Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline

Accurately estimating humans' subjective feedback on video fluency, e.g., motion consistency and frame continuity, is crucial for various applications like streaming and gaming. Yet, it has long been overlooked, as prior arts have focused on solving it in the video quality assessment (VQA) task, merely as a sub-dimension of overall quality. In this work, we conduct pilot experiments and reveal that current VQA predictions largely underrepresent fluency, thereby limiting their applicability. To this end, we pioneer Video Fluency Assessment (VFA) as a standalone perceptual task focused on the temporal dimension. To advance VFA research, 1) we construct a fluency-oriented dataset, FluVid, comprising 4,606 in-the-wild videos with balanced fluency distribution, featuring the first-ever scoring criteria and human study for VFA. 2) We develop a large-scale benchmark of 23 methods, the most comprehensive one thus far on FluVid, gathering insights for VFA-tailored model designs. 3) We propose a baseline model called FluNet, which deploys temporal permuted self-attention (T-PSA) to enrich input fluency information and enhance long-range inter-frame interactions. Our work not only achieves state-of-the-art performance but, more importantly, offers the community a roadmap to explore solutions for VFA.

Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models

Although diffusion-based real-world image restoration (Real-IR) has achieved remarkable progress, efficiently leveraging ultra-large-scale pre-trained text-to-image (T2I) models and fully exploiting their potential remain significant challenges. To address this issue, we propose ResFlow-Tuner, an image restoration framework based on the state-of-the-art flow matching model, FLUX.1-dev, which integrates unified multi-modal fusion (UMMF) with test-time scaling (TTS) to achieve unprecedented restoration performance. Our approach fully leverages the advantages of the Multi-Modal Diffusion Transformer (MM-DiT) architecture by encoding multi-modal conditions into a unified sequence that guides the synthesis of high-quality images. Furthermore, we introduce a training-free test-time scaling paradigm tailored for image restoration. During inference, this technique dynamically steers the denoising direction through feedback from a reward model (RM), thereby achieving significant performance gains with controllable computational overhead. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple standard benchmarks. This work not only validates the powerful capabilities of the flow matching model in low-level vision tasks but, more importantly, proposes a novel and efficient inference-time scaling paradigm suitable for large pre-trained models.

ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration

Look-Up Table based methods have emerged as a promising direction for efficient image restoration tasks. Recent LUT-based methods focus on improving their performance by expanding the receptive field. However, they inevitably introduce extra computational and storage overhead, which hinders their deployment in edge devices. To address this issue, we propose ShiftLUT, a novel framework that attains the largest receptive field among all LUT-based methods while maintaining high efficiency. Our key insight lies in three complementary components. First, Learnable Spatial Shift module (LSS) is introduced to expand the receptive field by applying learnable, channel-wise spatial offsets on feature maps. Second, we propose an asymmetric dual-branch architecture that allocates more computation to the information-dense branch, substantially reducing inference latency without compromising restoration quality. Finally, we incorporate a feature-level LUT compression strategy called Error-bounded Adaptive Sampling (EAS) to minimize the storage overhead. Compared to the previous state-of-the-art method TinyLUT, ShiftLUT achieves a 3.8$\times$ larger receptive field and improves an average PSNR by over 0.21 dB across multiple standard benchmarks, while maintaining a small storage size and inference time. The code is available at: https://github.com/Sailor-t/ShiftLUT .

Equipping LLM with Directional Multi-Talker Speech Understanding Capabilities

Recent studies have demonstrated that prompting large language models (LLM) with audio encodings enables effective speech understanding capabilities. However, most speech LLMs are trained on single-channel, single-talker data, which makes it challenging to directly apply them to multi-talker and multi-channel speech understanding task. In this work, we present a comprehensive investigation on how to enable directional multi-talker speech understanding capabilities for LLMs, specifically in smart glasses usecase. We propose two novel approaches to integrate directivity into LLMs: (1) a cascaded system that leverages a source separation front-end module, and (2) an end-to-end system that utilizes serialized output training. All of the approaches utilize a multi-microphone array embedded in smart glasses to optimize directivity interpretation and processing in a streaming manner. Experimental results demonstrate the efficacy of our proposed methods in endowing LLMs with directional speech understanding capabilities, achieving strong performance in both speech recognition and speech translation tasks.

SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learning

Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this degradation is closely associated with the erosion of spatial inductive bias during RL adaptation, as sparse rewards and spatially agnostic exploration increasingly favor short-horizon visual cues. To address this issue, we propose \textbf{SA-VLA}, a spatially-aware RL adaptation framework that preserves spatial grounding during policy optimization by aligning representation learning, reward design, and exploration with task geometry. SA-VLA fuses implicit spatial representations with visual tokens, provides dense rewards that reflect geometric progress, and employs \textbf{SCAN}, a spatially-conditioned annealed exploration strategy tailored to flow-matching dynamics. Across challenging multi-object and cluttered manipulation benchmarks, SA-VLA enables stable RL fine-tuning and improves zero-shot spatial generalization, yielding more robust and transferable behaviors. Code and project page are available at https://xupan.top/Projects/savla.

InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior

Video inverse problems are fundamental to streaming, telepresence, and AR/VR, where high perceptual quality must coexist with tight latency constraints. Diffusion-based priors currently deliver state-of-the-art reconstructions, but existing approaches either adapt image diffusion models with ad hoc temporal regularizers - leading to temporal artifacts - or rely on native video diffusion models whose iterative posterior sampling is far too slow for real-time use. We introduce InstantViR, an amortized inference framework for ultra-fast video reconstruction powered by a pre-trained video diffusion prior. We distill a powerful bidirectional video diffusion model (teacher) into a causal autoregressive student that maps a degraded video directly to its restored version in a single forward pass, inheriting the teacher's strong temporal modeling while completely removing iterative test-time optimization. The distillation is prior-driven: it only requires the teacher diffusion model and known degradation operators, and does not rely on externally paired clean/noisy video data. To further boost throughput, we replace the video-diffusion backbone VAE with a high-efficiency LeanVAE via an innovative teacher-space regularized distillation scheme, enabling low-latency latent-space processing. Across streaming random inpainting, Gaussian deblurring and super-resolution, InstantViR matches or surpasses the reconstruction quality of diffusion-based baselines while running at over 35 FPS on NVIDIA A100 GPUs, achieving up to 100 times speedups over iterative video diffusion solvers. These results show that diffusion-based video reconstruction is compatible with real-time, interactive, editable, streaming scenarios, turning high-quality video restoration into a practical component of modern vision systems.

Multi-Channel Differential ASR for Robust Wearer Speech Recognition on Smart Glasses

With the growing adoption of wearable devices such as smart glasses for AI assistants, wearer speech recognition (WSR) is becoming increasingly critical to next-generation human-computer interfaces. However, in real environments, interference from side-talk speech remains a significant challenge to WSR and may cause accumulated errors for downstream tasks such as natural language processing. In this work, we introduce a novel multi-channel differential automatic speech recognition (ASR) method for robust WSR on smart glasses. The proposed system takes differential inputs from different frontends that complement each other to improve the robustness of WSR, including a beamformer, microphone selection, and a lightweight side-talk detection model. Evaluations on both simulated and real datasets demonstrate that the proposed system outperforms the traditional approach, achieving up to an 18.0% relative reduction in word error rate.

Generating Query-Relevant Document Summaries via Reinforcement Learning

E-commerce search engines often rely solely on product titles as input for ranking models with latency constraints. However, this approach can result in suboptimal relevance predictions, as product titles often lack sufficient detail to capture query intent. While product descriptions provide richer information, their verbosity and length make them unsuitable for real-time ranking, particularly for computationally expensive architectures like cross-encoder ranking models. To address this challenge, we propose ReLSum, a novel reinforcement learning framework designed to generate concise, query-relevant summaries of product descriptions optimized for search relevance. ReLSum leverages relevance scores as rewards to align the objectives of summarization and ranking, effectively overcoming limitations of prior methods, such as misaligned learning targets. The framework employs a trainable large language model (LLM) to produce summaries, which are then used as input for a cross-encoder ranking model. Experimental results demonstrate significant improvements in offline metrics, including recall and NDCG, as well as online user engagement metrics. ReLSum provides a scalable and efficient solution for enhancing search relevance in large-scale e-commerce systems.

Bridging Video Quality Scoring and Justification via Large Multimodal Models

Classical video quality assessment (VQA) methods generate a numerical score to judge a video's perceived visual fidelity and clarity. Yet, a score fails to describe the video's complex quality dimensions, restricting its applicability. Benefiting from the linguistic output, adapting video large multimodal models (LMMs) to VQA via instruction tuning has the potential to address this issue. The core of the approach lies in the video quality-centric instruction data. Previous explorations mainly focus on the image domain, and their data generation processes heavily rely on human quality annotations and proprietary systems, limiting data scalability and effectiveness. To address these challenges, we propose the Score-based Instruction Generation (SIG) pipeline. Specifically, SIG first scores multiple quality dimensions of an unlabeled video and maps scores to text-defined levels. It then explicitly incorporates a hierarchical Chain-of-Thought (CoT) to model the correlation between specific dimensions and overall quality, mimicking the human visual system's reasoning process. The automated pipeline eliminates the reliance on expert-written quality descriptions and proprietary systems, ensuring data scalability and generation efficiency. To this end, the resulting Score2Instruct (S2I) dataset contains over 320K diverse instruction-response pairs, laying the basis for instruction tuning. Moreover, to advance video LMMs' quality scoring and justification abilities simultaneously, we devise a progressive tuning strategy to fully unleash the power of S2I. Built upon SIG, we further curate a benchmark termed S2I-Bench with 400 open-ended questions to better evaluate the quality justification capacity of video LMMs. Experimental results on the S2I-Bench and existing benchmarks indicate that our method consistently improves quality scoring and justification capabilities across multiple video LMMs.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition

Recent studies have demonstrated that prompting large language models (LLM) with audio encodings enables effective speech recognition capabilities. However, the ability of Speech LLMs to comprehend and process multi-channel audio with spatial cues remains a relatively uninvestigated area of research. In this work, we present directional-SpeechLlama, a novel approach that leverages the microphone array of smart glasses to achieve directional speech recognition, source localization, and bystander cross-talk suppression. To enhance the model's ability to understand directivity, we propose two key techniques: serialized directional output training (S-DOT) and contrastive direction data augmentation (CDDA). Experimental results show that our proposed directional-SpeechLlama effectively captures the relationship between textual cues and spatial audio, yielding strong performance in both speech recognition and source localization tasks.