Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time. In this work, we present \textbf{Phys4D}, a pipeline for learning physics-consistent 4D world representations from video diffusion models. Phys4D adopts \textbf{a three-stage training paradigm} that progressively lifts appearance-driven video diffusion models into physics-consistent 4D world representations. We first bootstrap robust geometry and motion representations through large-scale pseudo-supervised pretraining, establishing a foundation for 4D scene modeling. We then perform physics-grounded supervised fine-tuning using simulation-generated data, enforcing temporally consistent 4D dynamics. Finally, we apply simulation-grounded reinforcement learning to correct residual physical violations that are difficult to capture through explicit supervision. To evaluate fine-grained physical consistency beyond appearance-based metrics, we introduce a set of \textbf{4D world consistency evaluation} that probe geometric coherence, motion stability, and long-horizon physical plausibility. Experimental results demonstrate that Phys4D substantially improves fine-grained spatiotemporal and physical consistency compared to appearance-driven baselines, while maintaining strong generative performance. Our project page is available at https://sensational-brioche-7657e7.netlify.app/

PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation

State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts rather than model limitations: manually adding physics details reliably produces physically plausible videos, but requires expertise and does not scale. We present PhyPrompt, a two-stage reinforcement learning framework that automatically refines prompts for physically realistic generation. First, we fine-tune a large language model on a physics-focused Chain-of-Thought dataset to integrate principles like object motion and force interactions while preserving user intent. Second, we apply Group Relative Policy Optimization with a dynamic reward curriculum that initially prioritizes semantic fidelity, then progressively shifts toward physical commonsense. This curriculum achieves synergistic optimization: PhyPrompt-7B reaches 40.8\% joint success on VideoPhy2 (8.6pp gain), improving physical commonsense by 11pp (55.8\% to 66.8\%) while simultaneously increasing semantic adherence by 4.4pp (43.4\% to 47.8\%). Remarkably, our curriculum exceeds single-objective training on both metrics, demonstrating compositional prompt discovery beyond conventional multi-objective trade-offs. PhyPrompt outperforms GPT-4o (+3.8\% joint) and DeepSeek-V3 (+2.2\%, 100$\times$ larger) using only 7B parameters. The approach transfers zero-shot across diverse T2V architectures (Lavie, VideoCrafter2, CogVideoX-5B) with up to 16.8\% improvement, establishing that domain-specialized reinforcement learning with compositional curricula surpasses general-purpose scaling for physics-aware generation.

Towards Sparse Video Understanding and Reasoning

We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames, \revise selects a small set of informative frames, maintains a summary-as-state across rounds, and stops early when confident. It supports proprietary vision-language models (VLMs) in a ``plug-and-play'' setting and enables reinforcement fine-tuning for open-source models. For fine-tuning, we introduce EAGER (Evidence-Adjusted Gain for Efficient Reasoning), an annotation-free reward with three terms: (1) Confidence gain: after new frames are added, we reward the increase in the log-odds gap between the correct option and the strongest alternative; (2) Summary sufficiency: at answer time we re-ask using only the last committed summary and reward success; (3) Correct-and-early stop: answering correctly within a small turn budget is rewarded. Across multiple VQA benchmarks, \revise improves accuracy while reducing frames, rounds, and prompt tokens, demonstrating practical sparse video reasoning.

SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models

Spatial perception is central to auditory intelligence, enabling accurate understanding of real-world acoustic scenes and advancing human-level perception of the world around us. While recent large audio-language models (LALMs) show strong reasoning over complex audios, most operate on monaural inputs and lack the ability to capture spatial cues such as direction, elevation, and distance. We introduce SPUR, a lightweight, plug-in approach that equips LALMs with spatial perception through minimal architectural changes. SPUR consists of: (i) a First-Order Ambisonics (FOA) encoder that maps (W, X, Y, Z) channels to rotation-aware, listener-centric spatial features, integrated into target LALMs via a multimodal adapter; and (ii) SPUR-Set, a spatial QA dataset combining open-source FOA recordings with controlled simulations, emphasizing relative direction, elevation, distance, and overlap for supervised spatial reasoning. Fine-tuning our model on the SPUR-Set consistently improves spatial QA and multi-speaker attribution while preserving general audio understanding. SPUR provides a simple recipe that transforms monaural LALMs into spatially aware models. Extensive ablations validate the effectiveness of our approach.

Transformation of audio embeddings into interpretable, concept-based representations

Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio representations. In this work, we explore the semantic interpretability of audio embeddings extracted from these neural networks by leveraging CLAP, a contrastive learning model that brings audio and text into a shared embedding space. We implement a post-hoc method to transform CLAP embeddings into concept-based, sparse representations with semantic interpretability. Qualitative and quantitative evaluations show that the concept-based representations outperform or match the performance of original audio embeddings on downstream tasks while providing interpretability. Additionally, we demonstrate that fine-tuning the concept-based representations can further improve their performance on downstream tasks. Lastly, we publish three audio-specific vocabularies for concept-based interpretability of audio embeddings.

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

The rapid proliferation of generative audio synthesis and editing technologies has raised significant concerns about copyright infringement, data provenance, and the spread of misinformation through deepfake audio. Watermarking offers a proactive solution by embedding imperceptible, identifiable, and traceable marks into audio content. While recent neural network-based watermarking methods like WavMark and AudioSeal have improved robustness and quality, they struggle to achieve both robust detection and accurate attribution simultaneously. This paper introduces Cross-Attention Robust Audio Watermark (XAttnMark), which bridges this gap by leveraging partial parameter sharing between the generator and the detector, a cross-attention mechanism for efficient message retrieval, and a temporal conditioning module for improved message distribution. Additionally, we propose a psychoacoustic-aligned temporal-frequency masking loss that captures fine-grained auditory masking effects, enhancing watermark imperceptibility. Our approach achieves state-of-the-art performance in both detection and attribution, demonstrating superior robustness against a wide range of audio transformations, including challenging generative editing with strong editing strength. The project webpage is available at https://liuyixin-louis.github.io/xattnmark/.

CiTrus: Squeezing Extra Performance out of Low-data Bio-signal Transfer Learning

Transfer learning for bio-signals has recently become an important technique to improve prediction performance on downstream tasks with small bio-signal datasets. Recent works have shown that pre-training a neural network model on a large dataset (e.g. EEG) with a self-supervised task, replacing the self-supervised head with a linear classification head, and fine-tuning the model on different downstream bio-signal datasets (e.g., EMG or ECG) can dramatically improve the performance on those datasets. In this paper, we propose a new convolution-transformer hybrid model architecture with masked auto-encoding for low-data bio-signal transfer learning, introduce a frequency-based masked auto-encoding task, employ a more comprehensive evaluation framework, and evaluate how much and when (multimodal) pre-training improves fine-tuning performance. We also introduce a dramatically more performant method of aligning a downstream dataset with a different temporal length and sampling rate to the original pre-training dataset. Our findings indicate that the convolution-only part of our hybrid model can achieve state-of-the-art performance on some low-data downstream tasks. The performance is often improved even further with our full model. In the case of transformer-based models we find that pre-training especially improves performance on downstream datasets, multimodal pre-training often increases those gains further, and our frequency-based pre-training performs the best on average for the lowest and highest data regimes.

Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos

A "match cut" is a common video editing technique where a pair of shots that have a similar composition transition fluidly from one to another. Although match cuts are often visual, certain match cuts involve the fluid transition of audio, where sounds from different sources merge into one indistinguishable transition between two shots. In this paper, we explore the ability to automatically find and create "audio match cuts" within videos and movies. We create a self-supervised audio representation for audio match cutting and develop a coarse-to-fine audio match pipeline that recommends matching shots and creates the blended audio. We further annotate a dataset for the proposed audio match cut task and compare the ability of multiple audio representations to find audio match cut candidates. Finally, we evaluate multiple methods to blend two matching audio candidates with the goal of creating a smooth transition. Project page and examples are available at: https://denfed.github.io/audiomatchcut/

RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text

In this work, we introduce a challenging task for simultaneously generating 3D holistic body motions and singing vocals directly from textual lyrics inputs, advancing beyond existing works that typically address these two modalities in isolation. To facilitate this, we first collect the RapVerse dataset, a large dataset containing synchronous rapping vocals, lyrics, and high-quality 3D holistic body meshes. With the RapVerse dataset, we investigate the extent to which scaling autoregressive multimodal transformers across language, audio, and motion can enhance the coherent and realistic generation of vocals and whole-body human motions. For modality unification, a vector-quantized variational autoencoder is employed to encode whole-body motion sequences into discrete motion tokens, while a vocal-to-unit model is leveraged to obtain quantized audio tokens preserving content, prosodic information, and singer identity. By jointly performing transformer modeling on these three modalities in a unified way, our framework ensures a seamless and realistic blend of vocals and human motions. Extensive experiments demonstrate that our unified generation framework not only produces coherent and realistic singing vocals alongside human motions directly from textual inputs but also rivals the performance of specialized single-modality generation systems, establishing new benchmarks for joint vocal-motion generation. The project page is available for research purposes at https://vis-www.cs.umass.edu/RapVerse.

DeepSpace: Dynamic Spatial and Source Cue Based Source Separation for Dialog Enhancement

Dialog Enhancement (DE) is a feature which allows a user to increase the level of dialog in TV or movie content relative to non-dialog sounds. When only the original mix is available, DE is "unguided," and requires source separation. In this paper, we describe the DeepSpace system, which performs source separation using both dynamic spatial cues and source cues to support unguided DE. Its technologies include spatio-level filtering (SLF) and deep-learning based dialog classification and denoising. Using subjective listening tests, we show that DeepSpace demonstrates significantly improved overall performance relative to state-of-the-art systems available for testing. We explore the feasibility of using existing automated metrics to evaluate unguided DE systems.