semantics into the tokenization process. Instead of compressing all attributes into a single latent space, CoFiRec decomposes item information into multiple semantic levels, ranging from high-level categories to detailed descriptions and collaborative filtering signals. Based on this design, we introduce the CoFiRec Tokenizer, which tokenizes each level independently while preserving structural order. During autoregressive decoding, the language model is instructed to generate item tokens from coarse to fine, progressively modeling user intent from general interests to specific item-level interests. Experiments across multiple public benchmarks and backbones demonstrate that CoFiRec outperforms existing methods, offering a new perspective for generative recommendation. Theoretically, we prove that structured tokenization leads to lower dissimilarity between generated and ground truth items, supporting its effectiveness in generative recommendation. Our code is available at https://github.com/YennNing/CoFiRec.

The ability to accomplish a sit-to-stand (STS) motion is key to increase functional mobility and reduce rehospitalization risks. While raising aid (transfer) devices and partial bodyweight support (rehabilitation) devices exist, both are unable to adjust the STS training to different mobility levels. Therefore, We have developed an STS training device that allows various configurations of impedance and vertical/forward forces to adapt to many training needs while maintaining commercial raising aid transfer capabilities. Experiments with healthy adults (both men and women) of various heights and weights show that the device 1) has a low impact on the natural STS kinematics, 2) can provide precise weight unloading at the patient's center of mass and 3) can add a forward virtual spring to assist the transfer of the bodyweight to the feet for seat-off, at the start of the STS motion. Keywords: Rehabilitation robotics, Force control, Human-robot interaction, Patient transfer, Floor-lift1. INTRODUCTION For patients in movement rehabilitation, accomplishing functional tasks is key to increasing quality of life and reducing the risk of rehospitalization [1, 2]. Training sit-to-stands (STS) is particularly useful as it has a significant correlation with increasing patient muscle power and the balance required to perform standing and walking tasks [3, 4]. Frequent training is essential to prevent muscle atrophy. However, studies indicate that up to 65% of patients hospitalized in short-term care for seven days or longer develop muscle weakness due to prolonged immobility [5]. This is partly due to the current shortage of qualified clinical staff in hospital settings [6]. Clinical staff can use passive lifts to assist the patient's STS motion, such as the Guldmann GPT1 or the ARJO Sara Stedy, which hold the patient's and knees in a fixed position to reduce fall risks. However, using passive lifts for STS training can be exhaustive and lead to injuries for the clinical staff since it relies on them to move the patient's center of mass (CoM) [7, 8].

Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend with varying physical factors like robot embodiment, environment characteristics, and spatial relationships of each task. Existing fine-tuning methods lack specificity, adapting the same set of parameters regardless of a task's visual, linguistic, and physical characteristics. Inspired by functional specificity in neuroscience, we hypothesize that it is more effective to finetune sparse model representations specific to a given task. In this work, we introduce Robotic Steering, a finetuning approach grounded in mechanistic interpretability that leverages few-shot demonstrations to identify and selectively finetune task-specific attention heads aligned with the physical, visual, and linguistic requirements of robotic tasks. Through comprehensive on-robot evaluations with a Franka Emika robot arm, we demonstrate that Robotic Steering outperforms LoRA while achieving superior robustness under task variation, reduced computational cost, and enhanced interpretability for adapting VLAs to diverse robotic tasks.

We present Generative Anchored Fields (GAF), a generative model that learns independent endpoint predictors $J$ (noise) and $K$ (data) rather than a trajectory predictor. The velocity field $v=K-J$ emerges from their time-conditioned disagreement. This factorization enables \textit{Transport Algebra}: algebraic operation on learned $\{(J_n,K_n)\}_{n=1}^N$ heads for compositional control. With class-specific $K_n$ heads, GAF supports a rich family of directed transport maps between a shared base distribution and multiple modalities, enabling controllable interpolation, hybrid generation, and semantic morphing through vector arithmetic. We achieve strong sample quality (FID 7.5 on CelebA-HQ $64\times 64$) while uniquely providing compositional generation as an architectural primitive. We further demonstrate, GAF has lossless cyclic transport between its initial and final state with LPIPS=$0.0$. Code available at https://github.com/IDLabMedia/GAF

A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics of the diffusion itself. This procedure is often ill posed, as user-specified rewards are usually only well defined on the data distribution at the end of generation. While common workarounds to this problem are to use a de-noiser to estimate what a sample would have been at the end of generation, we propose a simple solution to this problem by working directly with a flow map. By exploiting a relationship between the flow map and velocity field governing the instantaneous transport, we construct an algorithm, Flow Map Trajectory Tilting (FMTT), which provably performs better ascent on the reward than standard test-time methods involving the gradient of the reward. The approach can be used to either perform exact sampling via importance weighting or principled search that identifies local maximizers of the reward-tilted distribution. We demonstrate the efficacy of our approach against other look-ahead techniques, and show how the flow map enables engagement with complicated reward functions that make possible new forms of image editing, e.g. by interfacing with vision language models. Figure 1: Test-time search can overcome model biases and reliably sample from regions of the distribution (e.g., precise clock times) that baselines fail to capture. Large scale foundation models built out of diffusions (Ho et al., 2020; Song et al., 2020) or flow-based transport (Lipman et al., 2022; Albergo & V anden-Eijnden, 2022; Albergo et al., 2023; Liu In this paradigm, performing generation amounts to numerically solving an ordinary or stochastic differential equation (ODE/SDE), the coefficients of which are learned neural networks.

Multi-view unsupervised feature selection (MUFS) has recently emerged as an effective dimensionality reduction method for unlabeled multi-view data. However, most existing methods mainly use first-order similarity graphs to preserve local structure, often overlooking the global structure that can be captured by second-order similarity. In addition, a few MUFS methods leverage predefined second-order similarity graphs, making them vulnerable to noise and outliers and resulting in suboptimal feature selection performance. In this paper, we propose a novel MUFS method, termed Structure-aware Hybrid-order sImilarity learNing for multi-viEw unsupervised Feature Selection (SHINE-FS), to address the aforementioned problem. SHINE-FS first learns consensus anchors and the corresponding anchor graph to capture the cross-view relationships between the anchors and the samples. Based on the acquired cross-view consensus information, it generates low-dimensional representations of the samples, which facilitate the reconstruction of multi-view data by identifying discriminative features. Subsequently, it employs the anchor-sample relationships to learn a second-order similarity graph. Furthermore, by jointly learning first-order and second-order similarity graphs, SHINE-FS constructs a hybrid-order similarity graph that captures both local and global structures, thereby revealing the intrinsic data structure to enhance feature selection. Comprehensive experimental results on real multi-view datasets show that SHINE-FS outperforms the state-of-the-art methods.