Related papers: Stream-T1: Test-Time Scaling for Streaming Video G…

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine-tuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT)…

The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods…

Proactive streaming video understanding requires models to continuously process video streams and decide when to respond, rather than merely what to respond. This naturally introduces a decision-making problem under partial observations,…

Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…

As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies…

Diffusion transformers (DiT) have demonstrated exceptional performance in video generation. However, their large number of parameters and high computational complexity limit their deployment on edge devices. Quantization can reduce storage…

Existing matching-based approaches perform video object segmentation (VOS) via retrieving support features from a pixel-level memory, while some pixels may suffer from lack of correspondence in the memory (i.e., unseen), which inevitably…

We explore inference-time scaling in text-guided 3D diffusion models to enhance generative quality without additional training. To this end, we introduce ITS3D, a framework that formulates the task as an optimization problem to identify the…

While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods…

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete…

Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or search. Recent advances…

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…

To conduct real-time analytics computations, big data stream processing engines are required to process unbounded data streams at millions of events per second. However, current streaming engines exhibit low throughput and high tuple…

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we…

Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full…

With the rapid development of multimedia processing and deep learning technologies, especially in the field of video understanding, video quality assessment (VQA) has achieved significant progress. Although researchers have moved from…

The iterative and stochastic nature of diffusion models enables test-time scaling, whereby spending additional compute during denoising generates higher-fidelity samples. Increasing the number of denoising steps is the primary scaling axis,…