High-quality, large-scale audio captioning is crucial for advancing audio understanding, yet current automated methods often generate captions that lack fine-grained detail and contextual accuracy, primarily due to their reliance on limited unimodal or superficial multimodal information. Drawing inspiration from human auditory perception, which adeptly integrates cross-modal cues and performs sophisticated auditory scene analysis, we introduce a novel two-stage automated pipeline. This pipeline first employs specialized pretrained models to extract diverse contextual cues (e.g., speech, music, general sounds, and visual information from associated video). A large language model (LLM) then synthesizes these rich, multimodal inputs to generate detailed and context-aware audio captions. Key contributions of this work include: (1) the proposed scalable method for fine-grained audio caption generation; (2) FusionAudio, a new large-scale dataset comprising 1.2 million such detailed captions, combined with 6 million QA pairs; and (3) enhanced audio models developed using FusionAudio, specifically a CLAP-based audio encoder with superior audio-text alignment and instruction following. This paper paves the way for more nuanced and accurate automated understanding of complex audio environments.
论文检索
输入标题、作者或关键词，从 2,006 篇学术成果中精准定位
RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference
PDF ↗The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs: requiring preprocessing, lacking global evaluation, violating query independence, or incurring high computational overhead. We present RRAttention, a novel dynamic sparse attention method that simultaneously achieves all desirable properties through a head **r**ound-**r**obin (RR) sampling strategy. By rotating query sampling positions across attention heads within each stride, RRAttention maintains query independence while enabling efficient global pattern discovery with stride-level aggregation. Our method reduces complexity from O(L^2) to O(L^2/S^2) and employs adaptive Top-\tau selection for optimal sparsity. Extensive experiments on natural language understanding (HELMET) and multimodal video comprehension (Video-MME) demonstrate that RRAttention recovers over 99% of full attention performance while computing only half of the attention blocks, achieving 2.4\times speedup at 128K context length and outperforming existing dynamic sparse attention methods. The code is available at [https://github.com/PaddlePaddle/PaddleFleet](https://github.com/PaddlePaddle/PaddleFleet) (see ‘Research/RRAttention‘).
See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
PDF ↗Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency due to autoregressive generation. Speculative Decoding (SD) mitigates this by applying a draft-and-verify paradigm, yet existing methods are constrained by rigid exact-match rules, severely limiting the acceleration potential. To bridge this gap, we propose LVSpec, the first training-free loosely SD framework tailored for Video-LLMs. Grounded in the insight that generation is governed by sparse visual-relevant anchors (mandating strictness) amidst abundant visual-irrelevant fillers (permitting loose verification), LVSpec employs a lightweight visual-relevant token identification scheme to accurately pinpoint the former. To further maximize acceptance, we augment this with a position-shift tolerant mechanism that effectively salvages positionally mismatched but semantically equivalent tokens. Experiments demonstrate that LVSpec is high-fidelity and rapid: it preserves >99.8% of target performance while accelerating Qwen2.5-VL-32B by 2.70 \times and LLaVA-OneVision-72B by 2.94 \times. Notably, it boosts the mean accepted length and speedup ratio by 136% and 35% compared to SOTA training-free SD methods for Video-LLMs. Code is provided in the submitted software.
Reinforcement Learning (RL) is crucial for empowering Video-LLMs with complex spatiotemporal reasoning. However, current RL paradigms predominantly rely on random data shuffling or naive curriculum strategies based on scalar difficulty metrics. We argue that scalar metrics fail to disentangle two orthogonal challenges in video understanding: Visual-Temporal Perception Load and Cognitive Reasoning Depth. To address this, we propose VideoCuRL, a novel framework that decomposes difficulty into these two axes. We employ efficient, training-free proxies—optical flow/keyframe entropy for visual complexity and Calibrated Surprisal for cognitive complexity—to map data onto a 2D curriculum grid. A competence-aware Diagonal Wavefront strategy then schedules training from base alignment to complex reasoning. Furthermore, we introduce Dynamic Sparse KL and Structured Revisiting to stabilize training against reward collapse and catastrophic forgetting. Extensive experiments show that VideoCuRL surpasses strong RL baselines on reasoning (+2.5% on VSI-Bench) and perception (+2.9% on VideoMME) tasks. Notably, VideoCuRL eliminates the prohibitive inference overhead of generation-based curricula, offering a scalable solution for robust video post-training.
Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches effectively enhance perception abilities, they primarily target holistic content understanding, often lacking explicit supervision for intrinsic temporal coherence and inter-frame correlations. This tendency limits the models’ ability to capture intricate dynamics and fine-grained visual causality. To explicitly bridge this gap, we propose a novel post-training objective: Masked Video Prediction (MVP). By requiring the model to reconstruct a masked continuous segment from a set of challenging distractors, MVP forces the model to attend to the sequential logic and temporal context of events. To support scalable training, we introduce a scalable data synthesis pipeline capable of transforming arbitrary video corpora into MVP training samples, and further employ Group Relative Policy Optimization (GRPO) with a fine-grained reward function to enhance the model’s understanding of video context and temporal properties. Comprehensive evaluations demonstrate that MVP enhances video reasoning capabilities by directly reinforcing temporal reasoning and causal understanding.
Sign Language Production (SLP) is the process of converting the complex input text into a real video. Most previous works focused on the Text2Gloss, Gloss2Pose, Pose2Vid stages, and some concentrated on Prompt2Gloss and Text2Avatar stages. However, this field has made slow progress due to the inaccuracy of text conversion, pose generation, and the rendering of poses into real human videos in these stages, resulting in gradually accumulating errors. Therefore, in this paper, we streamline the traditional redundant structure, simplify and optimize the task objective, and design a new sign language generative model called **Stable Signer**. It redefines the SLP task as a hierarchical generation end-to-end task that only includes text understanding (Prompt2Gloss, Text2Gloss) and Pose2Vid, and executes text understanding through our proposed new **S**ign **L**anguage **U**nderstanding **L**inker called **SLUL**, and generates hand gestures through the named **SLP-MoE** hand gesture rendering expert block to end-to-end generate high-quality and multi-style sign language videos. SLUL is trained using the newly developed **S**emantic-**A**ware **G**loss **M**asking Loss (**SAGM Loss**). Its performance has improved by 48.6% compared to the current SOTA generation methods, which is a significant increase in the SLP field. More demo can be obtained at [anonymous url](https://anonymoussubmissionurl.github.io/Stable-Signer).
Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models
PDF ↗Long-video understanding is bottlenecked by the high cost of processing massive visual tokens. Current reduction strategies often rely on static allocation or inefficient in-network selection that disrupts optimized attention kernels. In this paper, we introduce Vista-LLM, a decoupled framework for query-guided visual token pruning. By filtering redundancy prior to inference with minimal overhead, Vista-LLM ensures full compatibility with Flash Attention. Our method employs a coarse-to-fine pipeline: (1) Query-Guided Dynamic Budgeting for adaptive temporal allocation; (2) a lightweight Semantic Scout for fine-grained, query-specific selection; and (3) Structure-Aware Compensation to preserve global context. Extensive experiments on benchmarks like Video-MME and MLVU demonstrate a significantly improved Pareto frontier. Notably, on LLaVA-OneVision, Vista-LLM reduces visual tokens by 90% and accelerates inference while retaining over 98% of baseline performance on average, effectively filtering visual noise.
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
PDF ↗While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extremes: vision-centric methods that incur high latency and redundancy through dense visual accumulation, or text-centric approaches that suffer from detail loss and hallucination via aggressive captioning. To bridge this gap, we propose **MM-Mem**, a pyramidal multimodal memory architecture grounded in *Fuzzy-Trace Theory*. **MM-Mem** structures memory hierarchically into a *Sensory Buffer*, *Episodic Stream*, and *Symbolic Schema*, enabling the progressive distillation of fine-grained perceptual traces (*verbatim*) into high-level semantic schemas (*gist*).Furthermore, to govern the dynamic construction of memory, we derive a Semantic Information Bottleneck objective and introduce SIB-GRPO to optimize the trade-off between memory compression and task-relevant information retention.In inference, we design an entropy-driven top-down memory retrieval strategy.Extensive experiments across 4 benchmarks confirm that **MM-Mem** achieves state-of-the-art performance on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.Code and associated configurations are publicly available at ‘https://github.com/EliSpectre/MM-Mem‘.
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvement in offline video understanding. However, extending these capabilities to streaming video inputs, remains challenging, as existing models struggle to simultaneously maintain stable understanding performance, real-time responses, and low GPU memory overhead. To address this challenge, we propose HERMES, a novel training-free architecture for real-time and accurate understanding of video streams. Based on a mechanistic attention investigation, we conceptualize KV cache as a hierarchical memory framework that encapsulates video information across multiple granularities. During inference, HERMES reuses a compact KV cache, enabling efficient streaming understanding under resource constraints. Notably, HERMES requires no auxiliary computations upon the arrival of user queries, thereby guaranteeing real-time responses for continuous video stream interactions. HERMES achieves 10\times faster TTFT compared to prior SOTA. Even when reducing video tokens by up to 68% compared with uniform sampling, HERMES achieves superior or comparable accuracy across all benchmarks, with up to 11.4% gains on streaming datasets.
As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistency and reliability is of critical importance. However, sycophancy, the tendency of these models to align with user input even when it contradicts the visual evidence, undermines their trustworthiness in such contexts. Current sycophancy research has largely overlooked its specific manifestations in the video-language domain, resulting in a notable absence of systematic benchmarks and targeted evaluations to understand how Video-LLMs respond under misleading user input. To fill this gap, we propose ViSE (Video-LLM Sycophancy Benchmarking and Evaluation), the first benchmark designed to evaluate sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks. Specifically, ViSE pioneeringly brings linguistic perspectives on sycophancy into the video domain, enabling fine-grained analysis across multiple sycophancy types and interaction patterns. Furthermore, we propose two potential training-free mitigation strategies revealing potential paths for reducing sycophantic bias: (i) enhancing visual grounding through interpretable key-frame selection and (ii) steering model behavior away from sycophancy via targeted, inference-time intervention on its internal neural representations. Our code is available at https://github.com/William030422/Video-Sycophancy.
Understanding long videos remains challenging due to the sparsity of visual evidence relevant to a given query. Prior work has explored program-based visual grounding, typically relying on executable programs generated by auxiliary large language models. However, when scaling to long videos, existing approaches face several critical limitations: (1) frame-centric vision modules are often insufficient for long video processing; (2) naively applying program-based reasoning to all queries incurs considerable computational overhead; and (3) errors arising from low-confidence predictions and imperfect program execution are difficult to recover from. To address these challenges, we propose VideoPro, a unified framework that enables VideoLLMs to adaptively reason over long videos and refine their predictions through executable programs. VideoPro first performs adaptive reasoning, dynamically determining whether a query can be resolved directly by the native VideoLLM or requires explicit multi-step program reasoning. For complex queries, the model decomposes the task into executable programs that invoke specialized vision modules for precise temporal and semantic grounding. To further improve robustness, VideoPro incorporates a self-refinement mechanism that leverages execution feedback and confidence signals to correct erroneous executions and refine low-confidence reasoning programs. By tightly integrating adaptive reasoning with self-refinement, VideoPro consistently outperforms prior methods across multiple long-video understanding benchmarks, yielding an average 6.7% improvement for Qwen3-VL-8B.
Large Vision-Language Models (LVLMs) excel at visual understanding but face severe computational bottlenecks when processing high-resolution images and long videos due to massive visual token counts. Token pruning mitigates this by selectively removing less informative tokens while maintaining performance. However, existing methods vary widely in pruning location (vision encoder vs. LLM decoder), importance criteria (attention vs. similarity vs. learned scores), and application strategy, lacking systematic comparison. This survey presents the first comprehensive review of token pruning for LVLMs. We propose a taxonomy categorizing methods into vision-side, LLM-side, and hybrid paradigms, systematically analyze token selection mechanisms and pruning strategy. We further discuss evaluation protocols and identify key challenges including prompt-adaptive pruning and hardware-aware design. Our survey provides a structured foundation for this rapidly growing research area.
Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches rely solely on audio and text. This omits crucial visual cues, such as facial expressions and gestures, as well as broader conversational contexts, which are necessary for accurate prediction. In this paper, we introduce Context-Aware Multimodal Alignment for Backchannel Prediction (CAMA-BC), a novel framework that leverages visual information through Multi-layer Multimodal Alignment (MMA). Our alignment process comprises two stages. First, Context Alignment (MMA-CA) utilizes unlabeled dialogues with videos to capture conversational contexts. Next, Backchannel Alignment (MMA-BA) fine-tunes the representations specifically for backchannel prediction. Experimental results show that CAMA-BC significantly outperforms both existing methods and simple multimodal baselines, with particular effectiveness in recognizing complex backchannels such as empathy.
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
PDF ↗The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention on a single GPU, yielding limited acceleration or degraded performance and restricting LMMs from handling longer, more complex videos. To overcome these issues, we propose APB-V, a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. By distributing approximate attention, APB-V reduces computation and increases parallelism, enabling efficient processing of more visual embeddings without compression and thereby improving task performance. System-level optimizations, such as load balancing and fused forward passes, further unleash the potential of APB-V, delivering speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB, without notable performance loss.
VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels
PDF ↗Video anomaly understanding (VAU) is critical for real-world scenarios. Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies. However, progress in anomaly localization is still limited by two key issues. First, most existing video anomaly datasets only annotate segments that are clearly inconsistent with the context, often omitting subsequent segments that are semantically part of the same abnormal event. Second, the field lacks systematic evaluation protocols. To bridge these gaps, we introduce VALU, a new benchmark that explicitly defines anomalies across five semantic levels and provides comprehensive temporal boundaries and detailed textual descriptions for each. Based on these annotations, we design three evaluation tasks that comprehensively assess models’ capabilities across different dimensions, including temporal grounding, anomaly localization, and anomaly detail discrimination. Evaluation results reveal persistent challenges in current models’ capabilities on VAU. We further analyze and discuss these findings, and hope that both VALU and insights will advance research in VAU and the development of Video-LLMs. Our benchmark will be publicly available.
Reinforcement Learning · Deep RL
Long-form video understanding remains a formidable challenge due to the complexity of modeling long-range temporal dependencies and multi-event narratives. Existing methods often rely on static reasoning or external Visual-Language Models (VLMs), resulting in high computational complexity and sub-optimal performance. In this paper, we propose Video-MTR, a reinforced multi-turn reasoning framework that operates solely through data-efficient, pure RL post-training. Video-MTR reformulates video understanding as a dynamic decision-making process, where the agent iteratively selects key segments conditioned on the evolving context of previously processed frames and the query. To ensure effective intermediate reasoning and training stability, we introduce a novel gated bi-level reward system, which synergizes trajectory-level rewards (answer correctness) with turn-level rewards (frame-query relevance). This mechanism eliminates the need for data-intensive supervised fine-tuning, thereby substantially reducing reliance on large-scale datasets. Remarkably, Video-MTR achieves competitive or superior performance using only $\sim$8K training samples, compared to existing approaches that require 257K to 4.4M examples. Extensive experiments on benchmarks including VideoMME, MLVU, LongVideoBench, LVBench, and EgoSchema demonstrate that Video-MTR surpasses state-of-the-art methods in both accuracy and efficiency.
Applications · Computer Vision
Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded streams. Secondly, due to the high cost of collecting and training on unbounded streams, models must learn from short sequences while generalizing to long streams. Existing streaming VideoVLLMs fail to scale to unbounded video streams or focus on cache reuse strategies, leaving the impact of cache construction underexplored. In this paper, we propose Decoupled Streaming Cache(DSCache), a training-free cache construction mechanism that adapts pretrained offline models to streaming settings. DSCache maintains a cumulative past KV cache while constructing a separate instant cache on-demand, decoupled from past caches to preserve the informativeness of recent inputs. To enable position extrapolation beyond the training length, DSCache further incorporates a position-agnostic encoding strategy, ensuring KV caches to support unseen positions and preventing position overflow. Experiments on Streaming Video QA benchmarks demonstrate DSCache's state-of-the-art performance, with an average 2.5% accuracy gains over prior methods.
Applications · Computer Vision
Existing AI-driven video creation systems typically treat script drafting and key-shot design as two disjoint tasks: the former relies on large language models, while the latter depends on image generation models. We argue that these two tasks should be unified within a single framework, as logical reasoning and imaginative thinking are both fundamental qualities of a film director. In this work, we propose **UniMAGE**, a unified director model that bridges user prompts with well-structured scripts, thereby empowering non-experts to produce long-context, multi-shot films by leveraging existing audio–video generation models. To achieve this, we employ the Mixture-of-Transformers architecture that unifies text and image generation. To further enhance narrative logic and keyframe consistency, we introduce a ``first interleaving, then disentangling" training paradigm. Specifically, we first perform **Interleaved Concept Learning**, which utilizes interleaved text–image data to foster the model’s deeper understanding and imaginative interpretation of scripts. We then conduct **Disentangled Expert Learning**, which decouples script writing from keyframe generation, enabling greater flexibility and creativity in storytelling. Extensive experiments demonstrate that UniMAGE achieves state-of-the-art performance among open-source models, generating logically coherent scripts and visually consistent keyframe images.
Applications · Computer Vision
Existing referring video object segmentation (RVOS) is largely built on passive perception and assumes the target is already visible in the observed video, which limits real-world use when queries refer to objects beyond the current view. To address this gap, we introduce **Referring Video Active Exploration and Segmentation** (**RVAS**), a new task that focuses on reasoning about exploration policy and then locating and segmenting the object according to an input referring expression. To support RVAS, we build a large-scale dataset with manually annotated exploration actions and reference reasoning traces, enabling supervised training and evaluation. We benchmark representative RVOS and related video understanding baselines and find that they struggle to perform active target search and incur substantial overhead when coupled with online decision making. Motivated by these challenges, we propose LESA, a baseline framework that introduces a state controller and hierarchical memory for efficient streaming processing and sparse MLLM reasoning. LESA substantially reduces inference cost while maintaining competitive planning quality, and consistently improves segmentation accuracy on the RVAS dataset.
Applications · Computer Vision
Long video understanding faces a critical dilemma: cloud-based Large Multimodal Models (LMMs) offer superior reasoning but suffer from prohibitive bandwidth costs and latency, while edge-based solutions sacrifice perception accuracy for speed. Current collaborative approaches attempt to bridge this gap via similarity-based filtering, yet they treat complex queries as flat semantic vectors. We identify this as a fundamental flaw leading to "Semantic Submergence," where dominant visual features drown out subtle but logically critical cues. To solve this, we introduce SCOPE (Semantic Cloud-Orchestrated Perception at Edge). Shifting the paradigm to "Think in Cloud, Look at Edges," SCOPE utilizes a cloud LMM to decompose complex queries into a structured Directed Acyclic Graph (DAG). This "observation plan" guides the edge to retrieve evidence based on logical necessity rather than mere statistical similarity. Experiments on Video-MME and LongVideoBench demonstrate that SCOPE redefines the Pareto frontier, matching cloud-level accuracy with significantly lower transmission costs and outperforming state-of-the-art baselines on complex reasoning tasks.