Vi-LAD: Vision-Language Attention Distillation for Socially-Aware Robot Navigation in Dynamic Environments

We introduce Vision-Language Attention Distillation (Vi-LAD), a novel approach for distilling socially compliant navigation knowledge from a large Vision-Language Model (VLM) into a lightweight transformer model for real-time robotic navigation. Unlike traditional methods that rely on expert demonstrations or human-annotated datasets, Vi-LAD performs knowledge distillation and fine-tuning at the intermediate layer representation level (i.e., attention maps) by leveraging the backbone of a pre-trained vision-action model. These attention maps highlight key navigational regions in a given scene, which serve as implicit guidance for socially aware motion planning. Vi-LAD fine-tunes a transformer-based model using intermediate attention maps extracted from the pre-trained vision-action model, combined with attention-like semantic maps constructed from a large VLM. To achieve this, we introduce a novel attention-level distillation loss that fuses knowledge from both sources, generating augmented attention maps with enhanced social awareness. These refined attention maps are then utilized as a traversability costmap within a socially aware model predictive controller (MPC) for navigation. We validate our approach through real-world experiments on a Husky wheeled robot, demonstrating significant improvements over state-of-the-art (SOTA) navigation methods. Our results show up to 14.2% - 50% improvement in success rate, which highlights the effectiveness of Vi-LAD in enabling socially compliant and efficient robot navigation.

AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning

We present a novel method, AutoSpatial, an efficient approach with structured spatial grounding to enhance VLMs' spatial reasoning. By combining minimal manual supervision with large-scale Visual Question-Answering (VQA) pairs auto-labeling, our approach tackles the challenge of VLMs' limited spatial understanding in social navigation tasks. By applying a hierarchical two-round VQA strategy during training, AutoSpatial achieves both global and detailed understanding of scenarios, demonstrating more accurate spatial perception, movement prediction, Chain of Thought (CoT) reasoning, final action, and explanation compared to other SOTA approaches. These five components are essential for comprehensive social navigation reasoning. Our approach was evaluated using both expert systems (GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet) that provided cross-validation scores and human evaluators who assigned relative rankings to compare model performances across four key aspects. Augmented by the enhanced spatial reasoning capabilities, AutoSpatial demonstrates substantial improvements by averaged cross-validation score from expert systems in: perception & prediction (up to 10.71%), reasoning (up to 16.26%), action (up to 20.50%), and explanation (up to 18.73%) compared to baseline models trained only on manually annotated data.

ProSE: Diffusion Priors for Speech Enhancement

Speech enhancement (SE) is the foundational task of enhancing the clarity and quality of speech in the presence of non-stationary additive noise. While deterministic deep learning models have been commonly employed for SE, recent research indicates that generative models, such as denoising diffusion probabilistic models (DDPMs), have shown promise. However, unlike speech generation, SE has a strong constraint in generating results in accordance with the underlying ground-truth signal. Additionally, for a wide variety of applications, SE systems need to be employed in real-time, and traditional diffusion models (DMs) requiring many iterations of a large model during inference are inefficient. To address these issues, we propose ProSE (diffusion-based Priors for SE), a novel methodology based on an alternative framework for applying diffusion models to SE. Specifically, we first apply DDPMs to generate priors in a latent space due to their powerful distribution mapping capabilities. The priors are then integrated into a transformer-based regression model for SE. The priors guide the regression model in the enhancement process. Since the diffusion process is applied to a compact latent space, the diffusion model takes fewer iterations than the traditional DM to obtain accurate estimations. Additionally, using a regression model for SE avoids the distortion issue caused by misaligned details generated by DMs. Our experiments show that ProSE achieves state-of-the-art performance on benchmark datasets with fewer computational costs.

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities

Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce Audio Flamingo 2 (AF2), an Audio-Language Model (ALM) with advanced audio understanding and reasoning capabilities. AF2 leverages (i) a custom CLAP model, (ii) synthetic Audio QA data for fine-grained audio reasoning, and (iii) a multi-stage curriculum learning strategy. AF2 achieves state-of-the-art performance with only a 3B parameter small language model, surpassing large open-source and proprietary models across over 20 benchmarks. Next, for the first time, we extend audio understanding to long audio segments (30 secs to 5 mins) and propose LongAudio, a large and novel dataset for training ALMs on long audio captioning and question-answering tasks. Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert annotated benchmark for evaluating ALMs on long audio understanding capabilities. We conduct extensive ablation studies to confirm the efficacy of our approach. Project Website: https://research.nvidia.com/labs/adlr/AF2/.

EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching

We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images, with their large fields of view, are particularly suited for dense matching techniques that aim to establish comprehensive correspondences across images. However, ERP images are subject to significant distortions, which we address by leveraging the spherical camera model and geodesic flow refinement in the dense matching method. To further mitigate these distortions, we propose spherical positional embeddings based on 3D Cartesian coordinates of the feature grid. Additionally, our method incorporates bidirectional transformations between spherical and Cartesian coordinate systems during refinement, utilizing a unit sphere to improve matching performance. We demonstrate that our proposed method achieves notable performance enhancements, with improvements of +26.72 and +42.62 in AUC@5{\deg} on the Matterport3D and Stanford2D3D datasets.

Towards Optimal Multi-draft Speculative Decoding

Large Language Models (LLMs) have become an indispensable part of natural language processing tasks. However, autoregressive sampling has become an efficiency bottleneck. Multi-Draft Speculative Decoding (MDSD) is a recent approach where, when generating each token, a small draft model generates multiple drafts, and the target LLM verifies them in parallel, ensuring that the final output conforms to the target model distribution. The two main design choices in MDSD are the draft sampling method and the verification algorithm. For a fixed draft sampling method, the optimal acceptance rate is a solution to an optimal transport problem, but the complexity of this problem makes it difficult to solve for the optimal acceptance rate and measure the gap between existing verification algorithms and the theoretical upper bound. This paper discusses the dual of the optimal transport problem, providing a way to efficiently compute the optimal acceptance rate. For the first time, we measure the theoretical upper bound of MDSD efficiency for vocabulary sizes in the thousands and quantify the gap between existing verification algorithms and this bound. We also compare different draft sampling methods based on their optimal acceptance rates. Our results show that the draft sampling method strongly influences the optimal acceptance rate, with sampling without replacement outperforming sampling with replacement. Additionally, existing verification algorithms do not reach the theoretical upper bound for both without replacement and with replacement sampling. Our findings suggest that carefully designed draft sampling methods can potentially improve the optimal acceptance rate and enable the development of verification algorithms that closely match the theoretical upper bound.

IM360: Textured Mesh Reconstruction for Large-scale Indoor Mapping with 360$^\circ$ Cameras

We present a novel 3D reconstruction pipeline for 360$^\circ$ cameras for 3D mapping and rendering of indoor environments. Traditional Structure-from-Motion (SfM) methods may not work well in large-scale indoor scenes due to the prevalence of textureless and repetitive regions. To overcome these challenges, our approach (IM360) leverages the wide field of view of omnidirectional images and integrates the spherical camera model into every core component of the SfM pipeline. In order to develop a comprehensive 3D reconstruction solution, we integrate a neural implicit surface reconstruction technique to generate high-quality surfaces from sparse input data. Additionally, we utilize a mesh-based neural rendering approach to refine texture maps and accurately capture view-dependent properties by combining diffuse and specular components. We evaluate our pipeline on large-scale indoor scenes from the Matterport3D and Stanford2D3D datasets. In practice, IM360 demonstrate superior performance in terms of textured mesh reconstruction over SOTA. We observe accuracy improvements in terms of camera localization and registration as well as rendering high frequency details.

V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation

We introduce V-Trans4Style, an innovative algorithm tailored for dynamic video content editing needs. It is designed to adapt videos to different production styles like documentaries, dramas, feature films, or a specific YouTube channel's video-making technique. Our algorithm recommends optimal visual transitions to help achieve this flexibility using a more bottom-up approach. We first employ a transformer-based encoder-decoder network to learn recommending temporally consistent and visually seamless sequences of visual transitions using only the input videos. We then introduce a style conditioning module that leverages this model to iteratively adjust the visual transitions obtained from the decoder through activation maximization. We demonstrate the efficacy of our method through experiments conducted on our newly introduced AutoTransition++ dataset. It is a 6k video version of AutoTransition Dataset that additionally categorizes its videos into different production style categories. Our encoder-decoder model outperforms the state-of-the-art transition recommendation method, achieving improvements of 10% to 80% in Recall@K and mean rank values over baseline. Our style conditioning module results in visual transitions that improve the capture of the desired video production style characteristics by an average of around 12% in comparison to other methods when measured with similarity metrics. We hope that our work serves as a foundation for exploring and understanding video production styles further.

AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs

With the rapid advancement of Multi-modal Large Language Models (MLLMs), several diagnostic benchmarks have recently been developed to assess these models' multi-modal reasoning proficiency. However, these benchmarks are restricted to assessing primarily the visual aspect and do not examine the holistic audio-visual (AV) understanding. Moreover, currently, there are no benchmarks that investigate the capabilities of AVLLMs to calibrate their responses when presented with perturbed inputs. To this end, we introduce Audio-Visual Trustworthiness assessment Benchmark (AVTrustBench), comprising 600K samples spanning over 9 meticulously crafted tasks, evaluating the capabilities of AVLLMs across three distinct dimensions: Adversarial attack, Compositional reasoning, and Modality-specific dependency. Using our benchmark we extensively evaluate 13 state-of-the-art AVLLMs. The findings reveal that the majority of existing models fall significantly short of achieving human-like comprehension, offering valuable insights for future research directions. To alleviate the limitations in the existing approaches, we further propose a robust, model-agnostic calibrated audio-visual preference optimization based training strategy CAVPref, obtaining a gain up to 30.19% across all 9 tasks. We will publicly release our code and benchmark to facilitate future research in this direction.

TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification

Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt Ensemble), a simple, training-free hard prompting method that boosts ALEs' zero-shot performance by customizing prompts for diverse audio classification tasks. Rather than using generic template-based prompts like "Sound of a car" we generate context-rich prompts, such as "Sound of a car coming from a tunnel". Specifically, we leverage label information to identify suitable sound attributes, such as "loud" and "feeble", and appropriate sound sources, such as "tunnel" and "street" and incorporate this information into the prompts used by Audio-Language Models (ALMs) for audio classification. Further, to enhance audio-text alignment, we perform prompt ensemble across TSPE-generated task-specific prompts. When evaluated on 12 diverse audio classification datasets, TSPE improves performance across ALMs by showing an absolute improvement of 1.23-16.36% over vanilla zero-shot evaluation.