Related papers: Relax Forcing: Relaxed KV-Memory for Consistent Lo…
The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural…
Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition generation on globally reconstructed 3D scenes by rendering…
Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…
In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…
Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory…
Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to…
Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion…
Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the…
Temporal sentence grounding in videos (TSGV) faces challenges due to public TSGV datasets containing significant temporal biases, which are attributed to the uneven temporal distributions of target moments. Existing methods generate…
Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing…
Video generation models have achieved notable progress in static scenarios, yet their performance in motion video generation remains limited, with quality degrading under drastic dynamic changes. This is due to noise disrupting temporal…
Interactive video generation has significant potential for scene simulation and video creation. However, existing methods often struggle with maintaining scene consistency during long video generation under dynamic camera control due to…
Video generation remains a challenging task due to spatiotemporal complexity and the requirement of synthesizing diverse motions with temporal consistency. Previous works attempt to generate videos in arbitrary lengths either in an…
Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures,…
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…
In this work, we propose Mutual Forcing, a framework for fast autoregressive audio-video generation with long-horizon audio-video synchronization. Our approach addresses two key challenges: joint audio-video modeling and fast autoregressive…
Recent advancements in diffusion models have significantly improved the realism and generalizability of character-driven animation, enabling the synthesis of high-quality motion from just a single RGB image and a set of driving poses.…
This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting…
Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies…
Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training…